← Qwen3.8 27B W4A16 AutoRound · 64k ctx, DFlash2 speculative decoding
Run 83638382
| Kind | evals (quick) |
| Started | 2026-09-17 23:05 UTC |
| Duration | 66,776 s |
| Engine | vllm@bae2023ff (build 0.28.0) |
| Driver | 595.99.02 |
| Throttled | no |
| Command | lab eval qwen3.8-27b-w4a16-autoround-fast/64k-dflash2 --tier quick |
| Lab version | 0.1.0+80d380e |
Metrics
| Metric | Method | Prompt | Gen | Depth | Value | ± sd | Unit |
|---|
eval_allowance_tokens | aime_2025 | — | — | 0 | 43,718 | — | tokens |
eval_allowance_tokens | bfcl | — | — | 0 | 43,091 | — | tokens |
eval_allowance_tokens | gpqa_diamond | — | — | 0 | 43,698 | — | tokens |
eval_allowance_tokens | livecodebench | — | — | 0 | 43,628 | — | tokens |
eval_excluded | aime_2025 | — | — | 0 | 0.00 | — | count |
eval_excluded | bfcl | — | — | 0 | 0.00 | — | count |
eval_excluded | gpqa_diamond | — | — | 0 | 0.00 | — | count |
eval_excluded | livecodebench | — | — | 0 | 0.00 | — | count |
eval_length_stops | aime_2025 | — | — | 0 | 18.0 | — | count |
eval_length_stops | bfcl | — | — | 0 | 0.00 | — | count |
eval_length_stops | gpqa_diamond | — | — | 0 | 23.0 | — | count |
eval_length_stops | livecodebench | — | — | 0 | 32.0 | — | count |
eval_seconds_per_task | aime_2025 | — | — | 0 | 595 | — | s |
eval_seconds_per_task | bfcl | — | — | 0 | 8.00 | — | s |
eval_seconds_per_task | gpqa_diamond | — | — | 0 | 123 | — | s |
eval_seconds_per_task | livecodebench | — | — | 0 | 213 | — | s |
eval_tokens_per_task | aime_2025 | — | — | 0 | 77,822 | — | tokens |
eval_tokens_per_task | bfcl | — | — | 0 | 771 | — | tokens |
eval_tokens_per_task | gpqa_diamond | — | — | 0 | 14,524 | — | tokens |
eval_tokens_per_task | livecodebench | — | — | 0 | 23,164 | — | tokens |
Eval results
| Task | Metric | Value | ± se | Tasks | Attempts | Harness | Subset |
|---|
| AIME 2025 | mean accuracy | 82.5% | 6.0% | 30 | 4 | lab 0.1.0+80d380e | aime_2025_full:e0d01ea1cb74 |
| BFCL | accuracy | 87.5% | 1.7% | 400 | 1 | bfcl-eval 2026.3.23 native tool calls | bfcl_quick_400:6d45d3c92a1c |
| GPQA Diamond | accuracy | 81.8% | 2.7% | 198 | 1 | lab 0.1.0+80d380e | gpqa_diamond_full:a88f544639ca |
| LiveCodeBench | pass@1 | 60.0% | 4.9% | 100 | 1 | livecodebench 28fef95ea8c9f7a547c8329f2cd3d32b92c1fa24 | livecodebench_v6_newest100:7e85c832cec0 |
Raw
{
"bench": {
"n_prompt": 512,
"n_gen": 128,
"depths": [
0,
4096,
16384
],
"reps": 5,
"delay_s": 3,
"http_prompt_lengths": [
512,
4096
]
},
"benchmarks": [
"livecodebench",
"bfcl",
"gpqa_diamond",
"aime_2025"
],
"allowance": {
"speed_run_id": "372dd3de-ecf3-490a-bb3f-3ab38b37b6fd",
"pp0": 741.364,
"tg": [
{
"depth": 0,
"tps": 145.866
}
],
"ctx": 65536,
"limit_s": 300,
"headline_tokens": 42185
},
"sandbox_images": {
"livecodebench": {
"tag": "lab-livecodebench:b4d2e5fd3081",
"image_id": "sha256:bf9fe62701b4781138c193ec2ef79dd7adb0caea68bed7e9044be645841dbaf9",
"host": "alex@web"
},
"bfcl": {
"tag": "lab-bfcl:62e1f0090a9a",
"image_id": "sha256:6d68e65b0bf15aed74b4ce9fe84b03b10747c304cbdf50804122f5a7f94d2442",
"host": "alex@web"
}
},
"harness_options": {
"livecodebench": {},
"bfcl": {
"mode": "FC"
}
},
"props": {
"sampling": {
"temperature": 1,
"top_p": 0.95,
"top_k": 20
},
"sampling_source": "generation_config.json plus the launch's overrides (vLLM has no /props)",
"n_ctx": 65536,
"served_model": "qwen3.8-27b-w4a16-autoround-fast/64k-dflash2",
"total_slots": 8,
"build_info": "vllm 0.28.0 (bae2023ff)",
"chat_template_caps": {
"supports_tools": true,
"supports_tool_calls": true
}
},
"subsets": {
"livecodebench": {
"id": "livecodebench_v6_newest100:7e85c832cec0",
"name": "livecodebench_v6_newest100",
"source": {
"harness": "livecodebench",
"commit": "28fef95ea8c9f7a547c8329f2cd3d32b92c1fa24",
"scenario": "codegeneration",
"lm_style": "OpenAIChat",
"dataset": "livecodebench/code_generation_lite",
"revision": "0fe84c3912ea0c4d4a78037083943e8f0c4dd505",
"file": "test6.jsonl",
"timeout_per_test_s": 6,
"newest": 100,
"date_window": [
"2025-02-15T06:30:00",
"2025-04-06T00:00:00"
]
},
"n_tasks": 100
},
"bfcl": {
"id": "bfcl_quick_400:6d45d3c92a1c",
"name": "bfcl_quick_400",
"source": {
"harness": "bfcl-eval",
"harness_version": "2026.3.23",
"categories": [
"simple_python",
"multiple",
"parallel",
"parallel_multiple",
"multi_turn_base"
]
},
"n_tasks": 400
},
"gpqa_diamond": {
"id": "gpqa_diamond_full:a88f544639ca",
"name": "gpqa_diamond_full",
"source": {
"repo": "Idavidrein/gpqa",
"revision": "633f5ee89ab8ad4522a9f850766b73f62147ffdd",
"files": [
"gpqa_diamond.csv"
]
},
"n_tasks": 198
},
"aime_2025": {
"id": "aime_2025_full:e0d01ea1cb74",
"name": "aime_2025_full",
"source": {
"repo": "opencompass/AIME2025",
"revision": "a6ad95f611d72cf628a80b58bd0432ef6638f958",
"files": [
"aime2025-I.jsonl",
"aime2025-II.jsonl"
]
},
"n_tasks": 30
}
},
"proxy_stats": {
"livecodebench:livecodebench/3692#1": {
"requests": 1,
"prompt_tokens": 448,
"completion_tokens": 24734,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 207.774,
"budget_s": 170.17088006183513,
"last_prompt_tokens": 448
},
"livecodebench:livecodebench/3723#1": {
"requests": 1,
"prompt_tokens": 403,
"completion_tokens": 1170,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 7.647,
"budget_s": 8.564653046490418,
"last_prompt_tokens": 403
},
"livecodebench:livecodebench/3763#1": {
"requests": 1,
"prompt_tokens": 572,
"completion_tokens": 18368,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 158.537,
"budget_s": 126.69534388749469,
"last_prompt_tokens": 572
},
"livecodebench:livecodebench/3709#1": {
"requests": 1,
"prompt_tokens": 425,
"completion_tokens": 2767,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 20.01,
"budget_s": 19.542732778123273,
"last_prompt_tokens": 425
},
"livecodebench:livecodebench/3733#1": {
"requests": 1,
"prompt_tokens": 784,
"completion_tokens": 43605,
"allowance_tokens": 43605,
"length_stops": 1,
"errors": 0,
"seconds": 410.402,
"budget_s": 299.99626221617365,
"last_prompt_tokens": 784
},
"livecodebench:livecodebench/3771#1": {
"requests": 1,
"prompt_tokens": 461,
"completion_tokens": 43669,
"allowance_tokens": 43669,
"length_stops": 1,
"errors": 0,
"seconds": 423.104,
"budget_s": 299.99933766107216,
"last_prompt_tokens": 461
},
"livecodebench:livecodebench/3779#1": {
"requests": 1,
"prompt_tokens": 632,
"completion_tokens": 43635,
"allowance_tokens": 43635,
"length_stops": 1,
"errors": 0,
"seconds": 423.054,
"budget_s": 299.9969029423375,
"last_prompt_tokens": 632
},
"livecodebench:livecodebench/abc394_a#1": {
"requests": 1,
"prompt_tokens": 392,
"completion_tokens": 108,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 1.096,
"budget_s": 1.2691606831762896,
"last_prompt_tokens": 392
},
"livecodebench:livecodebench/abc394_b#1": {
"requests": 1,
"prompt_tokens": 425,
"completion_tokens": 276,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.815,
"budget_s": 2.46541524010893,
"last_prompt_tokens": 425
},
"livecodebench:livecodebench/abc394_c#1": {
"requests": 1,
"prompt_tokens": 682,
"completion_tokens": 30490,
"allowance_tokens": 43625,
"length_stops": 0,
"errors": 0,
"seconds": 282.034,
"budget_s": 209.94738953673294,
"last_prompt_tokens": 682
},
"livecodebench:livecodebench/abc394_d#1": {
"requests": 1,
"prompt_tokens": 674,
"completion_tokens": 6844,
"allowance_tokens": 43627,
"length_stops": 0,
"errors": 0,
"seconds": 63.142,
"budget_s": 47.828910738298134,
"last_prompt_tokens": 674
},
"livecodebench:livecodebench/abc394_e#1": {
"requests": 1,
"prompt_tokens": 898,
"completion_tokens": 34047,
"allowance_tokens": 43583,
"length_stops": 0,
"errors": 0,
"seconds": 301.995,
"budget_s": 234.62413920517747,
"last_prompt_tokens": 898
},
"livecodebench:livecodebench/abc394_f#1": {
"requests": 1,
"prompt_tokens": 685,
"completion_tokens": 31656,
"allowance_tokens": 43625,
"length_stops": 0,
"errors": 0,
"seconds": 295.446,
"budget_s": 217.9450741284451,
"last_prompt_tokens": 685
},
"livecodebench:livecodebench/abc394_g#1": {
"requests": 1,
"prompt_tokens": 1501,
"completion_tokens": 43464,
"allowance_tokens": 43464,
"length_stops": 1,
"errors": 0,
"seconds": 423.56,
"budget_s": 299.99675785237224,
"last_prompt_tokens": 1501
},
"livecodebench:livecodebench/3764#1": {
"requests": 1,
"prompt_tokens": 508,
"completion_tokens": 4713,
"allowance_tokens": 43659,
"length_stops": 0,
"errors": 0,
"seconds": 38.468,
"budget_s": 32.99570019191142,
"last_prompt_tokens": 508
},
"livecodebench:livecodebench/3768#1": {
"requests": 1,
"prompt_tokens": 577,
"completion_tokens": 741,
"allowance_tokens": 43646,
"length_stops": 0,
"errors": 0,
"seconds": 4.885,
"budget_s": 5.858300078504312,
"last_prompt_tokens": 577
},
"livecodebench:livecodebench/3781#1": {
"requests": 1,
"prompt_tokens": 635,
"completion_tokens": 43634,
"allowance_tokens": 43634,
"length_stops": 1,
"errors": 0,
"seconds": 415.653,
"budget_s": 299.9940939303312,
"last_prompt_tokens": 635
},
"livecodebench:livecodebench/arc193_a#1": {
"requests": 1,
"prompt_tokens": 1156,
"completion_tokens": 43532,
"allowance_tokens": 43532,
"length_stops": 1,
"errors": 0,
"seconds": 399.21,
"budget_s": 299.99758069464673,
"last_prompt_tokens": 1156
},
"livecodebench:livecodebench/arc193_b#1": {
"requests": 1,
"prompt_tokens": 932,
"completion_tokens": 43576,
"allowance_tokens": 43576,
"length_stops": 1,
"errors": 0,
"seconds": 405.12,
"budget_s": 299.9970816369511,
"last_prompt_tokens": 932
},
"livecodebench:livecodebench/arc193_d#1": {
"requests": 1,
"prompt_tokens": 1072,
"completion_tokens": 43548,
"allowance_tokens": 43548,
"length_stops": 1,
"errors": 0,
"seconds": 428.814,
"budget_s": 299.99396574441033,
"last_prompt_tokens": 1072
},
"livecodebench:livecodebench/abc395_a#1": {
"requests": 1,
"prompt_tokens": 520,
"completion_tokens": 150,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 1.237,
"budget_s": 1.72975091393534,
"last_prompt_tokens": 520
},
"livecodebench:livecodebench/abc395_b#1": {
"requests": 1,
"prompt_tokens": 833,
"completion_tokens": 2077,
"allowance_tokens": 43595,
"length_stops": 0,
"errors": 0,
"seconds": 14.812,
"budget_s": 15.362700755836928,
"last_prompt_tokens": 833
},
"livecodebench:livecodebench/abc395_c#1": {
"requests": 1,
"prompt_tokens": 514,
"completion_tokens": 7069,
"allowance_tokens": 43658,
"length_stops": 0,
"errors": 0,
"seconds": 53.424,
"budget_s": 49.15560394816284,
"last_prompt_tokens": 514
},
"livecodebench:livecodebench/abc395_e#1": {
"requests": 1,
"prompt_tokens": 1053,
"completion_tokens": 37248,
"allowance_tokens": 43552,
"length_stops": 0,
"errors": 0,
"seconds": 342.632,
"budget_s": 256.77801194105876,
"last_prompt_tokens": 1053
},
"livecodebench:livecodebench/abc395_f#1": {
"requests": 1,
"prompt_tokens": 981,
"completion_tokens": 39651,
"allowance_tokens": 43566,
"length_stops": 0,
"errors": 0,
"seconds": 349.96,
"budget_s": 273.1549177606984,
"last_prompt_tokens": 981
},
"livecodebench:livecodebench/3776#1": {
"requests": 1,
"prompt_tokens": 599,
"completion_tokens": 18141,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 143.984,
"budget_s": 125.17554040959145,
"last_prompt_tokens": 599
},
"livecodebench:livecodebench/3778#1": {
"requests": 1,
"prompt_tokens": 460,
"completion_tokens": 477,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 3.867,
"budget_s": 3.8906025648087237,
"last_prompt_tokens": 460
},
"livecodebench:livecodebench/3783#1": {
"requests": 1,
"prompt_tokens": 611,
"completion_tokens": 32958,
"allowance_tokens": 43639,
"length_stops": 0,
"errors": 0,
"seconds": 291.368,
"budget_s": 226.77125868951094,
"last_prompt_tokens": 611
},
"livecodebench:livecodebench/3785#1": {
"requests": 1,
"prompt_tokens": 574,
"completion_tokens": 1307,
"allowance_tokens": 43646,
"length_stops": 0,
"errors": 0,
"seconds": 8.847,
"budget_s": 9.734527159148978,
"last_prompt_tokens": 574
},
"livecodebench:livecodebench/3705#1": {
"requests": 1,
"prompt_tokens": 762,
"completion_tokens": 1509,
"allowance_tokens": 43609,
"length_stops": 0,
"errors": 0,
"seconds": 10.341,
"budget_s": 11.372946445984859,
"last_prompt_tokens": 762
},
"livecodebench:livecodebench/3722#1": {
"requests": 1,
"prompt_tokens": 450,
"completion_tokens": 18557,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 147.734,
"budget_s": 127.82649211058622,
"last_prompt_tokens": 450
},
"livecodebench:livecodebench/3770#1": {
"requests": 1,
"prompt_tokens": 595,
"completion_tokens": 43642,
"allowance_tokens": 43642,
"length_stops": 1,
"errors": 0,
"seconds": 423.321,
"budget_s": 299.9949841853428,
"last_prompt_tokens": 595
},
"livecodebench:livecodebench/3786#1": {
"requests": 1,
"prompt_tokens": 506,
"completion_tokens": 30876,
"allowance_tokens": 43660,
"length_stops": 0,
"errors": 0,
"seconds": 263.063,
"budget_s": 212.3562536649406,
"last_prompt_tokens": 506
},
"livecodebench:livecodebench/abc396_a#1": {
"requests": 1,
"prompt_tokens": 586,
"completion_tokens": 243,
"allowance_tokens": 43644,
"length_stops": 0,
"errors": 0,
"seconds": 1.885,
"budget_s": 2.4563474779260797,
"last_prompt_tokens": 586
},
"livecodebench:livecodebench/abc396_b#1": {
"requests": 1,
"prompt_tokens": 777,
"completion_tokens": 967,
"allowance_tokens": 43606,
"length_stops": 0,
"errors": 0,
"seconds": 7.487,
"budget_s": 7.6774403189465215,
"last_prompt_tokens": 777
},
"livecodebench:livecodebench/abc396_c#1": {
"requests": 1,
"prompt_tokens": 593,
"completion_tokens": 7332,
"allowance_tokens": 43643,
"length_stops": 0,
"errors": 0,
"seconds": 53.644,
"budget_s": 51.0651889821898,
"last_prompt_tokens": 593
},
"livecodebench:livecodebench/abc396_d#1": {
"requests": 1,
"prompt_tokens": 1019,
"completion_tokens": 3671,
"allowance_tokens": 43559,
"length_stops": 0,
"errors": 0,
"seconds": 27.787,
"budget_s": 26.541427536515627,
"last_prompt_tokens": 1019
},
"livecodebench:livecodebench/abc396_e#1": {
"requests": 1,
"prompt_tokens": 927,
"completion_tokens": 35689,
"allowance_tokens": 43577,
"length_stops": 0,
"errors": 0,
"seconds": 330.65,
"budget_s": 245.92016331631572,
"last_prompt_tokens": 927
},
"livecodebench:livecodebench/abc396_f#1": {
"requests": 1,
"prompt_tokens": 619,
"completion_tokens": 28957,
"allowance_tokens": 43638,
"length_stops": 0,
"errors": 0,
"seconds": 230.152,
"budget_s": 199.3527651983101,
"last_prompt_tokens": 619
},
"livecodebench:livecodebench/abc396_g#1": {
"requests": 1,
"prompt_tokens": 781,
"completion_tokens": 43606,
"allowance_tokens": 43606,
"length_stops": 1,
"errors": 0,
"seconds": 372.207,
"budget_s": 299.99907122817996,
"last_prompt_tokens": 781
},
"livecodebench:livecodebench/3759#1": {
"requests": 1,
"prompt_tokens": 690,
"completion_tokens": 5022,
"allowance_tokens": 43624,
"length_stops": 0,
"errors": 0,
"seconds": 39.16,
"budget_s": 35.35957625887858,
"last_prompt_tokens": 690
},
"livecodebench:livecodebench/3789#1": {
"requests": 1,
"prompt_tokens": 603,
"completion_tokens": 30365,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 262.877,
"budget_s": 208.9838782964619,
"last_prompt_tokens": 603
},
"livecodebench:livecodebench/3791#1": {
"requests": 1,
"prompt_tokens": 575,
"completion_tokens": 6351,
"allowance_tokens": 43646,
"length_stops": 0,
"errors": 0,
"seconds": 45.564,
"budget_s": 44.31555874671265,
"last_prompt_tokens": 575
},
"livecodebench:livecodebench/arc194_a#1": {
"requests": 1,
"prompt_tokens": 734,
"completion_tokens": 18140,
"allowance_tokens": 43615,
"length_stops": 0,
"errors": 0,
"seconds": 162.211,
"budget_s": 125.35078158615646,
"last_prompt_tokens": 734
},
"livecodebench:livecodebench/arc194_b#1": {
"requests": 1,
"prompt_tokens": 588,
"completion_tokens": 42225,
"allowance_tokens": 43644,
"length_stops": 0,
"errors": 0,
"seconds": 394.005,
"budget_s": 290.2711467258873,
"last_prompt_tokens": 588
},
"livecodebench:livecodebench/arc194_c#1": {
"requests": 1,
"prompt_tokens": 968,
"completion_tokens": 43569,
"allowance_tokens": 43569,
"length_stops": 1,
"errors": 0,
"seconds": 439.631,
"budget_s": 299.99765152888085,
"last_prompt_tokens": 968
},
"livecodebench:livecodebench/arc194_d#1": {
"requests": 1,
"prompt_tokens": 578,
"completion_tokens": 43646,
"allowance_tokens": 43646,
"length_stops": 1,
"errors": 0,
"seconds": 455.215,
"budget_s": 299.99947590804345,
"last_prompt_tokens": 578
},
"livecodebench:livecodebench/arc194_e#1": {
"requests": 1,
"prompt_tokens": 857,
"completion_tokens": 43591,
"allowance_tokens": 43591,
"length_stops": 1,
"errors": 0,
"seconds": 396.825,
"budget_s": 299.99875086509803,
"last_prompt_tokens": 857
},
"livecodebench:livecodebench/abc397_a#1": {
"requests": 1,
"prompt_tokens": 514,
"completion_tokens": 439,
"allowance_tokens": 43658,
"length_stops": 0,
"errors": 0,
"seconds": 3.361,
"budget_s": 3.7029282046722467,
"last_prompt_tokens": 514
},
"livecodebench:livecodebench/abc397_b#1": {
"requests": 1,
"prompt_tokens": 496,
"completion_tokens": 14285,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 121.573,
"budget_s": 98.60138594034669,
"last_prompt_tokens": 496
},
"livecodebench:livecodebench/abc397_c#1": {
"requests": 1,
"prompt_tokens": 648,
"completion_tokens": 1683,
"allowance_tokens": 43632,
"length_stops": 0,
"errors": 0,
"seconds": 11.647,
"budget_s": 12.412051481578928,
"last_prompt_tokens": 648
},
"livecodebench:livecodebench/abc397_d#1": {
"requests": 1,
"prompt_tokens": 472,
"completion_tokens": 25301,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 190.847,
"budget_s": 174.0903821064342,
"last_prompt_tokens": 472
},
"livecodebench:livecodebench/abc397_e#1": {
"requests": 1,
"prompt_tokens": 597,
"completion_tokens": 43642,
"allowance_tokens": 43642,
"length_stops": 1,
"errors": 0,
"seconds": 437.045,
"budget_s": 299.9976819154727,
"last_prompt_tokens": 597
},
"livecodebench:livecodebench/abc397_f#1": {
"requests": 1,
"prompt_tokens": 628,
"completion_tokens": 43636,
"allowance_tokens": 43636,
"length_stops": 1,
"errors": 0,
"seconds": 417.16,
"budget_s": 299.9983630892789,
"last_prompt_tokens": 628
},
"livecodebench:livecodebench/abc397_g#1": {
"requests": 1,
"prompt_tokens": 606,
"completion_tokens": 43640,
"allowance_tokens": 43640,
"length_stops": 1,
"errors": 0,
"seconds": 406.651,
"budget_s": 299.99611048665486,
"last_prompt_tokens": 606
},
"livecodebench:livecodebench/3784#1": {
"requests": 1,
"prompt_tokens": 651,
"completion_tokens": 33039,
"allowance_tokens": 43631,
"length_stops": 0,
"errors": 0,
"seconds": 302.296,
"budget_s": 227.38051747539984,
"last_prompt_tokens": 651
},
"livecodebench:livecodebench/3799#1": {
"requests": 1,
"prompt_tokens": 493,
"completion_tokens": 1044,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 7.731,
"budget_s": 7.822244394992156,
"last_prompt_tokens": 493
},
"livecodebench:livecodebench/3750#1": {
"requests": 1,
"prompt_tokens": 561,
"completion_tokens": 3558,
"allowance_tokens": 43649,
"length_stops": 0,
"errors": 0,
"seconds": 27.084,
"budget_s": 25.14896372304802,
"last_prompt_tokens": 561
},
"livecodebench:livecodebench/3788#1": {
"requests": 1,
"prompt_tokens": 469,
"completion_tokens": 4622,
"allowance_tokens": 43667,
"length_stops": 0,
"errors": 0,
"seconds": 36.371,
"budget_s": 32.31923419907617,
"last_prompt_tokens": 469
},
"livecodebench:livecodebench/3795#1": {
"requests": 1,
"prompt_tokens": 957,
"completion_tokens": 17156,
"allowance_tokens": 43571,
"length_stops": 0,
"errors": 0,
"seconds": 148.644,
"budget_s": 118.9056610097251,
"last_prompt_tokens": 957
},
"livecodebench:livecodebench/3801#1": {
"requests": 1,
"prompt_tokens": 331,
"completion_tokens": 43694,
"allowance_tokens": 43694,
"length_stops": 1,
"errors": 0,
"seconds": 387.763,
"budget_s": 299.9953753826589,
"last_prompt_tokens": 331
},
"livecodebench:livecodebench/abc398_a#1": {
"requests": 1,
"prompt_tokens": 311,
"completion_tokens": 1020,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 7.207,
"budget_s": 7.412216380346987,
"last_prompt_tokens": 311
},
"livecodebench:livecodebench/abc398_b#1": {
"requests": 1,
"prompt_tokens": 512,
"completion_tokens": 1497,
"allowance_tokens": 43659,
"length_stops": 0,
"errors": 0,
"seconds": 11.519,
"budget_s": 10.95346289333771,
"last_prompt_tokens": 512
},
"livecodebench:livecodebench/abc398_c#1": {
"requests": 1,
"prompt_tokens": 536,
"completion_tokens": 596,
"allowance_tokens": 43654,
"length_stops": 0,
"errors": 0,
"seconds": 3.887,
"budget_s": 4.808933566678182,
"last_prompt_tokens": 536
},
"livecodebench:livecodebench/abc398_d#1": {
"requests": 1,
"prompt_tokens": 927,
"completion_tokens": 23586,
"allowance_tokens": 43577,
"length_stops": 0,
"errors": 0,
"seconds": 198.489,
"budget_s": 162.9467493610417,
"last_prompt_tokens": 927
},
"livecodebench:livecodebench/abc398_f#1": {
"requests": 1,
"prompt_tokens": 341,
"completion_tokens": 18494,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 148.766,
"budget_s": 127.2475625648372,
"last_prompt_tokens": 341
},
"livecodebench:livecodebench/abc398_g#1": {
"requests": 1,
"prompt_tokens": 753,
"completion_tokens": 43611,
"allowance_tokens": 43611,
"length_stops": 1,
"errors": 0,
"seconds": 453.637,
"budget_s": 299.9955810423674,
"last_prompt_tokens": 753
},
"livecodebench:livecodebench/3744#1": {
"requests": 1,
"prompt_tokens": 707,
"completion_tokens": 25415,
"allowance_tokens": 43620,
"length_stops": 0,
"errors": 0,
"seconds": 209.216,
"budget_s": 175.18890461762254,
"last_prompt_tokens": 707
},
"livecodebench:livecodebench/3794#1": {
"requests": 1,
"prompt_tokens": 730,
"completion_tokens": 37650,
"allowance_tokens": 43616,
"length_stops": 0,
"errors": 0,
"seconds": 325.458,
"budget_s": 259.0982826199392,
"last_prompt_tokens": 730
},
"livecodebench:livecodebench/3809#1": {
"requests": 1,
"prompt_tokens": 505,
"completion_tokens": 1582,
"allowance_tokens": 43660,
"length_stops": 0,
"errors": 0,
"seconds": 10.048,
"budget_s": 11.526747449979203,
"last_prompt_tokens": 505
},
"livecodebench:livecodebench/3817#1": {
"requests": 1,
"prompt_tokens": 407,
"completion_tokens": 213,
"allowance_tokens": 43679,
"length_stops": 0,
"errors": 0,
"seconds": 1.722,
"budget_s": 2.0092324152689343,
"last_prompt_tokens": 407
},
"livecodebench:livecodebench/arc195_a#1": {
"requests": 1,
"prompt_tokens": 549,
"completion_tokens": 20935,
"allowance_tokens": 43651,
"length_stops": 0,
"errors": 0,
"seconds": 169.378,
"budget_s": 144.2626636763014,
"last_prompt_tokens": 549
},
"livecodebench:livecodebench/arc195_b#1": {
"requests": 1,
"prompt_tokens": 715,
"completion_tokens": 43619,
"allowance_tokens": 43619,
"length_stops": 1,
"errors": 0,
"seconds": 429.391,
"budget_s": 299.99916902750897,
"last_prompt_tokens": 715
},
"livecodebench:livecodebench/arc195_c#1": {
"requests": 1,
"prompt_tokens": 980,
"completion_tokens": 43566,
"allowance_tokens": 43566,
"length_stops": 1,
"errors": 0,
"seconds": 389.007,
"budget_s": 299.9932710880567,
"last_prompt_tokens": 980
},
"livecodebench:livecodebench/arc195_d#1": {
"requests": 1,
"prompt_tokens": 717,
"completion_tokens": 43618,
"allowance_tokens": 43618,
"length_stops": 1,
"errors": 0,
"seconds": 428.762,
"budget_s": 299.9950111504377,
"last_prompt_tokens": 717
},
"livecodebench:livecodebench/arc195_e#1": {
"requests": 1,
"prompt_tokens": 980,
"completion_tokens": 43566,
"allowance_tokens": 43566,
"length_stops": 1,
"errors": 0,
"seconds": 367.295,
"budget_s": 299.9932710880567,
"last_prompt_tokens": 980
},
"livecodebench:livecodebench/abc399_a#1": {
"requests": 1,
"prompt_tokens": 441,
"completion_tokens": 242,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 1.574,
"budget_s": 2.253906436309467,
"last_prompt_tokens": 441
},
"livecodebench:livecodebench/abc399_b#1": {
"requests": 1,
"prompt_tokens": 821,
"completion_tokens": 365,
"allowance_tokens": 43598,
"length_stops": 0,
"errors": 0,
"seconds": 2.944,
"budget_s": 3.6097148467234916,
"last_prompt_tokens": 821
},
"livecodebench:livecodebench/abc399_c#1": {
"requests": 1,
"prompt_tokens": 527,
"completion_tokens": 2104,
"allowance_tokens": 43656,
"length_stops": 0,
"errors": 0,
"seconds": 14.726,
"budget_s": 15.135049440397516,
"last_prompt_tokens": 527
},
"livecodebench:livecodebench/abc399_d#1": {
"requests": 1,
"prompt_tokens": 860,
"completion_tokens": 43590,
"allowance_tokens": 43590,
"length_stops": 1,
"errors": 0,
"seconds": 397.131,
"budget_s": 299.99594185309167,
"last_prompt_tokens": 860
},
"livecodebench:livecodebench/abc399_e#1": {
"requests": 1,
"prompt_tokens": 589,
"completion_tokens": 43643,
"allowance_tokens": 43643,
"length_stops": 1,
"errors": 0,
"seconds": 451.417,
"budget_s": 299.9937466021544,
"last_prompt_tokens": 589
},
"livecodebench:livecodebench/abc399_f#1": {
"requests": 1,
"prompt_tokens": 557,
"completion_tokens": 12671,
"allowance_tokens": 43650,
"length_stops": 0,
"errors": 0,
"seconds": 93.407,
"budget_s": 87.61871668668418,
"last_prompt_tokens": 557
},
"livecodebench:livecodebench/3765#1": {
"requests": 1,
"prompt_tokens": 775,
"completion_tokens": 36135,
"allowance_tokens": 43607,
"length_stops": 0,
"errors": 0,
"seconds": 308.878,
"budget_s": 248.77273663814958,
"last_prompt_tokens": 775
},
"livecodebench:livecodebench/3805#1": {
"requests": 1,
"prompt_tokens": 739,
"completion_tokens": 43614,
"allowance_tokens": 43614,
"length_stops": 1,
"errors": 0,
"seconds": 405.38,
"budget_s": 299.9972637530617,
"last_prompt_tokens": 739
},
"livecodebench:livecodebench/3811#1": {
"requests": 1,
"prompt_tokens": 462,
"completion_tokens": 240,
"allowance_tokens": 43668,
"length_stops": 0,
"errors": 0,
"seconds": 2.063,
"budget_s": 2.268521388270829,
"last_prompt_tokens": 462
},
"livecodebench:livecodebench/3717#1": {
"requests": 1,
"prompt_tokens": 654,
"completion_tokens": 40479,
"allowance_tokens": 43631,
"length_stops": 0,
"errors": 0,
"seconds": 350.264,
"budget_s": 278.3902816470004,
"last_prompt_tokens": 654
},
"livecodebench:livecodebench/3793#1": {
"requests": 1,
"prompt_tokens": 450,
"completion_tokens": 16787,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 141.148,
"budget_s": 115.69206736458646,
"last_prompt_tokens": 450
},
"livecodebench:livecodebench/3832#1": {
"requests": 1,
"prompt_tokens": 608,
"completion_tokens": 4014,
"allowance_tokens": 43640,
"length_stops": 0,
"errors": 0,
"seconds": 32.918,
"budget_s": 28.338517264815124,
"last_prompt_tokens": 608
},
"livecodebench:livecodebench/abc400_a#1": {
"requests": 1,
"prompt_tokens": 366,
"completion_tokens": 299,
"allowance_tokens": 43687,
"length_stops": 0,
"errors": 0,
"seconds": 2.166,
"budget_s": 2.543511166903788,
"last_prompt_tokens": 366
},
"livecodebench:livecodebench/abc400_b#1": {
"requests": 1,
"prompt_tokens": 479,
"completion_tokens": 921,
"allowance_tokens": 43665,
"length_stops": 0,
"errors": 0,
"seconds": 6.628,
"budget_s": 6.960120598344109,
"last_prompt_tokens": 479
},
"livecodebench:livecodebench/abc400_c#1": {
"requests": 1,
"prompt_tokens": 446,
"completion_tokens": 11864,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 85.73,
"budget_s": 81.93651765316471,
"last_prompt_tokens": 446
},
"livecodebench:livecodebench/abc400_d#1": {
"requests": 1,
"prompt_tokens": 1396,
"completion_tokens": 43485,
"allowance_tokens": 43485,
"length_stops": 1,
"errors": 0,
"seconds": 454.076,
"budget_s": 299.99909477177783,
"last_prompt_tokens": 1396
},
"livecodebench:livecodebench/abc400_e#1": {
"requests": 1,
"prompt_tokens": 608,
"completion_tokens": 31384,
"allowance_tokens": 43640,
"length_stops": 0,
"errors": 0,
"seconds": 258.398,
"budget_s": 215.97648635973786,
"last_prompt_tokens": 608
},
"livecodebench:livecodebench/abc400_g#1": {
"requests": 1,
"prompt_tokens": 1138,
"completion_tokens": 43535,
"allowance_tokens": 43535,
"length_stops": 1,
"errors": 0,
"seconds": 457.967,
"budget_s": 299.9938679450813,
"last_prompt_tokens": 1138
},
"livecodebench:livecodebench/3773#1": {
"requests": 1,
"prompt_tokens": 404,
"completion_tokens": 6692,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 51.61,
"budget_s": 46.422664876194126,
"last_prompt_tokens": 404
},
"livecodebench:livecodebench/3777#1": {
"requests": 1,
"prompt_tokens": 700,
"completion_tokens": 43622,
"allowance_tokens": 43622,
"length_stops": 1,
"errors": 0,
"seconds": 410.242,
"budget_s": 299.99950287313834,
"last_prompt_tokens": 700
},
"livecodebench:livecodebench/arc196_a#1": {
"requests": 1,
"prompt_tokens": 517,
"completion_tokens": 43658,
"allowance_tokens": 43658,
"length_stops": 1,
"errors": 0,
"seconds": 410.611,
"budget_s": 299.99946242549606,
"last_prompt_tokens": 517
},
"livecodebench:livecodebench/arc196_b#1": {
"requests": 1,
"prompt_tokens": 1098,
"completion_tokens": 43543,
"allowance_tokens": 43543,
"length_stops": 1,
"errors": 0,
"seconds": 397.15,
"budget_s": 299.994758200093,
"last_prompt_tokens": 1098
},
"livecodebench:livecodebench/arc196_c#1": {
"requests": 1,
"prompt_tokens": 775,
"completion_tokens": 43607,
"allowance_tokens": 43607,
"length_stops": 1,
"errors": 0,
"seconds": 423.401,
"budget_s": 299.99783364499143,
"last_prompt_tokens": 775
},
"livecodebench:livecodebench/arc196_d#1": {
"requests": 1,
"prompt_tokens": 1052,
"completion_tokens": 43552,
"allowance_tokens": 43552,
"length_stops": 1,
"errors": 0,
"seconds": 443.899,
"budget_s": 299.99441087191616,
"last_prompt_tokens": 1052
},
"bfcl:simple_python_3#1": {
"requests": 1,
"prompt_tokens": 405,
"completion_tokens": 107,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 0.978,
"budget_s": 1.2798403218193064,
"last_prompt_tokens": 405
},
"bfcl:multiple_0#1": {
"requests": 1,
"prompt_tokens": 745,
"completion_tokens": 166,
"allowance_tokens": 43613,
"length_stops": 0,
"errors": 0,
"seconds": 1.489,
"budget_s": 2.1429352687636483,
"last_prompt_tokens": 745
},
"bfcl:parallel_0#1": {
"requests": 1,
"prompt_tokens": 399,
"completion_tokens": 173,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 1.147,
"budget_s": 1.7242172067042674,
"last_prompt_tokens": 399
},
"bfcl:parallel_multiple_0#1": {
"requests": 1,
"prompt_tokens": 530,
"completion_tokens": 388,
"allowance_tokens": 43655,
"length_stops": 0,
"errors": 0,
"seconds": 2.564,
"budget_s": 3.3748740784535767,
"last_prompt_tokens": 530
},
"bfcl:multi_turn_base_0#1": {
"requests": 19,
"prompt_tokens": 125142,
"completion_tokens": 2991,
"allowance_tokens": 763147,
"length_stops": 0,
"errors": 0,
"seconds": 40.662,
"budget_s": 46.0876959601244,
"last_prompt_tokens": 8131
},
"bfcl:simple_python_6#1": {
"requests": 1,
"prompt_tokens": 395,
"completion_tokens": 261,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 1.784,
"budget_s": 2.3221151801439524,
"last_prompt_tokens": 395
},
"bfcl:multiple_9#1": {
"requests": 1,
"prompt_tokens": 568,
"completion_tokens": 110,
"allowance_tokens": 43648,
"length_stops": 0,
"errors": 0,
"seconds": 1.041,
"budget_s": 1.5202721490069973,
"last_prompt_tokens": 568
},
"bfcl:parallel_5#1": {
"requests": 1,
"prompt_tokens": 457,
"completion_tokens": 314,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 2.24,
"budget_s": 2.7690919958297626,
"last_prompt_tokens": 457
},
"bfcl:parallel_multiple_1#1": {
"requests": 1,
"prompt_tokens": 646,
"completion_tokens": 132,
"allowance_tokens": 43632,
"length_stops": 0,
"errors": 0,
"seconds": 1.155,
"budget_s": 1.7763069824967332,
"last_prompt_tokens": 646
},
"bfcl:multi_turn_base_5#1": {
"requests": 20,
"prompt_tokens": 128901,
"completion_tokens": 2523,
"allowance_tokens": 805551,
"length_stops": 0,
"errors": 0,
"seconds": 33.524,
"budget_s": 43.115323176359155,
"last_prompt_tokens": 7990
},
"bfcl:simple_python_11#1": {
"requests": 1,
"prompt_tokens": 384,
"completion_tokens": 132,
"allowance_tokens": 43684,
"length_stops": 0,
"errors": 0,
"seconds": 1.204,
"budget_s": 1.42290433548393,
"last_prompt_tokens": 384
},
"bfcl:multiple_11#1": {
"requests": 1,
"prompt_tokens": 723,
"completion_tokens": 102,
"allowance_tokens": 43617,
"length_stops": 0,
"errors": 0,
"seconds": 1.123,
"budget_s": 1.6745013764627852,
"last_prompt_tokens": 723
},
"bfcl:parallel_8#1": {
"requests": 1,
"prompt_tokens": 423,
"completion_tokens": 246,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.484,
"budget_s": 2.2570492939451676,
"last_prompt_tokens": 423
},
"bfcl:parallel_multiple_2#1": {
"requests": 1,
"prompt_tokens": 566,
"completion_tokens": 307,
"allowance_tokens": 43648,
"length_stops": 0,
"errors": 0,
"seconds": 2.314,
"budget_s": 2.8681290374997,
"last_prompt_tokens": 566
},
"bfcl:multi_turn_base_7#1": {
"requests": 8,
"prompt_tokens": 44233,
"completion_tokens": 1251,
"allowance_tokens": 334934,
"length_stops": 0,
"errors": 0,
"seconds": 18.078999999999997,
"budget_s": 22.918846844060475,
"last_prompt_tokens": 6269
},
"bfcl:simple_python_17#1": {
"requests": 1,
"prompt_tokens": 374,
"completion_tokens": 71,
"allowance_tokens": 43686,
"length_stops": 0,
"errors": 0,
"seconds": 0.661,
"budget_s": 0.9912236455656682,
"last_prompt_tokens": 374
},
"bfcl:multiple_12#1": {
"requests": 1,
"prompt_tokens": 791,
"completion_tokens": 252,
"allowance_tokens": 43604,
"length_stops": 0,
"errors": 0,
"seconds": 2.173,
"budget_s": 2.7945652810477926,
"last_prompt_tokens": 791
},
"bfcl:parallel_10#1": {
"requests": 1,
"prompt_tokens": 400,
"completion_tokens": 183,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 1.332,
"budget_s": 1.7941221437804997,
"last_prompt_tokens": 400
},
"bfcl:parallel_multiple_4#1": {
"requests": 1,
"prompt_tokens": 560,
"completion_tokens": 324,
"allowance_tokens": 43649,
"length_stops": 0,
"errors": 0,
"seconds": 2.122,
"budget_s": 2.9765811695293003,
"last_prompt_tokens": 560
},
"bfcl:multi_turn_base_11#1": {
"requests": 7,
"prompt_tokens": 38132,
"completion_tokens": 991,
"allowance_tokens": 294273,
"length_stops": 0,
"errors": 0,
"seconds": 14.938,
"budget_s": 19.55417025059872,
"last_prompt_tokens": 5991
},
"bfcl:simple_python_22#1": {
"requests": 1,
"prompt_tokens": 378,
"completion_tokens": 106,
"allowance_tokens": 43685,
"length_stops": 0,
"errors": 0,
"seconds": 0.897,
"budget_s": 1.236565357864949,
"last_prompt_tokens": 378
},
"bfcl:multiple_17#1": {
"requests": 1,
"prompt_tokens": 707,
"completion_tokens": 126,
"allowance_tokens": 43620,
"length_stops": 0,
"errors": 0,
"seconds": 1.194,
"budget_s": 1.8174541082509506,
"last_prompt_tokens": 707
},
"bfcl:parallel_14#1": {
"requests": 1,
"prompt_tokens": 436,
"completion_tokens": 1004,
"allowance_tokens": 43674,
"length_stops": 0,
"errors": 0,
"seconds": 5.184,
"budget_s": 7.471134798245706,
"last_prompt_tokens": 436
},
"bfcl:parallel_multiple_5#1": {
"requests": 1,
"prompt_tokens": 603,
"completion_tokens": 139,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 1.232,
"budget_s": 1.7662950351124644,
"last_prompt_tokens": 603
},
"bfcl:multi_turn_base_13#1": {
"requests": 7,
"prompt_tokens": 37054,
"completion_tokens": 923,
"allowance_tokens": 295498,
"length_stops": 0,
"errors": 0,
"seconds": 14.280000000000001,
"budget_s": 18.84249551910384,
"last_prompt_tokens": 5778
},
"bfcl:simple_python_33#1": {
"requests": 1,
"prompt_tokens": 420,
"completion_tokens": 100,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 0.797,
"budget_s": 1.2520840473854133,
"last_prompt_tokens": 420
},
"bfcl:multiple_18#1": {
"requests": 1,
"prompt_tokens": 519,
"completion_tokens": 71,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 0.81,
"budget_s": 1.186809079981151,
"last_prompt_tokens": 519
},
"bfcl:parallel_16#1": {
"requests": 1,
"prompt_tokens": 424,
"completion_tokens": 268,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.921,
"budget_s": 2.4092215174349576,
"last_prompt_tokens": 424
},
"bfcl:parallel_multiple_7#1": {
"requests": 1,
"prompt_tokens": 545,
"completion_tokens": 219,
"allowance_tokens": 43652,
"length_stops": 0,
"errors": 0,
"seconds": 1.623,
"budget_s": 2.2365094374366556,
"last_prompt_tokens": 545
},
"bfcl:multi_turn_base_14#1": {
"requests": 14,
"prompt_tokens": 73830,
"completion_tokens": 1946,
"allowance_tokens": 576650,
"length_stops": 0,
"errors": 0,
"seconds": 25.907,
"budget_s": 33.161234877544146,
"last_prompt_tokens": 6528
},
"bfcl:simple_python_47#1": {
"requests": 1,
"prompt_tokens": 393,
"completion_tokens": 172,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 1.432,
"budget_s": 1.7092684091135313,
"last_prompt_tokens": 393
},
"bfcl:multiple_20#1": {
"requests": 1,
"prompt_tokens": 631,
"completion_tokens": 92,
"allowance_tokens": 43635,
"length_stops": 0,
"errors": 0,
"seconds": 1.097,
"budget_s": 1.481849718477526,
"last_prompt_tokens": 631
},
"bfcl:parallel_19#1": {
"requests": 1,
"prompt_tokens": 449,
"completion_tokens": 487,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 3.31,
"budget_s": 3.944321121105744,
"last_prompt_tokens": 449
},
"bfcl:parallel_multiple_10#1": {
"requests": 1,
"prompt_tokens": 633,
"completion_tokens": 301,
"allowance_tokens": 43635,
"length_stops": 0,
"errors": 0,
"seconds": 2.245,
"budget_s": 2.9173693536435232,
"last_prompt_tokens": 633
},
"bfcl:multi_turn_base_16#1": {
"requests": 22,
"prompt_tokens": 125165,
"completion_tokens": 7398,
"allowance_tokens": 868774,
"length_stops": 0,
"errors": 0,
"seconds": 70.533,
"budget_s": 76.93567234108752,
"last_prompt_tokens": 11131
},
"bfcl:simple_python_59#1": {
"requests": 1,
"prompt_tokens": 385,
"completion_tokens": 173,
"allowance_tokens": 43684,
"length_stops": 0,
"errors": 0,
"seconds": 1.404,
"budget_s": 1.705333095795186,
"last_prompt_tokens": 385
},
"bfcl:multiple_23#1": {
"requests": 1,
"prompt_tokens": 726,
"completion_tokens": 112,
"allowance_tokens": 43616,
"length_stops": 0,
"errors": 0,
"seconds": 1.156,
"budget_s": 1.7471040436688863,
"last_prompt_tokens": 726
},
"bfcl:parallel_20#1": {
"requests": 1,
"prompt_tokens": 457,
"completion_tokens": 311,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 2.35,
"budget_s": 2.748525174226373,
"last_prompt_tokens": 457
},
"bfcl:parallel_multiple_12#1": {
"requests": 1,
"prompt_tokens": 692,
"completion_tokens": 494,
"allowance_tokens": 43623,
"length_stops": 0,
"errors": 0,
"seconds": 3.237,
"budget_s": 4.3200845822927025,
"last_prompt_tokens": 692
},
"bfcl:multi_turn_base_17#1": {
"requests": 12,
"prompt_tokens": 62820,
"completion_tokens": 1973,
"allowance_tokens": 496731,
"length_stops": 0,
"errors": 0,
"seconds": 22.956,
"budget_s": 29.976871339768607,
"last_prompt_tokens": 6366
},
"bfcl:simple_python_67#1": {
"requests": 1,
"prompt_tokens": 403,
"completion_tokens": 89,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 0.757,
"budget_s": 1.1537416620691014,
"last_prompt_tokens": 403
},
"bfcl:multiple_28#1": {
"requests": 1,
"prompt_tokens": 604,
"completion_tokens": 112,
"allowance_tokens": 43640,
"length_stops": 0,
"errors": 0,
"seconds": 0.963,
"budget_s": 1.5825425057468938,
"last_prompt_tokens": 604
},
"bfcl:parallel_21#1": {
"requests": 1,
"prompt_tokens": 418,
"completion_tokens": 215,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 1.513,
"budget_s": 2.037781145385472,
"last_prompt_tokens": 418
},
"bfcl:parallel_multiple_15#1": {
"requests": 1,
"prompt_tokens": 575,
"completion_tokens": 327,
"allowance_tokens": 43646,
"length_stops": 0,
"errors": 0,
"seconds": 2.084,
"budget_s": 3.017380967106705,
"last_prompt_tokens": 575
},
"bfcl:multi_turn_base_18#1": {
"requests": 23,
"prompt_tokens": 177334,
"completion_tokens": 4994,
"allowance_tokens": 894165,
"length_stops": 0,
"errors": 0,
"seconds": 53.209999999999994,
"budget_s": 64.35166380216684,
"last_prompt_tokens": 10558
},
"bfcl:simple_python_90#1": {
"requests": 1,
"prompt_tokens": 450,
"completion_tokens": 154,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 1.353,
"budget_s": 1.6627527881944535,
"last_prompt_tokens": 450
},
"bfcl:multiple_29#1": {
"requests": 1,
"prompt_tokens": 501,
"completion_tokens": 148,
"allowance_tokens": 43661,
"length_stops": 0,
"errors": 0,
"seconds": 1.212,
"budget_s": 1.6904112632993273,
"last_prompt_tokens": 501
},
"bfcl:parallel_22#1": {
"requests": 1,
"prompt_tokens": 441,
"completion_tokens": 484,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 3.209,
"budget_s": 3.9129633789828797,
"last_prompt_tokens": 441
},
"bfcl:parallel_multiple_17#1": {
"requests": 1,
"prompt_tokens": 632,
"completion_tokens": 126,
"allowance_tokens": 43635,
"length_stops": 0,
"errors": 0,
"seconds": 1.326,
"budget_s": 1.7162892283808735,
"last_prompt_tokens": 632
},
"bfcl:multi_turn_base_20#1": {
"requests": 10,
"prompt_tokens": 55385,
"completion_tokens": 1116,
"allowance_tokens": 417873,
"length_stops": 0,
"errors": 0,
"seconds": 16.913,
"budget_s": 23.137177446972295,
"last_prompt_tokens": 6136
},
"bfcl:simple_python_91#1": {
"requests": 1,
"prompt_tokens": 410,
"completion_tokens": 88,
"allowance_tokens": 43679,
"length_stops": 0,
"errors": 0,
"seconds": 0.784,
"budget_s": 1.156328110322512,
"last_prompt_tokens": 410
},
"bfcl:multiple_30#1": {
"requests": 1,
"prompt_tokens": 624,
"completion_tokens": 79,
"allowance_tokens": 43637,
"length_stops": 0,
"errors": 0,
"seconds": 0.888,
"budget_s": 1.3832847694082977,
"last_prompt_tokens": 624
},
"bfcl:parallel_23#1": {
"requests": 1,
"prompt_tokens": 476,
"completion_tokens": 279,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 2.08,
"budget_s": 2.5547741800239723,
"last_prompt_tokens": 476
},
"bfcl:parallel_multiple_20#1": {
"requests": 1,
"prompt_tokens": 589,
"completion_tokens": 441,
"allowance_tokens": 43643,
"length_stops": 0,
"errors": 0,
"seconds": 2.928,
"budget_s": 3.8178042989445835,
"last_prompt_tokens": 589
},
"bfcl:multi_turn_base_24#1": {
"requests": 13,
"prompt_tokens": 72919,
"completion_tokens": 2233,
"allowance_tokens": 535096,
"length_stops": 0,
"errors": 0,
"seconds": 26.629000000000005,
"budget_s": 32.08710342284141,
"last_prompt_tokens": 6956
},
"bfcl:simple_python_93#1": {
"requests": 1,
"prompt_tokens": 443,
"completion_tokens": 132,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 1.007,
"budget_s": 1.5024873743150573,
"last_prompt_tokens": 443
},
"bfcl:multiple_31#1": {
"requests": 1,
"prompt_tokens": 562,
"completion_tokens": 82,
"allowance_tokens": 43649,
"length_stops": 0,
"errors": 0,
"seconds": 0.844,
"budget_s": 1.3202219569857565,
"last_prompt_tokens": 562
},
"bfcl:parallel_26#1": {
"requests": 1,
"prompt_tokens": 456,
"completion_tokens": 420,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 2.87,
"budget_s": 3.4944374940845875,
"last_prompt_tokens": 456
},
"bfcl:parallel_multiple_21#1": {
"requests": 1,
"prompt_tokens": 568,
"completion_tokens": 181,
"allowance_tokens": 43648,
"length_stops": 0,
"errors": 0,
"seconds": 1.686,
"budget_s": 2.0070202602872134,
"last_prompt_tokens": 568
},
"bfcl:multi_turn_base_25#1": {
"requests": 17,
"prompt_tokens": 76742,
"completion_tokens": 2809,
"allowance_tokens": 696828,
"length_stops": 0,
"errors": 0,
"seconds": 32.455,
"budget_s": 39.37976966666446,
"last_prompt_tokens": 6350
},
"bfcl:simple_python_96#1": {
"requests": 1,
"prompt_tokens": 473,
"completion_tokens": 121,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 1.01,
"budget_s": 1.4675416470506604,
"last_prompt_tokens": 473
},
"bfcl:multiple_32#1": {
"requests": 1,
"prompt_tokens": 580,
"completion_tokens": 106,
"allowance_tokens": 43645,
"length_stops": 0,
"errors": 0,
"seconds": 1.033,
"budget_s": 1.5090361009816904,
"last_prompt_tokens": 580
},
"bfcl:parallel_31#1": {
"requests": 1,
"prompt_tokens": 418,
"completion_tokens": 384,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 2.504,
"budget_s": 3.196378762376409,
"last_prompt_tokens": 418
},
"bfcl:parallel_multiple_24#1": {
"requests": 1,
"prompt_tokens": 511,
"completion_tokens": 152,
"allowance_tokens": 43659,
"length_stops": 0,
"errors": 0,
"seconds": 1.22,
"budget_s": 1.7313223427531903,
"last_prompt_tokens": 511
},
"bfcl:multi_turn_base_26#1": {
"requests": 11,
"prompt_tokens": 41887,
"completion_tokens": 1065,
"allowance_tokens": 462427,
"length_stops": 0,
"errors": 0,
"seconds": 16.421,
"budget_s": 21.50072420776729,
"last_prompt_tokens": 4365
},
"bfcl:simple_python_104#1": {
"requests": 1,
"prompt_tokens": 400,
"completion_tokens": 117,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 0.912,
"budget_s": 1.3416520685059328,
"last_prompt_tokens": 400
},
"bfcl:multiple_34#1": {
"requests": 1,
"prompt_tokens": 601,
"completion_tokens": 84,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 0.911,
"budget_s": 1.3865389089204565,
"last_prompt_tokens": 601
},
"bfcl:parallel_32#1": {
"requests": 1,
"prompt_tokens": 421,
"completion_tokens": 171,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.337,
"budget_s": 1.7401810237305637,
"last_prompt_tokens": 421
},
"bfcl:parallel_multiple_25#1": {
"requests": 1,
"prompt_tokens": 545,
"completion_tokens": 201,
"allowance_tokens": 43652,
"length_stops": 0,
"errors": 0,
"seconds": 1.571,
"budget_s": 2.113108507816319,
"last_prompt_tokens": 545
},
"bfcl:multi_turn_base_27#1": {
"requests": 9,
"prompt_tokens": 45919,
"completion_tokens": 1422,
"allowance_tokens": 376856,
"length_stops": 0,
"errors": 0,
"seconds": 19.211,
"budget_s": 23.94817597857063,
"last_prompt_tokens": 6106
},
"bfcl:simple_python_105#1": {
"requests": 1,
"prompt_tokens": 397,
"completion_tokens": 81,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 0.801,
"budget_s": 1.0908036140704567,
"last_prompt_tokens": 397
},
"bfcl:multiple_44#1": {
"requests": 1,
"prompt_tokens": 676,
"completion_tokens": 121,
"allowance_tokens": 43626,
"length_stops": 0,
"errors": 0,
"seconds": 1.266,
"budget_s": 1.7413612552323365,
"last_prompt_tokens": 676
},
"bfcl:parallel_33#1": {
"requests": 1,
"prompt_tokens": 414,
"completion_tokens": 294,
"allowance_tokens": 43678,
"length_stops": 0,
"errors": 0,
"seconds": 1.705,
"budget_s": 2.573978654014989,
"last_prompt_tokens": 414
},
"bfcl:parallel_multiple_28#1": {
"requests": 1,
"prompt_tokens": 507,
"completion_tokens": 172,
"allowance_tokens": 43660,
"length_stops": 0,
"errors": 0,
"seconds": 1.53,
"budget_s": 1.863039026516049,
"last_prompt_tokens": 507
},
"bfcl:multi_turn_base_28#1": {
"requests": 11,
"prompt_tokens": 69287,
"completion_tokens": 1411,
"allowance_tokens": 454960,
"length_stops": 0,
"errors": 0,
"seconds": 21.76,
"budget_s": 27.595631878577052,
"last_prompt_tokens": 7047
},
"bfcl:simple_python_107#1": {
"requests": 1,
"prompt_tokens": 430,
"completion_tokens": 134,
"allowance_tokens": 43675,
"length_stops": 0,
"errors": 0,
"seconds": 0.996,
"budget_s": 1.4986633428731704,
"last_prompt_tokens": 430
},
"bfcl:multiple_47#1": {
"requests": 1,
"prompt_tokens": 612,
"completion_tokens": 289,
"allowance_tokens": 43639,
"length_stops": 0,
"errors": 0,
"seconds": 2.316,
"budget_s": 2.806775900866344,
"last_prompt_tokens": 612
},
"bfcl:parallel_40#1": {
"requests": 1,
"prompt_tokens": 461,
"completion_tokens": 624,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 4.779,
"budget_s": 4.899725688439739,
"last_prompt_tokens": 461
},
"bfcl:parallel_multiple_31#1": {
"requests": 1,
"prompt_tokens": 482,
"completion_tokens": 261,
"allowance_tokens": 43664,
"length_stops": 0,
"errors": 0,
"seconds": 1.75,
"budget_s": 2.4394664407932423,
"last_prompt_tokens": 482
},
"bfcl:multi_turn_base_29#1": {
"requests": 10,
"prompt_tokens": 35848,
"completion_tokens": 702,
"allowance_tokens": 423317,
"length_stops": 0,
"errors": 0,
"seconds": 12.819999999999997,
"budget_s": 18.11784125570569,
"last_prompt_tokens": 4061
},
"bfcl:simple_python_110#1": {
"requests": 1,
"prompt_tokens": 458,
"completion_tokens": 131,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 0.948,
"budget_s": 1.515864743087943,
"last_prompt_tokens": 458
},
"bfcl:multiple_50#1": {
"requests": 1,
"prompt_tokens": 672,
"completion_tokens": 82,
"allowance_tokens": 43627,
"length_stops": 0,
"errors": 0,
"seconds": 0.996,
"budget_s": 1.4685971141285366,
"last_prompt_tokens": 672
},
"bfcl:parallel_47#1": {
"requests": 1,
"prompt_tokens": 392,
"completion_tokens": 564,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 4.233,
"budget_s": 4.39531756689148,
"last_prompt_tokens": 392
},
"bfcl:parallel_multiple_37#1": {
"requests": 1,
"prompt_tokens": 509,
"completion_tokens": 397,
"allowance_tokens": 43659,
"length_stops": 0,
"errors": 0,
"seconds": 2.58,
"budget_s": 3.408248376900123,
"last_prompt_tokens": 509
},
"bfcl:multi_turn_base_30#1": {
"requests": 12,
"prompt_tokens": 69036,
"completion_tokens": 2046,
"allowance_tokens": 497107,
"length_stops": 0,
"errors": 0,
"seconds": 26.559,
"budget_s": 32.214668869086545,
"last_prompt_tokens": 7197
},
"bfcl:simple_python_111#1": {
"requests": 1,
"prompt_tokens": 381,
"completion_tokens": 77,
"allowance_tokens": 43684,
"length_stops": 0,
"errors": 0,
"seconds": 0.636,
"budget_s": 1.0417993442269875,
"last_prompt_tokens": 381
},
"bfcl:multiple_51#1": {
"requests": 1,
"prompt_tokens": 664,
"completion_tokens": 177,
"allowance_tokens": 43629,
"length_stops": 0,
"errors": 0,
"seconds": 1.432,
"budget_s": 2.109088877716393,
"last_prompt_tokens": 664
},
"bfcl:parallel_49#1": {
"requests": 1,
"prompt_tokens": 438,
"completion_tokens": 271,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 1.626,
"budget_s": 2.4486724499474284,
"last_prompt_tokens": 438
},
"bfcl:parallel_multiple_38#1": {
"requests": 1,
"prompt_tokens": 477,
"completion_tokens": 223,
"allowance_tokens": 43665,
"length_stops": 0,
"errors": 0,
"seconds": 1.474,
"budget_s": 2.1722090418256377,
"last_prompt_tokens": 477
},
"bfcl:multi_turn_base_32#1": {
"requests": 8,
"prompt_tokens": 49836,
"completion_tokens": 1251,
"allowance_tokens": 332925,
"length_stops": 0,
"errors": 0,
"seconds": 17.596999999999998,
"budget_s": 23.225039213800578,
"last_prompt_tokens": 6761
},
"bfcl:simple_python_113#1": {
"requests": 1,
"prompt_tokens": 433,
"completion_tokens": 131,
"allowance_tokens": 43674,
"length_stops": 0,
"errors": 0,
"seconds": 1.213,
"budget_s": 1.482143116464584,
"last_prompt_tokens": 433
},
"bfcl:multiple_55#1": {
"requests": 1,
"prompt_tokens": 525,
"completion_tokens": 91,
"allowance_tokens": 43656,
"length_stops": 0,
"errors": 0,
"seconds": 0.977,
"budget_s": 1.3320144143933532,
"last_prompt_tokens": 525
},
"bfcl:parallel_51#1": {
"requests": 1,
"prompt_tokens": 395,
"completion_tokens": 296,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 1.96,
"budget_s": 2.5620614321834956,
"last_prompt_tokens": 395
},
"bfcl:parallel_multiple_39#1": {
"requests": 1,
"prompt_tokens": 488,
"completion_tokens": 162,
"allowance_tokens": 43663,
"length_stops": 0,
"errors": 0,
"seconds": 1.233,
"budget_s": 1.7688545182709978,
"last_prompt_tokens": 488
},
"bfcl:multi_turn_base_35#1": {
"requests": 14,
"prompt_tokens": 91102,
"completion_tokens": 1731,
"allowance_tokens": 573999,
"length_stops": 0,
"errors": 0,
"seconds": 24.674999999999997,
"budget_s": 32.02179786540497,
"last_prompt_tokens": 7436
},
"bfcl:simple_python_115#1": {
"requests": 1,
"prompt_tokens": 447,
"completion_tokens": 185,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 1.369,
"budget_s": 1.8712300162346742,
"last_prompt_tokens": 447
},
"bfcl:multiple_57#1": {
"requests": 1,
"prompt_tokens": 680,
"completion_tokens": 143,
"allowance_tokens": 43626,
"length_stops": 0,
"errors": 0,
"seconds": 1.214,
"budget_s": 1.8975800739169295,
"last_prompt_tokens": 680
},
"bfcl:parallel_55#1": {
"requests": 1,
"prompt_tokens": 431,
"completion_tokens": 243,
"allowance_tokens": 43674,
"length_stops": 0,
"errors": 0,
"seconds": 1.874,
"budget_s": 2.247273392861253,
"last_prompt_tokens": 431
},
"bfcl:parallel_multiple_48#1": {
"requests": 1,
"prompt_tokens": 463,
"completion_tokens": 108,
"allowance_tokens": 43668,
"length_stops": 0,
"errors": 0,
"seconds": 0.916,
"budget_s": 1.3649301027866294,
"last_prompt_tokens": 463
},
"bfcl:multi_turn_base_37#1": {
"requests": 11,
"prompt_tokens": 44704,
"completion_tokens": 2040,
"allowance_tokens": 459542,
"length_stops": 0,
"errors": 0,
"seconds": 22.89,
"budget_s": 28.963236371335974,
"last_prompt_tokens": 5400
},
"bfcl:simple_python_116#1": {
"requests": 1,
"prompt_tokens": 415,
"completion_tokens": 162,
"allowance_tokens": 43678,
"length_stops": 0,
"errors": 0,
"seconds": 1.349,
"budget_s": 1.6703873685307893,
"last_prompt_tokens": 415
},
"bfcl:multiple_58#1": {
"requests": 1,
"prompt_tokens": 513,
"completion_tokens": 119,
"allowance_tokens": 43658,
"length_stops": 0,
"errors": 0,
"seconds": 1.106,
"budget_s": 1.5077850352457753,
"last_prompt_tokens": 513
},
"bfcl:parallel_65#1": {
"requests": 1,
"prompt_tokens": 424,
"completion_tokens": 371,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 2.35,
"budget_s": 3.1153490591513275,
"last_prompt_tokens": 424
},
"bfcl:parallel_multiple_49#1": {
"requests": 1,
"prompt_tokens": 558,
"completion_tokens": 272,
"allowance_tokens": 43650,
"length_stops": 0,
"errors": 0,
"seconds": 1.677,
"budget_s": 2.6173918649406818,
"last_prompt_tokens": 558
},
"bfcl:multi_turn_base_39#1": {
"requests": 13,
"prompt_tokens": 57764,
"completion_tokens": 1922,
"allowance_tokens": 536367,
"length_stops": 0,
"errors": 0,
"seconds": 22.898999999999997,
"budget_s": 30.058872193289986,
"last_prompt_tokens": 5501
},
"bfcl:simple_python_124#1": {
"requests": 1,
"prompt_tokens": 468,
"completion_tokens": 242,
"allowance_tokens": 43667,
"length_stops": 0,
"errors": 0,
"seconds": 1.76,
"budget_s": 2.290325793062695,
"last_prompt_tokens": 468
},
"bfcl:multiple_59#1": {
"requests": 1,
"prompt_tokens": 554,
"completion_tokens": 119,
"allowance_tokens": 43650,
"length_stops": 0,
"errors": 0,
"seconds": 1.237,
"budget_s": 1.5630885029080843,
"last_prompt_tokens": 554
},
"bfcl:parallel_66#1": {
"requests": 1,
"prompt_tokens": 418,
"completion_tokens": 193,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 1.408,
"budget_s": 1.8869577869606164,
"last_prompt_tokens": 418
},
"bfcl:parallel_multiple_50#1": {
"requests": 1,
"prompt_tokens": 583,
"completion_tokens": 283,
"allowance_tokens": 43645,
"length_stops": 0,
"errors": 0,
"seconds": 1.939,
"budget_s": 2.7265251707764686,
"last_prompt_tokens": 583
},
"bfcl:multi_turn_base_40#1": {
"requests": 17,
"prompt_tokens": 87233,
"completion_tokens": 1471,
"allowance_tokens": 699616,
"length_stops": 0,
"errors": 0,
"seconds": 24.786,
"budget_s": 32.272079645967295,
"last_prompt_tokens": 6087
},
"bfcl:simple_python_125#1": {
"requests": 1,
"prompt_tokens": 448,
"completion_tokens": 138,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 1.029,
"budget_s": 1.5503653428465078,
"last_prompt_tokens": 448
},
"bfcl:multiple_63#1": {
"requests": 1,
"prompt_tokens": 608,
"completion_tokens": 90,
"allowance_tokens": 43640,
"length_stops": 0,
"errors": 0,
"seconds": 0.969,
"budget_s": 1.4371146075817758,
"last_prompt_tokens": 608
},
"bfcl:parallel_68#1": {
"requests": 1,
"prompt_tokens": 484,
"completion_tokens": 284,
"allowance_tokens": 43664,
"length_stops": 0,
"errors": 0,
"seconds": 2.149,
"budget_s": 2.5998431365490964,
"last_prompt_tokens": 484
},
"bfcl:parallel_multiple_51#1": {
"requests": 1,
"prompt_tokens": 506,
"completion_tokens": 150,
"allowance_tokens": 43660,
"length_stops": 0,
"errors": 0,
"seconds": 1.325,
"budget_s": 1.7108668030262588,
"last_prompt_tokens": 506
},
"bfcl:multi_turn_base_42#1": {
"requests": 11,
"prompt_tokens": 66254,
"completion_tokens": 950,
"allowance_tokens": 457919,
"length_stops": 0,
"errors": 0,
"seconds": 17.724,
"budget_s": 23.969838511453855,
"last_prompt_tokens": 6606
},
"bfcl:simple_python_129#1": {
"requests": 1,
"prompt_tokens": 471,
"completion_tokens": 796,
"allowance_tokens": 43667,
"length_stops": 0,
"errors": 0,
"seconds": 5.49,
"budget_s": 6.092378777683409,
"last_prompt_tokens": 471
},
"bfcl:multiple_65#1": {
"requests": 1,
"prompt_tokens": 638,
"completion_tokens": 100,
"allowance_tokens": 43634,
"length_stops": 0,
"errors": 0,
"seconds": 1.177,
"budget_s": 1.5461366315411045,
"last_prompt_tokens": 638
},
"bfcl:parallel_70#1": {
"requests": 1,
"prompt_tokens": 427,
"completion_tokens": 346,
"allowance_tokens": 43675,
"length_stops": 0,
"errors": 0,
"seconds": 2.375,
"budget_s": 2.9480054743178856,
"last_prompt_tokens": 427
},
"bfcl:parallel_multiple_61#1": {
"requests": 1,
"prompt_tokens": 730,
"completion_tokens": 392,
"allowance_tokens": 43616,
"length_stops": 0,
"errors": 0,
"seconds": 2.541,
"budget_s": 3.672069520244969,
"last_prompt_tokens": 730
},
"bfcl:multi_turn_base_44#1": {
"requests": 14,
"prompt_tokens": 95136,
"completion_tokens": 2219,
"allowance_tokens": 569319,
"length_stops": 0,
"errors": 0,
"seconds": 28.687999999999995,
"budget_s": 36.57861500786736,
"last_prompt_tokens": 8007
},
"bfcl:simple_python_131#1": {
"requests": 1,
"prompt_tokens": 497,
"completion_tokens": 148,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 1.145,
"budget_s": 1.6850158030395899,
"last_prompt_tokens": 497
},
"bfcl:multiple_66#1": {
"requests": 1,
"prompt_tokens": 640,
"completion_tokens": 101,
"allowance_tokens": 43633,
"length_stops": 0,
"errors": 0,
"seconds": 1.145,
"budget_s": 1.555689968872103,
"last_prompt_tokens": 640
},
"bfcl:parallel_72#1": {
"requests": 1,
"prompt_tokens": 533,
"completion_tokens": 407,
"allowance_tokens": 43654,
"length_stops": 0,
"errors": 0,
"seconds": 2.302,
"budget_s": 3.509177210469846,
"last_prompt_tokens": 533
},
"bfcl:parallel_multiple_64#1": {
"requests": 1,
"prompt_tokens": 674,
"completion_tokens": 679,
"allowance_tokens": 43627,
"length_stops": 0,
"errors": 0,
"seconds": 5.089,
"budget_s": 5.564092343332899,
"last_prompt_tokens": 674
},
"bfcl:multi_turn_base_46#1": {
"requests": 9,
"prompt_tokens": 41297,
"completion_tokens": 681,
"allowance_tokens": 378872,
"length_stops": 0,
"errors": 0,
"seconds": 13.895000000000001,
"budget_s": 19.28092375240336,
"last_prompt_tokens": 4947
},
"bfcl:simple_python_138#1": {
"requests": 1,
"prompt_tokens": 494,
"completion_tokens": 142,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 1.053,
"budget_s": 1.639835564638008,
"last_prompt_tokens": 494
},
"bfcl:multiple_68#1": {
"requests": 1,
"prompt_tokens": 599,
"completion_tokens": 86,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 0.91,
"budget_s": 1.3975523931928473,
"last_prompt_tokens": 599
},
"bfcl:parallel_73#1": {
"requests": 1,
"prompt_tokens": 481,
"completion_tokens": 254,
"allowance_tokens": 43665,
"length_stops": 0,
"errors": 0,
"seconds": 1.994,
"budget_s": 2.3901283253203993,
"last_prompt_tokens": 481
},
"bfcl:parallel_multiple_67#1": {
"requests": 1,
"prompt_tokens": 982,
"completion_tokens": 362,
"allowance_tokens": 43566,
"length_stops": 0,
"errors": 0,
"seconds": 2.447,
"budget_s": 3.8063153005745347,
"last_prompt_tokens": 982
},
"bfcl:multi_turn_base_49#1": {
"requests": 16,
"prompt_tokens": 113067,
"completion_tokens": 2572,
"allowance_tokens": 646177,
"length_stops": 0,
"errors": 0,
"seconds": 32.205,
"budget_s": 41.43064806194284,
"last_prompt_tokens": 8522
},
"bfcl:simple_python_140#1": {
"requests": 1,
"prompt_tokens": 440,
"completion_tokens": 159,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 1.141,
"budget_s": 1.683542173550759,
"last_prompt_tokens": 440
},
"bfcl:multiple_69#1": {
"requests": 1,
"prompt_tokens": 740,
"completion_tokens": 214,
"allowance_tokens": 43614,
"length_stops": 0,
"errors": 0,
"seconds": 2.031,
"budget_s": 2.4652600890932073,
"last_prompt_tokens": 740
},
"bfcl:parallel_74#1": {
"requests": 1,
"prompt_tokens": 396,
"completion_tokens": 286,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 1.799,
"budget_s": 2.494854225237132,
"last_prompt_tokens": 396
},
"bfcl:parallel_multiple_68#1": {
"requests": 1,
"prompt_tokens": 951,
"completion_tokens": 413,
"allowance_tokens": 43572,
"length_stops": 0,
"errors": 0,
"seconds": 2.749,
"budget_s": 4.114136450819189,
"last_prompt_tokens": 951
},
"bfcl:multi_turn_base_50#1": {
"requests": 2,
"prompt_tokens": 6973,
"completion_tokens": 361,
"allowance_tokens": 85922,
"length_stops": 0,
"errors": 0,
"seconds": 6.071,
"budget_s": 8.254761002851609,
"last_prompt_tokens": 3622
},
"bfcl:simple_python_143#1": {
"requests": 1,
"prompt_tokens": 408,
"completion_tokens": 115,
"allowance_tokens": 43679,
"length_stops": 0,
"errors": 0,
"seconds": 1.033,
"budget_s": 1.338731774623148,
"last_prompt_tokens": 408
},
"bfcl:multiple_72#1": {
"requests": 1,
"prompt_tokens": 557,
"completion_tokens": 97,
"allowance_tokens": 43650,
"length_stops": 0,
"errors": 0,
"seconds": 0.891,
"budget_s": 1.4163117396780316,
"last_prompt_tokens": 557
},
"bfcl:parallel_75#1": {
"requests": 1,
"prompt_tokens": 355,
"completion_tokens": 162,
"allowance_tokens": 43689,
"length_stops": 0,
"errors": 0,
"seconds": 1.337,
"budget_s": 1.5894554646347274,
"last_prompt_tokens": 355
},
"bfcl:parallel_multiple_69#1": {
"requests": 1,
"prompt_tokens": 981,
"completion_tokens": 1037,
"allowance_tokens": 43566,
"length_stops": 0,
"errors": 0,
"seconds": 6.083,
"budget_s": 8.432501296272218,
"last_prompt_tokens": 981
},
"bfcl:multi_turn_base_52#1": {
"requests": 14,
"prompt_tokens": 105244,
"completion_tokens": 3737,
"allowance_tokens": 556713,
"length_stops": 0,
"errors": 0,
"seconds": 39.26700000000001,
"budget_s": 45.51246608827409,
"last_prompt_tokens": 9280
},
"bfcl:simple_python_149#1": {
"requests": 1,
"prompt_tokens": 361,
"completion_tokens": 65,
"allowance_tokens": 43688,
"length_stops": 0,
"errors": 0,
"seconds": 0.57,
"budget_s": 0.9325547565147427,
"last_prompt_tokens": 361
},
"bfcl:multiple_73#1": {
"requests": 1,
"prompt_tokens": 456,
"completion_tokens": 67,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 0.724,
"budget_s": 1.074408152085767,
"last_prompt_tokens": 456
},
"bfcl:parallel_81#1": {
"requests": 1,
"prompt_tokens": 569,
"completion_tokens": 461,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 3.073,
"budget_s": 3.927939141668493,
"last_prompt_tokens": 569
},
"bfcl:parallel_multiple_71#1": {
"requests": 1,
"prompt_tokens": 712,
"completion_tokens": 493,
"allowance_tokens": 43619,
"length_stops": 0,
"errors": 0,
"seconds": 3.281,
"budget_s": 4.34020627639026,
"last_prompt_tokens": 712
},
"bfcl:multi_turn_base_57#1": {
"requests": 5,
"prompt_tokens": 30374,
"completion_tokens": 956,
"allowance_tokens": 210231,
"length_stops": 0,
"errors": 0,
"seconds": 14.61,
"budget_s": 18.518393610247905,
"last_prompt_tokens": 6557
},
"bfcl:simple_python_160#1": {
"requests": 1,
"prompt_tokens": 428,
"completion_tokens": 90,
"allowance_tokens": 43675,
"length_stops": 0,
"errors": 0,
"seconds": 0.822,
"budget_s": 1.1943188958935902,
"last_prompt_tokens": 428
},
"bfcl:multiple_74#1": {
"requests": 1,
"prompt_tokens": 570,
"completion_tokens": 142,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 1.15,
"budget_s": 1.7423493095730196,
"last_prompt_tokens": 570
},
"bfcl:parallel_84#1": {
"requests": 1,
"prompt_tokens": 548,
"completion_tokens": 412,
"allowance_tokens": 43651,
"length_stops": 0,
"errors": 0,
"seconds": 2.537,
"budget_s": 3.5636882224495103,
"last_prompt_tokens": 548
},
"bfcl:parallel_multiple_72#1": {
"requests": 1,
"prompt_tokens": 688,
"completion_tokens": 483,
"allowance_tokens": 43624,
"length_stops": 0,
"errors": 0,
"seconds": 4.515,
"budget_s": 4.239277442820537,
"last_prompt_tokens": 688
},
"bfcl:multi_turn_base_64#1": {
"requests": 12,
"prompt_tokens": 52414,
"completion_tokens": 2434,
"allowance_tokens": 498488,
"length_stops": 0,
"errors": 0,
"seconds": 26.199,
"budget_s": 32.39543047377555,
"last_prompt_tokens": 5856
},
"bfcl:simple_python_167#1": {
"requests": 1,
"prompt_tokens": 395,
"completion_tokens": 104,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 0.824,
"budget_s": 1.2457848495665735,
"last_prompt_tokens": 395
},
"bfcl:multiple_76#1": {
"requests": 1,
"prompt_tokens": 595,
"completion_tokens": 503,
"allowance_tokens": 43642,
"length_stops": 0,
"errors": 0,
"seconds": 3.696,
"budget_s": 4.250945135804238,
"last_prompt_tokens": 595
},
"bfcl:parallel_85#1": {
"requests": 1,
"prompt_tokens": 548,
"completion_tokens": 1044,
"allowance_tokens": 43651,
"length_stops": 0,
"errors": 0,
"seconds": 6.813,
"budget_s": 7.896431973563546,
"last_prompt_tokens": 548
},
"bfcl:parallel_multiple_74#1": {
"requests": 1,
"prompt_tokens": 812,
"completion_tokens": 373,
"allowance_tokens": 43600,
"length_stops": 0,
"errors": 0,
"seconds": 2.841,
"budget_s": 3.6524199187481203,
"last_prompt_tokens": 812
},
"bfcl:multi_turn_base_68#1": {
"requests": 17,
"prompt_tokens": 110494,
"completion_tokens": 3253,
"allowance_tokens": 689903,
"length_stops": 0,
"errors": 0,
"seconds": 39.194,
"budget_s": 45.65014449928909,
"last_prompt_tokens": 8957
},
"bfcl:simple_python_183#1": {
"requests": 1,
"prompt_tokens": 399,
"completion_tokens": 186,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 1.691,
"budget_s": 1.8133401003189547,
"last_prompt_tokens": 399
},
"bfcl:multiple_78#1": {
"requests": 1,
"prompt_tokens": 635,
"completion_tokens": 131,
"allowance_tokens": 43634,
"length_stops": 0,
"errors": 0,
"seconds": 1.353,
"budget_s": 1.7546138595813257,
"last_prompt_tokens": 635
},
"bfcl:parallel_87#1": {
"requests": 1,
"prompt_tokens": 494,
"completion_tokens": 206,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 1.565,
"budget_s": 2.0785944255103153,
"last_prompt_tokens": 494
},
"bfcl:parallel_multiple_77#1": {
"requests": 1,
"prompt_tokens": 787,
"completion_tokens": 343,
"allowance_tokens": 43604,
"length_stops": 0,
"errors": 0,
"seconds": 2.562,
"budget_s": 3.413030076090867,
"last_prompt_tokens": 787
},
"bfcl:multi_turn_base_69#1": {
"requests": 9,
"prompt_tokens": 55124,
"completion_tokens": 1733,
"allowance_tokens": 372407,
"length_stops": 0,
"errors": 0,
"seconds": 20.880999999999997,
"budget_s": 27.015033308121513,
"last_prompt_tokens": 6810
},
"bfcl:simple_python_192#1": {
"requests": 1,
"prompt_tokens": 479,
"completion_tokens": 212,
"allowance_tokens": 43665,
"length_stops": 0,
"errors": 0,
"seconds": 1.398,
"budget_s": 2.0994950927430787,
"last_prompt_tokens": 479
},
"bfcl:multiple_80#1": {
"requests": 1,
"prompt_tokens": 681,
"completion_tokens": 144,
"allowance_tokens": 43625,
"length_stops": 0,
"errors": 0,
"seconds": 1.391,
"budget_s": 1.9057845461829936,
"last_prompt_tokens": 681
},
"bfcl:parallel_91#1": {
"requests": 1,
"prompt_tokens": 449,
"completion_tokens": 288,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 1.95,
"budget_s": 2.5800552880809127,
"last_prompt_tokens": 449
},
"bfcl:parallel_multiple_79#1": {
"requests": 1,
"prompt_tokens": 706,
"completion_tokens": 3491,
"allowance_tokens": 43620,
"length_stops": 0,
"errors": 0,
"seconds": 29.312,
"budget_s": 24.885223474987807,
"last_prompt_tokens": 706
},
"bfcl:multi_turn_base_70#1": {
"requests": 12,
"prompt_tokens": 64772,
"completion_tokens": 2967,
"allowance_tokens": 487057,
"length_stops": 0,
"errors": 0,
"seconds": 30.790000000000003,
"budget_s": 35.798580209899946,
"last_prompt_tokens": 6618
},
"bfcl:simple_python_198#1": {
"requests": 1,
"prompt_tokens": 418,
"completion_tokens": 88,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 0.845,
"budget_s": 1.1671190308419868,
"last_prompt_tokens": 418
},
"bfcl:multiple_81#1": {
"requests": 1,
"prompt_tokens": 613,
"completion_tokens": 115,
"allowance_tokens": 43639,
"length_stops": 0,
"errors": 0,
"seconds": 1.086,
"budget_s": 1.6152491129346926,
"last_prompt_tokens": 613
},
"bfcl:parallel_92#1": {
"requests": 1,
"prompt_tokens": 419,
"completion_tokens": 313,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 2.113,
"budget_s": 2.710979516161127,
"last_prompt_tokens": 419
},
"bfcl:parallel_multiple_84#1": {
"requests": 1,
"prompt_tokens": 729,
"completion_tokens": 219,
"allowance_tokens": 43616,
"length_stops": 0,
"errors": 0,
"seconds": 1.9,
"budget_s": 2.4847006093845785,
"last_prompt_tokens": 729
},
"bfcl:multi_turn_base_71#1": {
"requests": 18,
"prompt_tokens": 94045,
"completion_tokens": 3517,
"allowance_tokens": 724592,
"length_stops": 0,
"errors": 0,
"seconds": 38.737,
"budget_s": 45.818456016362234,
"last_prompt_tokens": 7238
},
"bfcl:simple_python_199#1": {
"requests": 1,
"prompt_tokens": 394,
"completion_tokens": 82,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 0.747,
"budget_s": 1.0936126260767833,
"last_prompt_tokens": 394
},
"bfcl:multiple_86#1": {
"requests": 1,
"prompt_tokens": 627,
"completion_tokens": 87,
"allowance_tokens": 43636,
"length_stops": 0,
"errors": 0,
"seconds": 0.988,
"budget_s": 1.4421762222121393,
"last_prompt_tokens": 627
},
"bfcl:parallel_93#1": {
"requests": 1,
"prompt_tokens": 486,
"completion_tokens": 1300,
"allowance_tokens": 43664,
"length_stops": 0,
"errors": 0,
"seconds": 9.047,
"budget_s": 9.567837783026846,
"last_prompt_tokens": 486
},
"bfcl:parallel_multiple_85#1": {
"requests": 1,
"prompt_tokens": 671,
"completion_tokens": 339,
"allowance_tokens": 43627,
"length_stops": 0,
"errors": 0,
"seconds": 2.112,
"budget_s": 3.2291392997539616,
"last_prompt_tokens": 671
},
"bfcl:multi_turn_base_72#1": {
"requests": 19,
"prompt_tokens": 103618,
"completion_tokens": 2372,
"allowance_tokens": 776336,
"length_stops": 0,
"errors": 0,
"seconds": 31.408,
"budget_s": 40.00422315405458,
"last_prompt_tokens": 6886
},
"bfcl:simple_python_203#1": {
"requests": 1,
"prompt_tokens": 402,
"completion_tokens": 101,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 0.83,
"budget_s": 1.2346600834177246,
"last_prompt_tokens": 402
},
"bfcl:multiple_87#1": {
"requests": 1,
"prompt_tokens": 647,
"completion_tokens": 93,
"allowance_tokens": 43632,
"length_stops": 0,
"errors": 0,
"seconds": 1.163,
"budget_s": 1.5102871667176054,
"last_prompt_tokens": 647
},
"bfcl:parallel_95#1": {
"requests": 1,
"prompt_tokens": 557,
"completion_tokens": 193,
"allowance_tokens": 43650,
"length_stops": 0,
"errors": 0,
"seconds": 1.67,
"budget_s": 2.074450030986493,
"last_prompt_tokens": 557
},
"bfcl:parallel_multiple_90#1": {
"requests": 1,
"prompt_tokens": 747,
"completion_tokens": 313,
"allowance_tokens": 43612,
"length_stops": 0,
"errors": 0,
"seconds": 2.126,
"budget_s": 3.153407257459598,
"last_prompt_tokens": 747
},
"bfcl:multi_turn_base_73#1": {
"requests": 12,
"prompt_tokens": 61413,
"completion_tokens": 3308,
"allowance_tokens": 489638,
"length_stops": 0,
"errors": 0,
"seconds": 34.02,
"budget_s": 38.43983690509544,
"last_prompt_tokens": 7015
},
"bfcl:simple_python_204#1": {
"requests": 1,
"prompt_tokens": 415,
"completion_tokens": 127,
"allowance_tokens": 43678,
"length_stops": 0,
"errors": 0,
"seconds": 0.952,
"budget_s": 1.430441116491246,
"last_prompt_tokens": 415
},
"bfcl:multiple_91#1": {
"requests": 1,
"prompt_tokens": 521,
"completion_tokens": 149,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 1.264,
"budget_s": 1.7242441717991444,
"last_prompt_tokens": 521
},
"bfcl:parallel_96#1": {
"requests": 1,
"prompt_tokens": 613,
"completion_tokens": 1433,
"allowance_tokens": 43639,
"length_stops": 0,
"errors": 0,
"seconds": 9.566,
"budget_s": 10.650939404023774,
"last_prompt_tokens": 613
},
"bfcl:parallel_multiple_93#1": {
"requests": 1,
"prompt_tokens": 532,
"completion_tokens": 159,
"allowance_tokens": 43655,
"length_stops": 0,
"errors": 0,
"seconds": 1.349,
"budget_s": 1.8076377595247206,
"last_prompt_tokens": 532
},
"bfcl:multi_turn_base_74#1": {
"requests": 11,
"prompt_tokens": 72503,
"completion_tokens": 1899,
"allowance_tokens": 453253,
"length_stops": 0,
"errors": 0,
"seconds": 24.557000000000002,
"budget_s": 31.049077397923146,
"last_prompt_tokens": 7568
},
"bfcl:simple_python_208#1": {
"requests": 1,
"prompt_tokens": 435,
"completion_tokens": 132,
"allowance_tokens": 43674,
"length_stops": 0,
"errors": 0,
"seconds": 1.086,
"budget_s": 1.4916964537955826,
"last_prompt_tokens": 435
},
"bfcl:multiple_93#1": {
"requests": 1,
"prompt_tokens": 643,
"completion_tokens": 275,
"allowance_tokens": 43633,
"length_stops": 0,
"errors": 0,
"seconds": 2.354,
"budget_s": 2.752612217063492,
"last_prompt_tokens": 643
},
"bfcl:parallel_97#1": {
"requests": 1,
"prompt_tokens": 548,
"completion_tokens": 361,
"allowance_tokens": 43651,
"length_stops": 0,
"errors": 0,
"seconds": 2.375,
"budget_s": 3.2140522551918904,
"last_prompt_tokens": 548
},
"bfcl:parallel_multiple_95#1": {
"requests": 1,
"prompt_tokens": 797,
"completion_tokens": 487,
"allowance_tokens": 43602,
"length_stops": 0,
"errors": 0,
"seconds": 2.743,
"budget_s": 4.413726163702902,
"last_prompt_tokens": 797
},
"bfcl:multi_turn_base_85#1": {
"requests": 12,
"prompt_tokens": 53166,
"completion_tokens": 1743,
"allowance_tokens": 497158,
"length_stops": 0,
"errors": 0,
"seconds": 21.879,
"budget_s": 28.0682608775349,
"last_prompt_tokens": 5306
},
"bfcl:simple_python_216#1": {
"requests": 1,
"prompt_tokens": 383,
"completion_tokens": 110,
"allowance_tokens": 43684,
"length_stops": 0,
"errors": 0,
"seconds": 1.012,
"budget_s": 1.27073211199414,
"last_prompt_tokens": 383
},
"bfcl:multiple_96#1": {
"requests": 1,
"prompt_tokens": 769,
"completion_tokens": 86,
"allowance_tokens": 43608,
"length_stops": 0,
"errors": 0,
"seconds": 1.038,
"budget_s": 1.6268594542316892,
"last_prompt_tokens": 769
},
"bfcl:parallel_98#1": {
"requests": 1,
"prompt_tokens": 496,
"completion_tokens": 355,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 2.251,
"budget_s": 3.102777628608525,
"last_prompt_tokens": 496
},
"bfcl:parallel_multiple_97#1": {
"requests": 1,
"prompt_tokens": 977,
"completion_tokens": 562,
"allowance_tokens": 43567,
"length_stops": 0,
"errors": 0,
"seconds": 3.741,
"budget_s": 5.170692415475823,
"last_prompt_tokens": 977
},
"bfcl:multi_turn_base_86#1": {
"requests": 13,
"prompt_tokens": 97163,
"completion_tokens": 4019,
"allowance_tokens": 516844,
"length_stops": 0,
"errors": 0,
"seconds": 41.54,
"budget_s": 47.422816612888795,
"last_prompt_tokens": 9596
},
"bfcl:simple_python_217#1": {
"requests": 1,
"prompt_tokens": 456,
"completion_tokens": 146,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 1.153,
"budget_s": 1.6160011209750214,
"last_prompt_tokens": 456
},
"bfcl:multiple_97#1": {
"requests": 1,
"prompt_tokens": 640,
"completion_tokens": 94,
"allowance_tokens": 43633,
"length_stops": 0,
"errors": 0,
"seconds": 1.09,
"budget_s": 1.5077007184641946,
"last_prompt_tokens": 640
},
"bfcl:parallel_105#1": {
"requests": 1,
"prompt_tokens": 503,
"completion_tokens": 416,
"allowance_tokens": 43660,
"length_stops": 0,
"errors": 0,
"seconds": 2.522,
"budget_s": 3.5304117233319836,
"last_prompt_tokens": 503
},
"bfcl:parallel_multiple_100#1": {
"requests": 1,
"prompt_tokens": 599,
"completion_tokens": 329,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 2.525,
"budget_s": 3.0634649430673893,
"last_prompt_tokens": 599
},
"bfcl:multi_turn_base_88#1": {
"requests": 9,
"prompt_tokens": 57725,
"completion_tokens": 2603,
"allowance_tokens": 369868,
"length_stops": 0,
"errors": 0,
"seconds": 28.386,
"budget_s": 33.466351861545746,
"last_prompt_tokens": 7951
},
"bfcl:simple_python_221#1": {
"requests": 1,
"prompt_tokens": 426,
"completion_tokens": 104,
"allowance_tokens": 43675,
"length_stops": 0,
"errors": 0,
"seconds": 0.875,
"budget_s": 1.2875996665795388,
"last_prompt_tokens": 426
},
"bfcl:multiple_102#1": {
"requests": 1,
"prompt_tokens": 724,
"completion_tokens": 120,
"allowance_tokens": 43617,
"length_stops": 0,
"errors": 0,
"seconds": 1.259,
"budget_s": 1.799251171148056,
"last_prompt_tokens": 724
},
"bfcl:parallel_107#1": {
"requests": 1,
"prompt_tokens": 398,
"completion_tokens": 335,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 1.845,
"budget_s": 2.8334767082223613,
"last_prompt_tokens": 398
},
"bfcl:parallel_multiple_104#1": {
"requests": 1,
"prompt_tokens": 645,
"completion_tokens": 265,
"allowance_tokens": 43632,
"length_stops": 0,
"errors": 0,
"seconds": 1.808,
"budget_s": 2.6867538751820628,
"last_prompt_tokens": 645
},
"bfcl:multi_turn_base_89#1": {
"requests": 15,
"prompt_tokens": 75699,
"completion_tokens": 3010,
"allowance_tokens": 610679,
"length_stops": 0,
"errors": 0,
"seconds": 33.432,
"budget_s": 39.95517200045561,
"last_prompt_tokens": 6690
},
"bfcl:simple_python_225#1": {
"requests": 1,
"prompt_tokens": 447,
"completion_tokens": 124,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 1.062,
"budget_s": 1.4530379769657564,
"last_prompt_tokens": 447
},
"bfcl:multiple_103#1": {
"requests": 1,
"prompt_tokens": 836,
"completion_tokens": 109,
"allowance_tokens": 43595,
"length_stops": 0,
"errors": 0,
"seconds": 1.224,
"budget_s": 1.874912379208277,
"last_prompt_tokens": 836
},
"bfcl:parallel_108#1": {
"requests": 1,
"prompt_tokens": 405,
"completion_tokens": 200,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 1.545,
"budget_s": 1.917411791524378,
"last_prompt_tokens": 405
},
"bfcl:parallel_multiple_105#1": {
"requests": 1,
"prompt_tokens": 737,
"completion_tokens": 438,
"allowance_tokens": 43614,
"length_stops": 0,
"errors": 0,
"seconds": 3.145,
"budget_s": 3.99686950695148,
"last_prompt_tokens": 737
},
"bfcl:multi_turn_base_90#1": {
"requests": 16,
"prompt_tokens": 117750,
"completion_tokens": 3876,
"allowance_tokens": 635240,
"length_stops": 0,
"errors": 0,
"seconds": 43.48,
"budget_s": 50.039887911307176,
"last_prompt_tokens": 9371
},
"bfcl:simple_python_230#1": {
"requests": 1,
"prompt_tokens": 397,
"completion_tokens": 103,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 0.942,
"budget_s": 1.2416269724953124,
"last_prompt_tokens": 397
},
"bfcl:multiple_108#1": {
"requests": 1,
"prompt_tokens": 621,
"completion_tokens": 116,
"allowance_tokens": 43637,
"length_stops": 0,
"errors": 0,
"seconds": 1.065,
"budget_s": 1.6328956406552972,
"last_prompt_tokens": 621
},
"bfcl:parallel_110#1": {
"requests": 1,
"prompt_tokens": 463,
"completion_tokens": 195,
"allowance_tokens": 43668,
"length_stops": 0,
"errors": 0,
"seconds": 1.516,
"budget_s": 1.9613679292849224,
"last_prompt_tokens": 463
},
"bfcl:parallel_multiple_106#1": {
"requests": 1,
"prompt_tokens": 722,
"completion_tokens": 563,
"allowance_tokens": 43617,
"length_stops": 0,
"errors": 0,
"seconds": 3.627,
"budget_s": 4.833587431118691,
"last_prompt_tokens": 722
},
"bfcl:multi_turn_base_92#1": {
"requests": 30,
"prompt_tokens": 219606,
"completion_tokens": 8591,
"allowance_tokens": 1131219,
"length_stops": 0,
"errors": 0,
"seconds": 105.88699999999999,
"budget_s": 92.85285060956383,
"last_prompt_tokens": 12976
},
"bfcl:simple_python_235#1": {
"requests": 1,
"prompt_tokens": 369,
"completion_tokens": 125,
"allowance_tokens": 43687,
"length_stops": 0,
"errors": 0,
"seconds": 1.059,
"budget_s": 1.3546821091020058,
"last_prompt_tokens": 369
},
"bfcl:multiple_110#1": {
"requests": 1,
"prompt_tokens": 587,
"completion_tokens": 107,
"allowance_tokens": 43644,
"length_stops": 0,
"errors": 0,
"seconds": 1.033,
"budget_s": 1.5253337636373607,
"last_prompt_tokens": 587
},
"bfcl:parallel_114#1": {
"requests": 1,
"prompt_tokens": 473,
"completion_tokens": 713,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 4.134,
"budget_s": 5.526061110119504,
"last_prompt_tokens": 473
},
"bfcl:parallel_multiple_108#1": {
"requests": 1,
"prompt_tokens": 804,
"completion_tokens": 352,
"allowance_tokens": 43601,
"length_stops": 0,
"errors": 0,
"seconds": 2.572,
"budget_s": 3.4976612470049195,
"last_prompt_tokens": 804
},
"bfcl:multi_turn_base_93#1": {
"requests": 11,
"prompt_tokens": 46135,
"completion_tokens": 1923,
"allowance_tokens": 459507,
"length_stops": 0,
"errors": 0,
"seconds": 21.721999999999998,
"budget_s": 28.27848158945308,
"last_prompt_tokens": 5554
},
"bfcl:simple_python_239#1": {
"requests": 1,
"prompt_tokens": 388,
"completion_tokens": 112,
"allowance_tokens": 43683,
"length_stops": 0,
"errors": 0,
"seconds": 1.066,
"budget_s": 1.2911876517210712,
"last_prompt_tokens": 388
},
"bfcl:multiple_111#1": {
"requests": 1,
"prompt_tokens": 659,
"completion_tokens": 105,
"allowance_tokens": 43630,
"length_stops": 0,
"errors": 0,
"seconds": 1.17,
"budget_s": 1.6087408339103755,
"last_prompt_tokens": 659
},
"bfcl:parallel_116#1": {
"requests": 1,
"prompt_tokens": 474,
"completion_tokens": 297,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 2.018,
"budget_s": 2.67547737951444,
"last_prompt_tokens": 474
},
"bfcl:parallel_multiple_109#1": {
"requests": 1,
"prompt_tokens": 778,
"completion_tokens": 349,
"allowance_tokens": 43606,
"length_stops": 0,
"errors": 0,
"seconds": 2.291,
"budget_s": 3.4420239337132363,
"last_prompt_tokens": 778
},
"bfcl:multi_turn_base_94#1": {
"requests": 14,
"prompt_tokens": 71357,
"completion_tokens": 3076,
"allowance_tokens": 569410,
"length_stops": 0,
"errors": 0,
"seconds": 33.838,
"budget_s": 39.38520235650992,
"last_prompt_tokens": 6646
},
"bfcl:simple_python_240#1": {
"requests": 1,
"prompt_tokens": 401,
"completion_tokens": 127,
"allowance_tokens": 43680,
"length_stops": 0,
"errors": 0,
"seconds": 1.032,
"budget_s": 1.4115570055821651,
"last_prompt_tokens": 401
},
"bfcl:multiple_115#1": {
"requests": 1,
"prompt_tokens": 891,
"completion_tokens": 116,
"allowance_tokens": 43584,
"length_stops": 0,
"errors": 0,
"seconds": 1.34,
"budget_s": 1.9970892081875757,
"last_prompt_tokens": 891
},
"bfcl:parallel_117#1": {
"requests": 1,
"prompt_tokens": 514,
"completion_tokens": 562,
"allowance_tokens": 43658,
"length_stops": 0,
"errors": 0,
"seconds": 3.541,
"budget_s": 4.546167890411213,
"last_prompt_tokens": 514
},
"bfcl:parallel_multiple_110#1": {
"requests": 1,
"prompt_tokens": 610,
"completion_tokens": 345,
"allowance_tokens": 43639,
"length_stops": 0,
"errors": 0,
"seconds": 2.122,
"budget_s": 3.1879921739997443,
"last_prompt_tokens": 610
},
"bfcl:multi_turn_base_96#1": {
"requests": 11,
"prompt_tokens": 86962,
"completion_tokens": 9153,
"allowance_tokens": 416961,
"length_stops": 0,
"errors": 0,
"seconds": 83.003,
"budget_s": 79.73697933972448,
"last_prompt_tokens": 12088
},
"bfcl:simple_python_247#1": {
"requests": 1,
"prompt_tokens": 427,
"completion_tokens": 134,
"allowance_tokens": 43675,
"length_stops": 0,
"errors": 0,
"seconds": 1.073,
"budget_s": 1.4946167476783672,
"last_prompt_tokens": 427
},
"bfcl:multiple_116#1": {
"requests": 1,
"prompt_tokens": 551,
"completion_tokens": 110,
"allowance_tokens": 43651,
"length_stops": 0,
"errors": 0,
"seconds": 0.977,
"budget_s": 1.497341442903113,
"last_prompt_tokens": 551
},
"bfcl:parallel_118#1": {
"requests": 1,
"prompt_tokens": 414,
"completion_tokens": 264,
"allowance_tokens": 43678,
"length_stops": 0,
"errors": 0,
"seconds": 1.498,
"budget_s": 2.3683104379810946,
"last_prompt_tokens": 414
},
"bfcl:parallel_multiple_112#1": {
"requests": 1,
"prompt_tokens": 679,
"completion_tokens": 345,
"allowance_tokens": 43626,
"length_stops": 0,
"errors": 0,
"seconds": 2.533,
"budget_s": 3.2810638634802154,
"last_prompt_tokens": 679
},
"bfcl:multi_turn_base_97#1": {
"requests": 22,
"prompt_tokens": 137429,
"completion_tokens": 2976,
"allowance_tokens": 879066,
"length_stops": 0,
"errors": 0,
"seconds": 38.37899999999999,
"budget_s": 46.846786628600505,
"last_prompt_tokens": 7819
},
"bfcl:simple_python_249#1": {
"requests": 1,
"prompt_tokens": 423,
"completion_tokens": 148,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.201,
"budget_s": 1.5851997882344468,
"last_prompt_tokens": 423
},
"bfcl:multiple_117#1": {
"requests": 1,
"prompt_tokens": 787,
"completion_tokens": 99,
"allowance_tokens": 43604,
"length_stops": 0,
"errors": 0,
"seconds": 1.152,
"budget_s": 1.7402619190151953,
"last_prompt_tokens": 787
},
"bfcl:parallel_120#1": {
"requests": 1,
"prompt_tokens": 452,
"completion_tokens": 293,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 1.924,
"budget_s": 2.618379919281365,
"last_prompt_tokens": 452
},
"bfcl:parallel_multiple_120#1": {
"requests": 1,
"prompt_tokens": 596,
"completion_tokens": 211,
"allowance_tokens": 43642,
"length_stops": 0,
"errors": 0,
"seconds": 1.764,
"budget_s": 2.2504566981392697,
"last_prompt_tokens": 596
},
"bfcl:multi_turn_base_98#1": {
"requests": 12,
"prompt_tokens": 80622,
"completion_tokens": 2421,
"allowance_tokens": 492839,
"length_stops": 0,
"errors": 0,
"seconds": 30.055999999999997,
"budget_s": 34.70189193548429,
"last_prompt_tokens": 7860
},
"bfcl:simple_python_252#1": {
"requests": 1,
"prompt_tokens": 472,
"completion_tokens": 142,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 1.037,
"budget_s": 1.610160533209452,
"last_prompt_tokens": 472
},
"bfcl:multiple_121#1": {
"requests": 1,
"prompt_tokens": 691,
"completion_tokens": 110,
"allowance_tokens": 43623,
"length_stops": 0,
"errors": 0,
"seconds": 1.278,
"budget_s": 1.686182551993924,
"last_prompt_tokens": 691
},
"bfcl:parallel_121#1": {
"requests": 1,
"prompt_tokens": 449,
"completion_tokens": 222,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 1.509,
"budget_s": 2.1275852128063457,
"last_prompt_tokens": 449
},
"bfcl:parallel_multiple_121#1": {
"requests": 1,
"prompt_tokens": 787,
"completion_tokens": 609,
"allowance_tokens": 43604,
"length_stops": 0,
"errors": 0,
"seconds": 3.579,
"budget_s": 5.236621591591395,
"last_prompt_tokens": 787
},
"bfcl:multi_turn_base_99#1": {
"requests": 14,
"prompt_tokens": 70986,
"completion_tokens": 3705,
"allowance_tokens": 569043,
"length_stops": 0,
"errors": 0,
"seconds": 36.86599999999999,
"budget_s": 44.40553344511111,
"last_prompt_tokens": 7238
},
"bfcl:simple_python_260#1": {
"requests": 1,
"prompt_tokens": 575,
"completion_tokens": 142,
"allowance_tokens": 43646,
"length_stops": 0,
"errors": 0,
"seconds": 1.2,
"budget_s": 1.7490936348976915,
"last_prompt_tokens": 575
},
"bfcl:multiple_122#1": {
"requests": 1,
"prompt_tokens": 902,
"completion_tokens": 208,
"allowance_tokens": 43582,
"length_stops": 0,
"errors": 0,
"seconds": 1.782,
"budget_s": 2.6426425864057954,
"last_prompt_tokens": 902
},
"bfcl:parallel_122#1": {
"requests": 1,
"prompt_tokens": 518,
"completion_tokens": 411,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 2.948,
"budget_s": 3.51636666330035,
"last_prompt_tokens": 518
},
"bfcl:parallel_multiple_126#1": {
"requests": 1,
"prompt_tokens": 572,
"completion_tokens": 247,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 1.822,
"budget_s": 2.464885795821518,
"last_prompt_tokens": 572
},
"bfcl:multi_turn_base_102#1": {
"requests": 14,
"prompt_tokens": 81271,
"completion_tokens": 3044,
"allowance_tokens": 567732,
"length_stops": 0,
"errors": 0,
"seconds": 33.156,
"budget_s": 39.84834864893055,
"last_prompt_tokens": 7460
},
"bfcl:simple_python_261#1": {
"requests": 1,
"prompt_tokens": 400,
"completion_tokens": 95,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 0.85,
"budget_s": 1.190828710081077,
"last_prompt_tokens": 400
},
"bfcl:multiple_123#1": {
"requests": 1,
"prompt_tokens": 703,
"completion_tokens": 136,
"allowance_tokens": 43621,
"length_stops": 0,
"errors": 0,
"seconds": 1.413,
"budget_s": 1.8806147200025114,
"last_prompt_tokens": 703
},
"bfcl:parallel_123#1": {
"requests": 1,
"prompt_tokens": 463,
"completion_tokens": 290,
"allowance_tokens": 43668,
"length_stops": 0,
"errors": 0,
"seconds": 1.72,
"budget_s": 2.612650613392254,
"last_prompt_tokens": 463
},
"bfcl:parallel_multiple_132#1": {
"requests": 1,
"prompt_tokens": 630,
"completion_tokens": 263,
"allowance_tokens": 43635,
"length_stops": 0,
"errors": 0,
"seconds": 1.717,
"budget_s": 2.6528096848057876,
"last_prompt_tokens": 630
},
"bfcl:multi_turn_base_103#1": {
"requests": 14,
"prompt_tokens": 66190,
"completion_tokens": 2731,
"allowance_tokens": 578735,
"length_stops": 0,
"errors": 0,
"seconds": 28.599999999999998,
"budget_s": 37.301930670691426,
"last_prompt_tokens": 6736
},
"bfcl:simple_python_263#1": {
"requests": 1,
"prompt_tokens": 387,
"completion_tokens": 86,
"allowance_tokens": 43683,
"length_stops": 0,
"errors": 0,
"seconds": 0.744,
"budget_s": 1.1115929994267622,
"last_prompt_tokens": 387
},
"bfcl:multiple_126#1": {
"requests": 1,
"prompt_tokens": 782,
"completion_tokens": 136,
"allowance_tokens": 43605,
"length_stops": 0,
"errors": 0,
"seconds": 1.382,
"budget_s": 1.987175060132326,
"last_prompt_tokens": 782
},
"bfcl:parallel_126#1": {
"requests": 1,
"prompt_tokens": 446,
"completion_tokens": 261,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 1.971,
"budget_s": 2.390907298455605,
"last_prompt_tokens": 446
},
"bfcl:parallel_multiple_134#1": {
"requests": 1,
"prompt_tokens": 587,
"completion_tokens": 176,
"allowance_tokens": 43644,
"length_stops": 0,
"errors": 0,
"seconds": 1.374,
"budget_s": 1.998370660515317,
"last_prompt_tokens": 587
},
"bfcl:multi_turn_base_105#1": {
"requests": 8,
"prompt_tokens": 25926,
"completion_tokens": 1198,
"allowance_tokens": 339108,
"length_stops": 0,
"errors": 0,
"seconds": 14.058,
"budget_s": 18.407739587727427,
"last_prompt_tokens": 3837
},
"bfcl:simple_python_269#1": {
"requests": 1,
"prompt_tokens": 480,
"completion_tokens": 197,
"allowance_tokens": 43665,
"length_stops": 0,
"errors": 0,
"seconds": 1.474,
"budget_s": 1.998009849791066,
"last_prompt_tokens": 480
},
"bfcl:multiple_130#1": {
"requests": 1,
"prompt_tokens": 697,
"completion_tokens": 125,
"allowance_tokens": 43622,
"length_stops": 0,
"errors": 0,
"seconds": 1.123,
"budget_s": 1.7971098504004772,
"last_prompt_tokens": 697
},
"bfcl:parallel_127#1": {
"requests": 1,
"prompt_tokens": 446,
"completion_tokens": 258,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 1.529,
"budget_s": 2.3703404768522156,
"last_prompt_tokens": 446
},
"bfcl:parallel_multiple_136#1": {
"requests": 1,
"prompt_tokens": 1000,
"completion_tokens": 322,
"allowance_tokens": 43563,
"length_stops": 0,
"errors": 0,
"seconds": 2.398,
"budget_s": 3.5563705836981607,
"last_prompt_tokens": 1000
},
"bfcl:multi_turn_base_110#1": {
"requests": 17,
"prompt_tokens": 95506,
"completion_tokens": 3607,
"allowance_tokens": 689583,
"length_stops": 0,
"errors": 0,
"seconds": 39.637,
"budget_s": 46.59327787706124,
"last_prompt_tokens": 8132
},
"bfcl:simple_python_270#1": {
"requests": 1,
"prompt_tokens": 391,
"completion_tokens": 89,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 0.694,
"budget_s": 1.137555281289889,
"last_prompt_tokens": 391
},
"bfcl:multiple_131#1": {
"requests": 1,
"prompt_tokens": 775,
"completion_tokens": 136,
"allowance_tokens": 43607,
"length_stops": 0,
"errors": 0,
"seconds": 1.405,
"budget_s": 1.9777330046777855,
"last_prompt_tokens": 775
},
"bfcl:parallel_130#1": {
"requests": 1,
"prompt_tokens": 476,
"completion_tokens": 248,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 1.811,
"budget_s": 2.3422503567889486,
"last_prompt_tokens": 476
},
"bfcl:parallel_multiple_138#1": {
"requests": 1,
"prompt_tokens": 861,
"completion_tokens": 400,
"allowance_tokens": 43590,
"length_stops": 0,
"errors": 0,
"seconds": 2.972,
"budget_s": 3.9036157013604087,
"last_prompt_tokens": 861
},
"bfcl:multi_turn_base_111#1": {
"requests": 11,
"prompt_tokens": 49356,
"completion_tokens": 2267,
"allowance_tokens": 459277,
"length_stops": 0,
"errors": 0,
"seconds": 25.164,
"budget_s": 30.751463997161153,
"last_prompt_tokens": 5613
},
"bfcl:simple_python_272#1": {
"requests": 1,
"prompt_tokens": 351,
"completion_tokens": 78,
"allowance_tokens": 43690,
"length_stops": 0,
"errors": 0,
"seconds": 0.814,
"budget_s": 1.0081889994800866,
"last_prompt_tokens": 351
},
"bfcl:multiple_132#1": {
"requests": 1,
"prompt_tokens": 760,
"completion_tokens": 241,
"allowance_tokens": 43610,
"length_stops": 0,
"errors": 0,
"seconds": 1.935,
"budget_s": 2.6773387848223997,
"last_prompt_tokens": 760
},
"bfcl:parallel_131#1": {
"requests": 1,
"prompt_tokens": 449,
"completion_tokens": 410,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 2.768,
"budget_s": 3.416439366618749,
"last_prompt_tokens": 449
},
"bfcl:parallel_multiple_139#1": {
"requests": 1,
"prompt_tokens": 1147,
"completion_tokens": 519,
"allowance_tokens": 43534,
"length_stops": 0,
"errors": 0,
"seconds": 3.357,
"budget_s": 5.1052083668660835,
"last_prompt_tokens": 1147
},
"bfcl:multi_turn_base_116#1": {
"requests": 13,
"prompt_tokens": 50647,
"completion_tokens": 1994,
"allowance_tokens": 538921,
"length_stops": 0,
"errors": 0,
"seconds": 24.1,
"budget_s": 29.412684931901794,
"last_prompt_tokens": 5038
},
"bfcl:simple_python_280#1": {
"requests": 1,
"prompt_tokens": 397,
"completion_tokens": 138,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 0.97,
"budget_s": 1.4815732245348554,
"last_prompt_tokens": 397
},
"bfcl:multiple_135#1": {
"requests": 1,
"prompt_tokens": 589,
"completion_tokens": 146,
"allowance_tokens": 43643,
"length_stops": 0,
"errors": 0,
"seconds": 1.167,
"budget_s": 1.7954001746112918,
"last_prompt_tokens": 589
},
"bfcl:parallel_134#1": {
"requests": 1,
"prompt_tokens": 494,
"completion_tokens": 396,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 2.384,
"budget_s": 3.381159793724978,
"last_prompt_tokens": 494
},
"bfcl:parallel_multiple_145#1": {
"requests": 1,
"prompt_tokens": 1166,
"completion_tokens": 1125,
"allowance_tokens": 43530,
"length_stops": 0,
"errors": 0,
"seconds": 8.963,
"budget_s": 9.285334766984498,
"last_prompt_tokens": 1166
},
"bfcl:multi_turn_base_117#1": {
"requests": 15,
"prompt_tokens": 61465,
"completion_tokens": 3151,
"allowance_tokens": 616710,
"length_stops": 0,
"errors": 0,
"seconds": 32.629,
"budget_s": 38.64223065607584,
"last_prompt_tokens": 6094
},
"bfcl:simple_python_282#1": {
"requests": 1,
"prompt_tokens": 411,
"completion_tokens": 103,
"allowance_tokens": 43678,
"length_stops": 0,
"errors": 0,
"seconds": 0.81,
"budget_s": 1.2605110834043933,
"last_prompt_tokens": 411
},
"bfcl:multiple_139#1": {
"requests": 1,
"prompt_tokens": 921,
"completion_tokens": 135,
"allowance_tokens": 43578,
"length_stops": 0,
"errors": 0,
"seconds": 1.488,
"budget_s": 2.167811696957073,
"last_prompt_tokens": 921
},
"bfcl:parallel_137#1": {
"requests": 1,
"prompt_tokens": 491,
"completion_tokens": 683,
"allowance_tokens": 43663,
"length_stops": 0,
"errors": 0,
"seconds": 3.391,
"budget_s": 5.344672465254428,
"last_prompt_tokens": 491
},
"bfcl:parallel_multiple_151#1": {
"requests": 1,
"prompt_tokens": 1164,
"completion_tokens": 520,
"allowance_tokens": 43530,
"length_stops": 0,
"errors": 0,
"seconds": 4.051,
"budget_s": 5.134994680171098,
"last_prompt_tokens": 1164
},
"bfcl:multi_turn_base_118#1": {
"requests": 12,
"prompt_tokens": 53425,
"completion_tokens": 3125,
"allowance_tokens": 492469,
"length_stops": 0,
"errors": 0,
"seconds": 30.376000000000005,
"budget_s": 36.07919143404249,
"last_prompt_tokens": 6213
},
"bfcl:simple_python_285#1": {
"requests": 1,
"prompt_tokens": 430,
"completion_tokens": 143,
"allowance_tokens": 43675,
"length_stops": 0,
"errors": 0,
"seconds": 1.074,
"budget_s": 1.5603638076833386,
"last_prompt_tokens": 430
},
"bfcl:multiple_140#1": {
"requests": 1,
"prompt_tokens": 682,
"completion_tokens": 150,
"allowance_tokens": 43625,
"length_stops": 0,
"errors": 0,
"seconds": 1.319,
"budget_s": 1.948267054454707,
"last_prompt_tokens": 682
},
"bfcl:parallel_139#1": {
"requests": 1,
"prompt_tokens": 508,
"completion_tokens": 277,
"allowance_tokens": 43659,
"length_stops": 0,
"errors": 0,
"seconds": 2.081,
"budget_s": 2.5842266476996123,
"last_prompt_tokens": 508
},
"bfcl:parallel_multiple_154#1": {
"requests": 1,
"prompt_tokens": 849,
"completion_tokens": 318,
"allowance_tokens": 43592,
"length_stops": 0,
"errors": 0,
"seconds": 2.314,
"budget_s": 3.325269530088553,
"last_prompt_tokens": 849
},
"bfcl:multi_turn_base_122#1": {
"requests": 11,
"prompt_tokens": 52321,
"completion_tokens": 3876,
"allowance_tokens": 447452,
"length_stops": 0,
"errors": 0,
"seconds": 37.506,
"budget_s": 40.34289695949405,
"last_prompt_tokens": 6698
},
"bfcl:simple_python_289#1": {
"requests": 1,
"prompt_tokens": 377,
"completion_tokens": 119,
"allowance_tokens": 43685,
"length_stops": 0,
"errors": 0,
"seconds": 1.035,
"budget_s": 1.324339386414702,
"last_prompt_tokens": 377
},
"bfcl:multiple_143#1": {
"requests": 1,
"prompt_tokens": 862,
"completion_tokens": 221,
"allowance_tokens": 43590,
"length_stops": 0,
"errors": 0,
"seconds": 1.831,
"budget_s": 2.6778108774231084,
"last_prompt_tokens": 862
},
"bfcl:parallel_140#1": {
"requests": 1,
"prompt_tokens": 442,
"completion_tokens": 375,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 2.206,
"budget_s": 3.167051059124665,
"last_prompt_tokens": 442
},
"bfcl:parallel_multiple_157#1": {
"requests": 1,
"prompt_tokens": 931,
"completion_tokens": 387,
"allowance_tokens": 43576,
"length_stops": 0,
"errors": 0,
"seconds": 2.94,
"budget_s": 3.908913362291127,
"last_prompt_tokens": 931
},
"bfcl:multi_turn_base_124#1": {
"requests": 10,
"prompt_tokens": 59870,
"completion_tokens": 1714,
"allowance_tokens": 415001,
"length_stops": 0,
"errors": 0,
"seconds": 22.344,
"budget_s": 27.24357487857259,
"last_prompt_tokens": 7076
},
"bfcl:simple_python_291#1": {
"requests": 1,
"prompt_tokens": 479,
"completion_tokens": 171,
"allowance_tokens": 43665,
"length_stops": 0,
"errors": 0,
"seconds": 1.32,
"budget_s": 1.8184151974967568,
"last_prompt_tokens": 479
},
"bfcl:multiple_144#1": {
"requests": 1,
"prompt_tokens": 526,
"completion_tokens": 101,
"allowance_tokens": 43656,
"length_stops": 0,
"errors": 0,
"seconds": 0.919,
"budget_s": 1.4019193514695858,
"last_prompt_tokens": 526
},
"bfcl:parallel_143#1": {
"requests": 1,
"prompt_tokens": 461,
"completion_tokens": 287,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 2.071,
"budget_s": 2.5893860616589954,
"last_prompt_tokens": 461
},
"bfcl:parallel_multiple_159#1": {
"requests": 1,
"prompt_tokens": 1072,
"completion_tokens": 412,
"allowance_tokens": 43548,
"length_stops": 0,
"errors": 0,
"seconds": 2.758,
"budget_s": 4.270493516475117,
"last_prompt_tokens": 1072
},
"bfcl:multi_turn_base_126#1": {
"requests": 9,
"prompt_tokens": 29649,
"completion_tokens": 1076,
"allowance_tokens": 380592,
"length_stops": 0,
"errors": 0,
"seconds": 15.166,
"budget_s": 19.57172240048725,
"last_prompt_tokens": 4012
},
"bfcl:simple_python_293#1": {
"requests": 1,
"prompt_tokens": 469,
"completion_tokens": 183,
"allowance_tokens": 43667,
"length_stops": 0,
"errors": 0,
"seconds": 1.291,
"budget_s": 1.8871938332609708,
"last_prompt_tokens": 469
},
"bfcl:multiple_146#1": {
"requests": 1,
"prompt_tokens": 554,
"completion_tokens": 106,
"allowance_tokens": 43650,
"length_stops": 0,
"errors": 0,
"seconds": 1.027,
"budget_s": 1.4739656092933968,
"last_prompt_tokens": 554
},
"bfcl:parallel_147#1": {
"requests": 1,
"prompt_tokens": 497,
"completion_tokens": 450,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 3.503,
"budget_s": 3.7554091777807903,
"last_prompt_tokens": 497
},
"bfcl:parallel_multiple_160#1": {
"requests": 1,
"prompt_tokens": 750,
"completion_tokens": 228,
"allowance_tokens": 43612,
"length_stops": 0,
"errors": 0,
"seconds": 1.653,
"budget_s": 2.574727240558368,
"last_prompt_tokens": 750
},
"bfcl:multi_turn_base_127#1": {
"requests": 10,
"prompt_tokens": 32810,
"completion_tokens": 1401,
"allowance_tokens": 421621,
"length_stops": 0,
"errors": 0,
"seconds": 17.866,
"budget_s": 23.04209946565899,
"last_prompt_tokens": 4053
},
"bfcl:simple_python_303#1": {
"requests": 1,
"prompt_tokens": 410,
"completion_tokens": 106,
"allowance_tokens": 43679,
"length_stops": 0,
"errors": 0,
"seconds": 1.062,
"budget_s": 1.2797290399428485,
"last_prompt_tokens": 410
},
"bfcl:multiple_150#1": {
"requests": 1,
"prompt_tokens": 1092,
"completion_tokens": 123,
"allowance_tokens": 43544,
"length_stops": 0,
"errors": 0,
"seconds": 1.469,
"budget_s": 2.3162003366472916,
"last_prompt_tokens": 1092
},
"bfcl:parallel_149#1": {
"requests": 1,
"prompt_tokens": 423,
"completion_tokens": 211,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.533,
"budget_s": 2.0171030419056244,
"last_prompt_tokens": 423
},
"bfcl:parallel_multiple_161#1": {
"requests": 1,
"prompt_tokens": 773,
"completion_tokens": 256,
"allowance_tokens": 43607,
"length_stops": 0,
"errors": 0,
"seconds": 1.895,
"budget_s": 2.797708138683493,
"last_prompt_tokens": 773
},
"bfcl:multi_turn_base_128#1": {
"requests": 11,
"prompt_tokens": 39952,
"completion_tokens": 1581,
"allowance_tokens": 459666,
"length_stops": 0,
"errors": 0,
"seconds": 21.105999999999998,
"budget_s": 26.658204466536443,
"last_prompt_tokens": 4609
},
"bfcl:simple_python_304#1": {
"requests": 1,
"prompt_tokens": 439,
"completion_tokens": 150,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 1.216,
"budget_s": 1.6204928436756565,
"last_prompt_tokens": 439
},
"bfcl:multiple_151#1": {
"requests": 1,
"prompt_tokens": 729,
"completion_tokens": 324,
"allowance_tokens": 43616,
"length_stops": 0,
"errors": 0,
"seconds": 2.533,
"budget_s": 3.2045393655032077,
"last_prompt_tokens": 729
},
"bfcl:parallel_150#1": {
"requests": 1,
"prompt_tokens": 534,
"completion_tokens": 640,
"allowance_tokens": 43654,
"length_stops": 0,
"errors": 0,
"seconds": 4.32,
"budget_s": 5.107882553398024,
"last_prompt_tokens": 534
},
"bfcl:parallel_multiple_162#1": {
"requests": 1,
"prompt_tokens": 926,
"completion_tokens": 419,
"allowance_tokens": 43577,
"length_stops": 0,
"errors": 0,
"seconds": 2.645,
"budget_s": 4.121548467402609,
"last_prompt_tokens": 926
},
"bfcl:multi_turn_base_130#1": {
"requests": 10,
"prompt_tokens": 53723,
"completion_tokens": 4300,
"allowance_tokens": 401318,
"length_stops": 0,
"errors": 0,
"seconds": 40.730000000000004,
"budget_s": 42.11932548835808,
"last_prompt_tokens": 7173
},
"bfcl:simple_python_306#1": {
"requests": 1,
"prompt_tokens": 433,
"completion_tokens": 167,
"allowance_tokens": 43674,
"length_stops": 0,
"errors": 0,
"seconds": 1.344,
"budget_s": 1.7289449757052568,
"last_prompt_tokens": 433
},
"bfcl:multiple_156#1": {
"requests": 1,
"prompt_tokens": 714,
"completion_tokens": 138,
"allowance_tokens": 43619,
"length_stops": 0,
"errors": 0,
"seconds": 1.32,
"budget_s": 1.9091634501190489,
"last_prompt_tokens": 714
},
"bfcl:parallel_151#1": {
"requests": 1,
"prompt_tokens": 472,
"completion_tokens": 772,
"allowance_tokens": 43666,
"length_stops": 0,
"errors": 0,
"seconds": 5.454,
"budget_s": 5.9291930699212285,
"last_prompt_tokens": 472
},
"bfcl:parallel_multiple_163#1": {
"requests": 1,
"prompt_tokens": 653,
"completion_tokens": 182,
"allowance_tokens": 43631,
"length_stops": 0,
"errors": 0,
"seconds": 1.345,
"budget_s": 2.128529398007764,
"last_prompt_tokens": 653
},
"bfcl:multi_turn_base_131#1": {
"requests": 16,
"prompt_tokens": 87976,
"completion_tokens": 3501,
"allowance_tokens": 647391,
"length_stops": 0,
"errors": 0,
"seconds": 36.816,
"budget_s": 43.56541971296346,
"last_prompt_tokens": 7595
},
"bfcl:simple_python_316#1": {
"requests": 1,
"prompt_tokens": 416,
"completion_tokens": 141,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 1.243,
"budget_s": 1.5277684823719977,
"last_prompt_tokens": 416
},
"bfcl:multiple_158#1": {
"requests": 1,
"prompt_tokens": 912,
"completion_tokens": 115,
"allowance_tokens": 43580,
"length_stops": 0,
"errors": 0,
"seconds": 1.369,
"budget_s": 2.0185597673500677,
"last_prompt_tokens": 912
},
"bfcl:parallel_158#1": {
"requests": 1,
"prompt_tokens": 448,
"completion_tokens": 479,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 2.678,
"budget_s": 3.888127398431771,
"last_prompt_tokens": 448
},
"bfcl:parallel_multiple_164#1": {
"requests": 1,
"prompt_tokens": 687,
"completion_tokens": 359,
"allowance_tokens": 43624,
"length_stops": 0,
"errors": 0,
"seconds": 2.534,
"budget_s": 3.3878332848155077,
"last_prompt_tokens": 687
},
"bfcl:multi_turn_base_135#1": {
"requests": 10,
"prompt_tokens": 34708,
"completion_tokens": 1829,
"allowance_tokens": 420178,
"length_stops": 0,
"errors": 0,
"seconds": 18.509999999999998,
"budget_s": 24.30640439735381,
"last_prompt_tokens": 4554
},
"bfcl:simple_python_332#1": {
"requests": 1,
"prompt_tokens": 392,
"completion_tokens": 86,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 0.716,
"budget_s": 1.1183373247514339,
"last_prompt_tokens": 392
},
"bfcl:multiple_160#1": {
"requests": 1,
"prompt_tokens": 848,
"completion_tokens": 119,
"allowance_tokens": 43592,
"length_stops": 0,
"errors": 0,
"seconds": 1.429,
"budget_s": 1.9596548319987874,
"last_prompt_tokens": 848
},
"bfcl:parallel_162#1": {
"requests": 1,
"prompt_tokens": 538,
"completion_tokens": 258,
"allowance_tokens": 43653,
"length_stops": 0,
"errors": 0,
"seconds": 1.836,
"budget_s": 2.494436062826177,
"last_prompt_tokens": 538
},
"bfcl:parallel_multiple_168#1": {
"requests": 1,
"prompt_tokens": 777,
"completion_tokens": 310,
"allowance_tokens": 43606,
"length_stops": 0,
"errors": 0,
"seconds": 2.292,
"budget_s": 3.17330638780424,
"last_prompt_tokens": 777
},
"bfcl:multi_turn_base_150#1": {
"requests": 6,
"prompt_tokens": 22950,
"completion_tokens": 731,
"allowance_tokens": 254914,
"length_stops": 0,
"errors": 0,
"seconds": 11.102000000000002,
"budget_s": 14.817697886098715,
"last_prompt_tokens": 4205
},
"bfcl:simple_python_334#1": {
"requests": 1,
"prompt_tokens": 453,
"completion_tokens": 172,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 1.429,
"budget_s": 1.7902003130095934,
"last_prompt_tokens": 453
},
"bfcl:multiple_163#1": {
"requests": 1,
"prompt_tokens": 599,
"completion_tokens": 119,
"allowance_tokens": 43641,
"length_stops": 0,
"errors": 0,
"seconds": 1.146,
"budget_s": 1.6237874308301308,
"last_prompt_tokens": 599
},
"bfcl:parallel_163#1": {
"requests": 1,
"prompt_tokens": 544,
"completion_tokens": 283,
"allowance_tokens": 43652,
"length_stops": 0,
"errors": 0,
"seconds": 1.787,
"budget_s": 2.6739194332440284,
"last_prompt_tokens": 544
},
"bfcl:parallel_multiple_170#1": {
"requests": 1,
"prompt_tokens": 1050,
"completion_tokens": 428,
"allowance_tokens": 43553,
"length_stops": 0,
"errors": 0,
"seconds": 3.082,
"budget_s": 4.350508200264638,
"last_prompt_tokens": 1050
},
"bfcl:multi_turn_base_153#1": {
"requests": 11,
"prompt_tokens": 49935,
"completion_tokens": 1861,
"allowance_tokens": 456477,
"length_stops": 0,
"errors": 0,
"seconds": 21.776000000000003,
"budget_s": 28.144788797008854,
"last_prompt_tokens": 5568
},
"bfcl:simple_python_338#1": {
"requests": 1,
"prompt_tokens": 422,
"completion_tokens": 117,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 0.874,
"budget_s": 1.3713270999344886,
"last_prompt_tokens": 422
},
"bfcl:multiple_166#1": {
"requests": 1,
"prompt_tokens": 737,
"completion_tokens": 153,
"allowance_tokens": 43614,
"length_stops": 0,
"errors": 0,
"seconds": 1.302,
"budget_s": 2.0430214546294865,
"last_prompt_tokens": 737
},
"bfcl:parallel_164#1": {
"requests": 1,
"prompt_tokens": 535,
"completion_tokens": 270,
"allowance_tokens": 43654,
"length_stops": 0,
"errors": 0,
"seconds": 2.029,
"budget_s": 2.5726567540449317,
"last_prompt_tokens": 535
},
"bfcl:parallel_multiple_172#1": {
"requests": 1,
"prompt_tokens": 919,
"completion_tokens": 369,
"allowance_tokens": 43578,
"length_stops": 0,
"errors": 0,
"seconds": 2.845,
"budget_s": 3.769326051891578,
"last_prompt_tokens": 919
},
"bfcl:multi_turn_base_156#1": {
"requests": 14,
"prompt_tokens": 93818,
"completion_tokens": 2910,
"allowance_tokens": 561768,
"length_stops": 0,
"errors": 0,
"seconds": 32.434999999999995,
"budget_s": 40.74661852644576,
"last_prompt_tokens": 8061
},
"bfcl:simple_python_342#1": {
"requests": 1,
"prompt_tokens": 422,
"completion_tokens": 124,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 0.993,
"budget_s": 1.4193163503423973,
"last_prompt_tokens": 422
},
"bfcl:multiple_167#1": {
"requests": 1,
"prompt_tokens": 815,
"completion_tokens": 130,
"allowance_tokens": 43599,
"length_stops": 0,
"errors": 0,
"seconds": 1.304,
"budget_s": 1.9905539640683814,
"last_prompt_tokens": 815
},
"bfcl:parallel_166#1": {
"requests": 1,
"prompt_tokens": 532,
"completion_tokens": 390,
"allowance_tokens": 43655,
"length_stops": 0,
"errors": 0,
"seconds": 2.601,
"budget_s": 3.391283022985705,
"last_prompt_tokens": 532
},
"bfcl:parallel_multiple_175#1": {
"requests": 1,
"prompt_tokens": 665,
"completion_tokens": 515,
"allowance_tokens": 43628,
"length_stops": 0,
"errors": 0,
"seconds": 4.195,
"budget_s": 4.427632976763201,
"last_prompt_tokens": 665
},
"bfcl:multi_turn_base_160#1": {
"requests": 10,
"prompt_tokens": 105176,
"completion_tokens": 9299,
"allowance_tokens": 364287,
"length_stops": 0,
"errors": 0,
"seconds": 86.06299999999999,
"budget_s": 80.53017277108955,
"last_prompt_tokens": 14097
},
"bfcl:simple_python_344#1": {
"requests": 1,
"prompt_tokens": 410,
"completion_tokens": 143,
"allowance_tokens": 43679,
"length_stops": 0,
"errors": 0,
"seconds": 1.057,
"budget_s": 1.5333865063846512,
"last_prompt_tokens": 410
},
"bfcl:multiple_168#1": {
"requests": 1,
"prompt_tokens": 674,
"completion_tokens": 232,
"allowance_tokens": 43627,
"length_stops": 0,
"errors": 0,
"seconds": 2.229,
"budget_s": 2.499635924427876,
"last_prompt_tokens": 674
},
"bfcl:parallel_169#1": {
"requests": 1,
"prompt_tokens": 576,
"completion_tokens": 1429,
"allowance_tokens": 43646,
"length_stops": 0,
"errors": 0,
"seconds": 8.301,
"budget_s": 10.573608967816684,
"last_prompt_tokens": 576
},
"bfcl:parallel_multiple_180#1": {
"requests": 1,
"prompt_tokens": 773,
"completion_tokens": 355,
"allowance_tokens": 43607,
"length_stops": 0,
"errors": 0,
"seconds": 2.264,
"budget_s": 3.4764132515953436,
"last_prompt_tokens": 773
},
"bfcl:multi_turn_base_166#1": {
"requests": 11,
"prompt_tokens": 60276,
"completion_tokens": 1821,
"allowance_tokens": 454418,
"length_stops": 0,
"errors": 0,
"seconds": 22.712,
"budget_s": 29.73334716363802,
"last_prompt_tokens": 6608
},
"bfcl:simple_python_347#1": {
"requests": 1,
"prompt_tokens": 392,
"completion_tokens": 91,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 0.844,
"budget_s": 1.1526153607570828,
"last_prompt_tokens": 392
},
"bfcl:multiple_170#1": {
"requests": 1,
"prompt_tokens": 834,
"completion_tokens": 115,
"allowance_tokens": 43595,
"length_stops": 0,
"errors": 0,
"seconds": 1.272,
"budget_s": 1.913348292285187,
"last_prompt_tokens": 834
},
"bfcl:parallel_170#1": {
"requests": 1,
"prompt_tokens": 544,
"completion_tokens": 747,
"allowance_tokens": 43652,
"length_stops": 0,
"errors": 0,
"seconds": 3.971,
"budget_s": 5.854921174568258,
"last_prompt_tokens": 544
},
"bfcl:parallel_multiple_181#1": {
"requests": 1,
"prompt_tokens": 817,
"completion_tokens": 290,
"allowance_tokens": 43599,
"length_stops": 0,
"errors": 0,
"seconds": 2.094,
"budget_s": 3.0901488463790185,
"last_prompt_tokens": 817
},
"bfcl:multi_turn_base_171#1": {
"requests": 14,
"prompt_tokens": 125529,
"completion_tokens": 7325,
"allowance_tokens": 528785,
"length_stops": 0,
"errors": 0,
"seconds": 64.702,
"budget_s": 70.27899285904462,
"last_prompt_tokens": 12209
},
"bfcl:simple_python_357#1": {
"requests": 1,
"prompt_tokens": 390,
"completion_tokens": 86,
"allowance_tokens": 43683,
"length_stops": 0,
"errors": 0,
"seconds": 0.794,
"budget_s": 1.1156395946215651,
"last_prompt_tokens": 390
},
"bfcl:multiple_172#1": {
"requests": 1,
"prompt_tokens": 938,
"completion_tokens": 170,
"allowance_tokens": 43575,
"length_stops": 0,
"errors": 0,
"seconds": 1.805,
"budget_s": 2.4306886551005,
"last_prompt_tokens": 938
},
"bfcl:parallel_171#1": {
"requests": 1,
"prompt_tokens": 518,
"completion_tokens": 263,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 2.062,
"budget_s": 2.5017367975331393,
"last_prompt_tokens": 518
},
"bfcl:parallel_multiple_182#1": {
"requests": 1,
"prompt_tokens": 839,
"completion_tokens": 303,
"allowance_tokens": 43594,
"length_stops": 0,
"errors": 0,
"seconds": 2.289,
"budget_s": 3.208946771422262,
"last_prompt_tokens": 839
},
"bfcl:multi_turn_base_175#1": {
"requests": 10,
"prompt_tokens": 79897,
"completion_tokens": 4896,
"allowance_tokens": 395989,
"length_stops": 0,
"errors": 0,
"seconds": 45.785,
"budget_s": 50.08730103711253,
"last_prompt_tokens": 10383
},
"bfcl:simple_python_358#1": {
"requests": 1,
"prompt_tokens": 448,
"completion_tokens": 104,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 0.914,
"budget_s": 1.3172746980080947,
"last_prompt_tokens": 448
},
"bfcl:multiple_173#1": {
"requests": 1,
"prompt_tokens": 700,
"completion_tokens": 82,
"allowance_tokens": 43622,
"length_stops": 0,
"errors": 0,
"seconds": 1.073,
"budget_s": 1.5063653359466986,
"last_prompt_tokens": 700
},
"bfcl:parallel_175#1": {
"requests": 1,
"prompt_tokens": 573,
"completion_tokens": 356,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 2.319,
"budget_s": 3.213495845809601,
"last_prompt_tokens": 573
},
"bfcl:parallel_multiple_185#1": {
"requests": 1,
"prompt_tokens": 673,
"completion_tokens": 479,
"allowance_tokens": 43627,
"length_stops": 0,
"errors": 0,
"seconds": 3.062,
"budget_s": 4.191622038042003,
"last_prompt_tokens": 673
},
"bfcl:multi_turn_base_178#1": {
"requests": 16,
"prompt_tokens": 121072,
"completion_tokens": 5153,
"allowance_tokens": 627532,
"length_stops": 0,
"errors": 0,
"seconds": 51.282000000000004,
"budget_s": 57.23251256195595,
"last_prompt_tokens": 10005
},
"bfcl:simple_python_363#1": {
"requests": 1,
"prompt_tokens": 439,
"completion_tokens": 143,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 1.24,
"budget_s": 1.5725035932677478,
"last_prompt_tokens": 439
},
"bfcl:multiple_176#1": {
"requests": 1,
"prompt_tokens": 1085,
"completion_tokens": 130,
"allowance_tokens": 43546,
"length_stops": 0,
"errors": 0,
"seconds": 1.537,
"budget_s": 2.3547475316006596,
"last_prompt_tokens": 1085
},
"bfcl:parallel_176#1": {
"requests": 1,
"prompt_tokens": 489,
"completion_tokens": 282,
"allowance_tokens": 43663,
"length_stops": 0,
"errors": 0,
"seconds": 1.692,
"budget_s": 2.5928762474715086,
"last_prompt_tokens": 489
},
"bfcl:parallel_multiple_187#1": {
"requests": 1,
"prompt_tokens": 803,
"completion_tokens": 241,
"allowance_tokens": 43601,
"length_stops": 0,
"errors": 0,
"seconds": 1.813,
"budget_s": 2.735339982614577,
"last_prompt_tokens": 803
},
"bfcl:multi_turn_base_180#1": {
"requests": 18,
"prompt_tokens": 132458,
"completion_tokens": 5448,
"allowance_tokens": 707321,
"length_stops": 0,
"errors": 0,
"seconds": 54.266000000000005,
"budget_s": 60.11009713745763,
"last_prompt_tokens": 10574
},
"bfcl:simple_python_366#1": {
"requests": 1,
"prompt_tokens": 469,
"completion_tokens": 168,
"allowance_tokens": 43667,
"length_stops": 0,
"errors": 0,
"seconds": 1.578,
"budget_s": 1.7843597252440238,
"last_prompt_tokens": 469
},
"bfcl:multiple_184#1": {
"requests": 1,
"prompt_tokens": 684,
"completion_tokens": 95,
"allowance_tokens": 43625,
"length_stops": 0,
"errors": 0,
"seconds": 1.057,
"budget_s": 1.5739063885224365,
"last_prompt_tokens": 684
},
"bfcl:parallel_184#1": {
"requests": 1,
"prompt_tokens": 510,
"completion_tokens": 160,
"allowance_tokens": 43659,
"length_stops": 0,
"errors": 0,
"seconds": 1.3,
"budget_s": 1.7848183352972942,
"last_prompt_tokens": 510
},
"bfcl:parallel_multiple_188#1": {
"requests": 1,
"prompt_tokens": 1079,
"completion_tokens": 404,
"allowance_tokens": 43547,
"length_stops": 0,
"errors": 0,
"seconds": 3.059,
"budget_s": 4.225090714320619,
"last_prompt_tokens": 1079
},
"bfcl:multi_turn_base_181#1": {
"requests": 12,
"prompt_tokens": 89174,
"completion_tokens": 4337,
"allowance_tokens": 474185,
"length_stops": 0,
"errors": 0,
"seconds": 42.324,
"budget_s": 47.28689838635577,
"last_prompt_tokens": 9317
},
"bfcl:simple_python_373#1": {
"requests": 1,
"prompt_tokens": 454,
"completion_tokens": 156,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 1.31,
"budget_s": 1.6818594628564507,
"last_prompt_tokens": 454
},
"bfcl:multiple_185#1": {
"requests": 1,
"prompt_tokens": 594,
"completion_tokens": 132,
"allowance_tokens": 43642,
"length_stops": 0,
"errors": 0,
"seconds": 1.173,
"budget_s": 1.7061659991201463,
"last_prompt_tokens": 594
},
"bfcl:parallel_188#1": {
"requests": 1,
"prompt_tokens": 463,
"completion_tokens": 296,
"allowance_tokens": 43668,
"length_stops": 0,
"errors": 0,
"seconds": 2.606,
"budget_s": 2.653784256599032,
"last_prompt_tokens": 463
},
"bfcl:parallel_multiple_189#1": {
"requests": 1,
"prompt_tokens": 1191,
"completion_tokens": 523,
"allowance_tokens": 43525,
"length_stops": 0,
"errors": 0,
"seconds": 4.224,
"budget_s": 5.191980858527715,
"last_prompt_tokens": 1191
},
"bfcl:multi_turn_base_182#1": {
"requests": 4,
"prompt_tokens": 16439,
"completion_tokens": 1109,
"allowance_tokens": 169202,
"length_stops": 0,
"errors": 0,
"seconds": 12.548,
"budget_s": 15.878155559425277,
"last_prompt_tokens": 4565
},
"bfcl:simple_python_380#1": {
"requests": 1,
"prompt_tokens": 535,
"completion_tokens": 259,
"allowance_tokens": 43654,
"length_stops": 0,
"errors": 0,
"seconds": 1.952,
"budget_s": 2.497245074832504,
"last_prompt_tokens": 535
},
"bfcl:multiple_188#1": {
"requests": 1,
"prompt_tokens": 877,
"completion_tokens": 118,
"allowance_tokens": 43587,
"length_stops": 0,
"errors": 0,
"seconds": 1.355,
"budget_s": 1.9919163116807543,
"last_prompt_tokens": 877
},
"bfcl:parallel_194#1": {
"requests": 1,
"prompt_tokens": 460,
"completion_tokens": 283,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 1.691,
"budget_s": 2.560614767789542,
"last_prompt_tokens": 460
},
"bfcl:parallel_multiple_192#1": {
"requests": 1,
"prompt_tokens": 816,
"completion_tokens": 245,
"allowance_tokens": 43599,
"length_stops": 0,
"errors": 0,
"seconds": 1.922,
"budget_s": 2.780297657263243,
"last_prompt_tokens": 816
},
"bfcl:multi_turn_base_190#1": {
"requests": 12,
"prompt_tokens": 77626,
"completion_tokens": 2991,
"allowance_tokens": 486219,
"length_stops": 0,
"errors": 0,
"seconds": 30.993999999999996,
"budget_s": 38.19413760012849,
"last_prompt_tokens": 8133
},
"bfcl:simple_python_382#1": {
"requests": 1,
"prompt_tokens": 485,
"completion_tokens": 272,
"allowance_tokens": 43664,
"length_stops": 0,
"errors": 0,
"seconds": 1.978,
"budget_s": 2.5189247152004732,
"last_prompt_tokens": 485
},
"bfcl:multiple_190#1": {
"requests": 1,
"prompt_tokens": 736,
"completion_tokens": 247,
"allowance_tokens": 43614,
"length_stops": 0,
"errors": 0,
"seconds": 2.297,
"budget_s": 2.6860996664707537,
"last_prompt_tokens": 736
},
"bfcl:parallel_196#1": {
"requests": 1,
"prompt_tokens": 485,
"completion_tokens": 207,
"allowance_tokens": 43664,
"length_stops": 0,
"errors": 0,
"seconds": 1.584,
"budget_s": 2.073310247127036,
"last_prompt_tokens": 485
},
"bfcl:parallel_multiple_193#1": {
"requests": 1,
"prompt_tokens": 1001,
"completion_tokens": 549,
"allowance_tokens": 43562,
"length_stops": 0,
"errors": 0,
"seconds": 3.332,
"budget_s": 5.1139422834195605,
"last_prompt_tokens": 1001
},
"bfcl:multi_turn_base_193#1": {
"requests": 10,
"prompt_tokens": 57131,
"completion_tokens": 1673,
"allowance_tokens": 414570,
"length_stops": 0,
"errors": 0,
"seconds": 20.215,
"budget_s": 26.89370286501461,
"last_prompt_tokens": 6652
},
"bfcl:simple_python_386#1": {
"requests": 1,
"prompt_tokens": 516,
"completion_tokens": 203,
"allowance_tokens": 43658,
"length_stops": 0,
"errors": 0,
"seconds": 1.44,
"budget_s": 2.087702635335482,
"last_prompt_tokens": 516
},
"bfcl:multiple_195#1": {
"requests": 1,
"prompt_tokens": 788,
"completion_tokens": 138,
"allowance_tokens": 43604,
"length_stops": 0,
"errors": 0,
"seconds": 1.389,
"budget_s": 2.0089794649241917,
"last_prompt_tokens": 788
},
"bfcl:parallel_197#1": {
"requests": 1,
"prompt_tokens": 495,
"completion_tokens": 233,
"allowance_tokens": 43662,
"length_stops": 0,
"errors": 0,
"seconds": 1.739,
"budget_s": 2.265044685005755,
"last_prompt_tokens": 495
},
"bfcl:parallel_multiple_194#1": {
"requests": 1,
"prompt_tokens": 1020,
"completion_tokens": 454,
"allowance_tokens": 43559,
"length_stops": 0,
"errors": 0,
"seconds": 3.317,
"budget_s": 4.488288035545982,
"last_prompt_tokens": 1020
},
"bfcl:multi_turn_base_195#1": {
"requests": 12,
"prompt_tokens": 79574,
"completion_tokens": 3052,
"allowance_tokens": 488761,
"length_stops": 0,
"errors": 0,
"seconds": 32.933,
"budget_s": 38.82275258952717,
"last_prompt_tokens": 8159
},
"bfcl:simple_python_396#1": {
"requests": 1,
"prompt_tokens": 442,
"completion_tokens": 103,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 0.861,
"budget_s": 1.3023259004173586,
"last_prompt_tokens": 442
},
"bfcl:multiple_197#1": {
"requests": 1,
"prompt_tokens": 906,
"completion_tokens": 93,
"allowance_tokens": 43581,
"length_stops": 0,
"errors": 0,
"seconds": 1.222,
"budget_s": 1.8596432185356058,
"last_prompt_tokens": 906
},
"bfcl:parallel_199#1": {
"requests": 1,
"prompt_tokens": 425,
"completion_tokens": 318,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 1.901,
"budget_s": 2.7533507425563823,
"last_prompt_tokens": 425
},
"bfcl:parallel_multiple_197#1": {
"requests": 1,
"prompt_tokens": 767,
"completion_tokens": 313,
"allowance_tokens": 43608,
"length_stops": 0,
"errors": 0,
"seconds": 2.177,
"budget_s": 3.180384558758286,
"last_prompt_tokens": 767
},
"bfcl:multi_turn_base_196#1": {
"requests": 14,
"prompt_tokens": 92792,
"completion_tokens": 3538,
"allowance_tokens": 563173,
"length_stops": 0,
"errors": 0,
"seconds": 38.017,
"budget_s": 44.272295841223205,
"last_prompt_tokens": 8447
},
"gpqa_diamond:gpqa_diamond/rec06pnAkLOr2t2mp#1": {
"requests": 1,
"prompt_tokens": 199,
"completion_tokens": 1211,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 7.508,
"budget_s": 8.570564468490131,
"last_prompt_tokens": 199
},
"gpqa_diamond:gpqa_diamond/rec0Arme2jcXQZnAW#1": {
"requests": 1,
"prompt_tokens": 208,
"completion_tokens": 10427,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 79.898,
"budget_s": 71.7639802196868,
"last_prompt_tokens": 208
},
"gpqa_diamond:gpqa_diamond/rec0VuKUjt1SZ7NYv#1": {
"requests": 1,
"prompt_tokens": 219,
"completion_tokens": 11522,
"allowance_tokens": 43716,
"length_stops": 0,
"errors": 0,
"seconds": 87.99,
"budget_s": 79.28570762063822,
"last_prompt_tokens": 219
},
"gpqa_diamond:gpqa_diamond/rec0wZvZgiz320KRs#1": {
"requests": 1,
"prompt_tokens": 229,
"completion_tokens": 609,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 3.223,
"budget_s": 4.48395488535802,
"last_prompt_tokens": 229
},
"gpqa_diamond:gpqa_diamond/rec0yTRmO1o1xCA6H#1": {
"requests": 1,
"prompt_tokens": 205,
"completion_tokens": 5119,
"allowance_tokens": 43719,
"length_stops": 0,
"errors": 0,
"seconds": 37.921,
"budget_s": 35.37037060089501,
"last_prompt_tokens": 205
},
"gpqa_diamond:gpqa_diamond/rec1oj2DveQWl9Rpw#1": {
"requests": 1,
"prompt_tokens": 242,
"completion_tokens": 43712,
"allowance_tokens": 43712,
"length_stops": 1,
"errors": 0,
"seconds": 378.454,
"budget_s": 299.9987273215001,
"last_prompt_tokens": 242
},
"gpqa_diamond:gpqa_diamond/rec1zl5LvaatzGhFt#1": {
"requests": 1,
"prompt_tokens": 436,
"completion_tokens": 1297,
"allowance_tokens": 43674,
"length_stops": 0,
"errors": 0,
"seconds": 7.276,
"budget_s": 9.479827708176739,
"last_prompt_tokens": 436
},
"gpqa_diamond:gpqa_diamond/rec260hNUCEj109Dj#1": {
"requests": 1,
"prompt_tokens": 255,
"completion_tokens": 1065,
"allowance_tokens": 43709,
"length_stops": 0,
"errors": 0,
"seconds": 5.362,
"budget_s": 7.645182260761503,
"last_prompt_tokens": 255
},
"gpqa_diamond:gpqa_diamond/rec2UlKqC6RFHdcro#1": {
"requests": 1,
"prompt_tokens": 241,
"completion_tokens": 921,
"allowance_tokens": 43712,
"length_stops": 0,
"errors": 0,
"seconds": 5.764,
"budget_s": 6.639090712889731,
"last_prompt_tokens": 241
},
"gpqa_diamond:gpqa_diamond/rec2ZTsqazBZ3LTWZ#1": {
"requests": 1,
"prompt_tokens": 521,
"completion_tokens": 21869,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 179.007,
"budget_s": 150.62803258033847,
"last_prompt_tokens": 521
},
"gpqa_diamond:gpqa_diamond/rec2fsnzUuvNtUYK8#1": {
"requests": 1,
"prompt_tokens": 312,
"completion_tokens": 43698,
"allowance_tokens": 43698,
"length_stops": 1,
"errors": 0,
"seconds": 411.839,
"budget_s": 299.99716937522965,
"last_prompt_tokens": 312
},
"gpqa_diamond:gpqa_diamond/rec32C1ZEapBnCC0E#1": {
"requests": 1,
"prompt_tokens": 292,
"completion_tokens": 1576,
"allowance_tokens": 43702,
"length_stops": 0,
"errors": 0,
"seconds": 10.222,
"budget_s": 11.198305547941404,
"last_prompt_tokens": 292
},
"gpqa_diamond:gpqa_diamond/rec47oNPXudlTIk4y#1": {
"requests": 1,
"prompt_tokens": 333,
"completion_tokens": 41096,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 365.563,
"budget_s": 282.18720560425356,
"last_prompt_tokens": 333
},
"gpqa_diamond:gpqa_diamond/rec4JrWy7Il8ho5vk#1": {
"requests": 1,
"prompt_tokens": 203,
"completion_tokens": 1253,
"allowance_tokens": 43719,
"length_stops": 0,
"errors": 0,
"seconds": 9.412,
"budget_s": 8.863895431197319,
"last_prompt_tokens": 203
},
"gpqa_diamond:gpqa_diamond/rec4L69T0Y1AS4AFS#1": {
"requests": 1,
"prompt_tokens": 443,
"completion_tokens": 19114,
"allowance_tokens": 43672,
"length_stops": 0,
"errors": 0,
"seconds": 150.143,
"budget_s": 131.635623266161,
"last_prompt_tokens": 443
},
"gpqa_diamond:gpqa_diamond/rec4UqStf9WUVif1f#1": {
"requests": 1,
"prompt_tokens": 227,
"completion_tokens": 1149,
"allowance_tokens": 43715,
"length_stops": 0,
"errors": 0,
"seconds": 6.225,
"budget_s": 8.183285043838245,
"last_prompt_tokens": 227
},
"gpqa_diamond:gpqa_diamond/rec4r4KWNLrT7g2kR#1": {
"requests": 1,
"prompt_tokens": 393,
"completion_tokens": 43682,
"allowance_tokens": 43682,
"length_stops": 1,
"errors": 0,
"seconds": 393.412,
"budget_s": 299.99673773027126,
"last_prompt_tokens": 393
},
"gpqa_diamond:gpqa_diamond/rec527dNeEtWJrYNl#1": {
"requests": 1,
"prompt_tokens": 199,
"completion_tokens": 10276,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 89.792,
"budget_s": 70.71664374673179,
"last_prompt_tokens": 199
},
"gpqa_diamond:gpqa_diamond/rec5eA17Qr1ucNLUf#1": {
"requests": 1,
"prompt_tokens": 357,
"completion_tokens": 1090,
"allowance_tokens": 43689,
"length_stops": 0,
"errors": 0,
"seconds": 6.835,
"budget_s": 7.954156677413054,
"last_prompt_tokens": 357
},
"gpqa_diamond:gpqa_diamond/rec5rjeLsEq5Fg7Oj#1": {
"requests": 1,
"prompt_tokens": 271,
"completion_tokens": 43706,
"allowance_tokens": 43706,
"length_stops": 1,
"errors": 0,
"seconds": 397.606,
"budget_s": 299.99671076517643,
"last_prompt_tokens": 271
},
"gpqa_diamond:gpqa_diamond/rec6sE2CRtD4drtHg#1": {
"requests": 1,
"prompt_tokens": 959,
"completion_tokens": 12826,
"allowance_tokens": 43571,
"length_stops": 0,
"errors": 0,
"seconds": 110.978,
"budget_s": 89.22357955896292,
"last_prompt_tokens": 959
},
"gpqa_diamond:gpqa_diamond/rec7C06XOB2h298ue#1": {
"requests": 1,
"prompt_tokens": 209,
"completion_tokens": 638,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 3.753,
"budget_s": 4.655790192892097,
"last_prompt_tokens": 209
},
"gpqa_diamond:gpqa_diamond/rec7qmSnbud4FHSqL#1": {
"requests": 1,
"prompt_tokens": 296,
"completion_tokens": 4876,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 31.92,
"budget_s": 33.827204771929495,
"last_prompt_tokens": 296
},
"gpqa_diamond:gpqa_diamond/rec8nshandHARTkrg#1": {
"requests": 1,
"prompt_tokens": 593,
"completion_tokens": 38768,
"allowance_tokens": 43643,
"length_stops": 0,
"errors": 0,
"seconds": 346.806,
"budget_s": 266.57805695690627,
"last_prompt_tokens": 593
},
"gpqa_diamond:gpqa_diamond/rec8y3ZrBOcLgNEkE#1": {
"requests": 1,
"prompt_tokens": 253,
"completion_tokens": 689,
"allowance_tokens": 43710,
"length_stops": 0,
"errors": 0,
"seconds": 4.518,
"budget_s": 5.064776223006828,
"last_prompt_tokens": 253
},
"gpqa_diamond:gpqa_diamond/rec9GugrngvsQR99A#1": {
"requests": 1,
"prompt_tokens": 326,
"completion_tokens": 16286,
"allowance_tokens": 43695,
"length_stops": 0,
"errors": 0,
"seconds": 134.78,
"budget_s": 112.09014888876858,
"last_prompt_tokens": 326
},
"gpqa_diamond:gpqa_diamond/rec9W28HgpEUeUN8k#1": {
"requests": 1,
"prompt_tokens": 295,
"completion_tokens": 23058,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 178.958,
"budget_s": 158.47450603780666,
"last_prompt_tokens": 295
},
"gpqa_diamond:gpqa_diamond/rec9ubQihAh6g9bft#1": {
"requests": 1,
"prompt_tokens": 190,
"completion_tokens": 13126,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 112.737,
"budget_s": 90.24298448436733,
"last_prompt_tokens": 190
},
"gpqa_diamond:gpqa_diamond/recA1i5ZAh0Uzclxp#1": {
"requests": 1,
"prompt_tokens": 321,
"completion_tokens": 19741,
"allowance_tokens": 43696,
"length_stops": 0,
"errors": 0,
"seconds": 172.342,
"budget_s": 135.76952744334739,
"last_prompt_tokens": 321
},
"gpqa_diamond:gpqa_diamond/recAAJoHMW45Lv5je#1": {
"requests": 1,
"prompt_tokens": 277,
"completion_tokens": 12402,
"allowance_tokens": 43705,
"length_stops": 0,
"errors": 0,
"seconds": 92.972,
"budget_s": 85.39687613139864,
"last_prompt_tokens": 277
},
"gpqa_diamond:gpqa_diamond/recAYkd96NNuNl1Ei#1": {
"requests": 1,
"prompt_tokens": 185,
"completion_tokens": 5764,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 44.485,
"budget_s": 39.765259944325045,
"last_prompt_tokens": 185
},
"gpqa_diamond:gpqa_diamond/recBGxVySx1pkrO1i#1": {
"requests": 1,
"prompt_tokens": 413,
"completion_tokens": 43678,
"allowance_tokens": 43678,
"length_stops": 1,
"errors": 0,
"seconds": 405.762,
"budget_s": 299.99629260276544,
"last_prompt_tokens": 413
},
"gpqa_diamond:gpqa_diamond/recBXlqrZUCR897It#1": {
"requests": 1,
"prompt_tokens": 424,
"completion_tokens": 18286,
"allowance_tokens": 43676,
"length_stops": 0,
"errors": 0,
"seconds": 143.979,
"budget_s": 125.93355206739176,
"last_prompt_tokens": 424
},
"gpqa_diamond:gpqa_diamond/recBhnXrUyTJ6WHIR#1": {
"requests": 1,
"prompt_tokens": 275,
"completion_tokens": 25482,
"allowance_tokens": 43705,
"length_stops": 0,
"errors": 0,
"seconds": 241.121,
"budget_s": 175.0655205920466,
"last_prompt_tokens": 275
},
"gpqa_diamond:gpqa_diamond/recBtVK8rBVtIlXDq#1": {
"requests": 1,
"prompt_tokens": 215,
"completion_tokens": 840,
"allowance_tokens": 43717,
"length_stops": 0,
"errors": 0,
"seconds": 5.697,
"budget_s": 6.048716037909923,
"last_prompt_tokens": 215
},
"gpqa_diamond:gpqa_diamond/recCJJOeBGERaHYax#1": {
"requests": 1,
"prompt_tokens": 379,
"completion_tokens": 43685,
"allowance_tokens": 43685,
"length_stops": 1,
"errors": 0,
"seconds": 381.898,
"budget_s": 299.9984204409656,
"last_prompt_tokens": 379
},
"gpqa_diamond:gpqa_diamond/recD8oX1KevFbl7bL#1": {
"requests": 1,
"prompt_tokens": 459,
"completion_tokens": 11125,
"allowance_tokens": 43669,
"length_stops": 0,
"errors": 0,
"seconds": 81.158,
"budget_s": 76.88775917737392,
"last_prompt_tokens": 459
},
"gpqa_diamond:gpqa_diamond/recDDxpS9s8cwkqfq#1": {
"requests": 1,
"prompt_tokens": 152,
"completion_tokens": 4316,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 32.076,
"budget_s": 29.793828169946256,
"last_prompt_tokens": 152
},
"gpqa_diamond:gpqa_diamond/recDj2Y2BbtV02Wv5#1": {
"requests": 1,
"prompt_tokens": 189,
"completion_tokens": 35995,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 341.521,
"budget_s": 247.02251670193985,
"last_prompt_tokens": 189
},
"gpqa_diamond:gpqa_diamond/recDytVnNYZe2HuUU#1": {
"requests": 1,
"prompt_tokens": 209,
"completion_tokens": 10300,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 74.992,
"budget_s": 70.89466697020826,
"last_prompt_tokens": 209
},
"gpqa_diamond:gpqa_diamond/recE2ihVfqEK4R9d0#1": {
"requests": 1,
"prompt_tokens": 207,
"completion_tokens": 1515,
"allowance_tokens": 43719,
"length_stops": 0,
"errors": 0,
"seconds": 8.626,
"budget_s": 10.665459978153065,
"last_prompt_tokens": 207
},
"gpqa_diamond:gpqa_diamond/recEmTBhx2hgw6tPQ#1": {
"requests": 1,
"prompt_tokens": 367,
"completion_tokens": 43687,
"allowance_tokens": 43687,
"length_stops": 1,
"errors": 0,
"seconds": 362.833,
"budget_s": 299.9959452745886,
"last_prompt_tokens": 367
},
"gpqa_diamond:gpqa_diamond/recFaL6j8UMhutXrc#1": {
"requests": 1,
"prompt_tokens": 521,
"completion_tokens": 22459,
"allowance_tokens": 43657,
"length_stops": 0,
"errors": 0,
"seconds": 178.352,
"budget_s": 154.67284082900505,
"last_prompt_tokens": 521
},
"gpqa_diamond:gpqa_diamond/recG1ljJQcVy6CbSl#1": {
"requests": 1,
"prompt_tokens": 370,
"completion_tokens": 4894,
"allowance_tokens": 43687,
"length_stops": 0,
"errors": 0,
"seconds": 33.945,
"budget_s": 34.05042171635497,
"last_prompt_tokens": 370
},
"gpqa_diamond:gpqa_diamond/recGFKDUd8qgz81Zl#1": {
"requests": 1,
"prompt_tokens": 210,
"completion_tokens": 1510,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 10.91,
"budget_s": 10.635228537342218,
"last_prompt_tokens": 210
},
"gpqa_diamond:gpqa_diamond/recGFNRVl1qBZGwyU#1": {
"requests": 1,
"prompt_tokens": 214,
"completion_tokens": 43717,
"allowance_tokens": 43717,
"length_stops": 1,
"errors": 0,
"seconds": 391.247,
"budget_s": 299.9952371356876,
"last_prompt_tokens": 214
},
"gpqa_diamond:gpqa_diamond/recGee5m84dg5FZkc#1": {
"requests": 1,
"prompt_tokens": 286,
"completion_tokens": 40936,
"allowance_tokens": 43703,
"length_stops": 0,
"errors": 0,
"seconds": 374.878,
"budget_s": 281.02691179402086,
"last_prompt_tokens": 286
},
"gpqa_diamond:gpqa_diamond/recHVUd2DkoKfedJZ#1": {
"requests": 1,
"prompt_tokens": 350,
"completion_tokens": 14551,
"allowance_tokens": 43690,
"length_stops": 0,
"errors": 0,
"seconds": 116.837,
"budget_s": 100.2280431563668,
"last_prompt_tokens": 350
},
"gpqa_diamond:gpqa_diamond/recI1ls9OXdxatHQn#1": {
"requests": 1,
"prompt_tokens": 297,
"completion_tokens": 1034,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 5.951,
"budget_s": 7.489310770253724,
"last_prompt_tokens": 297
},
"gpqa_diamond:gpqa_diamond/recIDiDKKrN61Auyr#1": {
"requests": 1,
"prompt_tokens": 229,
"completion_tokens": 784,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 5.515,
"budget_s": 5.683686145555735,
"last_prompt_tokens": 229
},
"gpqa_diamond:gpqa_diamond/recIIUynGGpsGEYuo#1": {
"requests": 1,
"prompt_tokens": 201,
"completion_tokens": 1119,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 8.016,
"budget_s": 7.942546336116057,
"last_prompt_tokens": 201
},
"gpqa_diamond:gpqa_diamond/recIMcQfaQNa6vzsT#1": {
"requests": 1,
"prompt_tokens": 286,
"completion_tokens": 2611,
"allowance_tokens": 43703,
"length_stops": 0,
"errors": 0,
"seconds": 17.051,
"budget_s": 18.285765810721145,
"last_prompt_tokens": 286
},
"gpqa_diamond:gpqa_diamond/recINGR1z01Fh1Z3A#1": {
"requests": 1,
"prompt_tokens": 299,
"completion_tokens": 3678,
"allowance_tokens": 43700,
"length_stops": 0,
"errors": 0,
"seconds": 26.401,
"budget_s": 25.618233940170793,
"last_prompt_tokens": 299
},
"gpqa_diamond:gpqa_diamond/recINSFEYLCyyd08m#1": {
"requests": 1,
"prompt_tokens": 318,
"completion_tokens": 10077,
"allowance_tokens": 43697,
"length_stops": 0,
"errors": 0,
"seconds": 77.238,
"budget_s": 69.51289285643415,
"last_prompt_tokens": 318
},
"gpqa_diamond:gpqa_diamond/recIOlKBsOeEcgkA1#1": {
"requests": 1,
"prompt_tokens": 362,
"completion_tokens": 7138,
"allowance_tokens": 43688,
"length_stops": 0,
"errors": 0,
"seconds": 52.251,
"budget_s": 49.42361335517077,
"last_prompt_tokens": 362
},
"gpqa_diamond:gpqa_diamond/recIj8lR4tuDgrHou#1": {
"requests": 1,
"prompt_tokens": 232,
"completion_tokens": 6734,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 46.533,
"budget_s": 46.47859558747287,
"last_prompt_tokens": 232
},
"gpqa_diamond:gpqa_diamond/recIlghoOw5VbY4Zh#1": {
"requests": 1,
"prompt_tokens": 150,
"completion_tokens": 18972,
"allowance_tokens": 43730,
"length_stops": 0,
"errors": 0,
"seconds": 168.739,
"budget_s": 130.2669095795748,
"last_prompt_tokens": 150
},
"gpqa_diamond:gpqa_diamond/recJJcOHhFeSaRpl4#1": {
"requests": 1,
"prompt_tokens": 269,
"completion_tokens": 2044,
"allowance_tokens": 43706,
"length_stops": 0,
"errors": 0,
"seconds": 15.132,
"budget_s": 14.375705821576663,
"last_prompt_tokens": 269
},
"gpqa_diamond:gpqa_diamond/recJZ3QEfRKjYw9a7#1": {
"requests": 1,
"prompt_tokens": 208,
"completion_tokens": 34563,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 314.108,
"budget_s": 237.23091562615576,
"last_prompt_tokens": 208
},
"gpqa_diamond:gpqa_diamond/recJpyGtGIsxulevT#1": {
"requests": 1,
"prompt_tokens": 203,
"completion_tokens": 3158,
"allowance_tokens": 43719,
"length_stops": 0,
"errors": 0,
"seconds": 20.887,
"budget_s": 21.923827149349595,
"last_prompt_tokens": 203
},
"gpqa_diamond:gpqa_diamond/recK9F5aqdaybl8bb#1": {
"requests": 1,
"prompt_tokens": 477,
"completion_tokens": 43665,
"allowance_tokens": 43665,
"length_stops": 1,
"errors": 0,
"seconds": 394.754,
"budget_s": 299.99349707330657,
"last_prompt_tokens": 477
},
"gpqa_diamond:gpqa_diamond/recKcjTwONILZqHAX#1": {
"requests": 1,
"prompt_tokens": 253,
"completion_tokens": 895,
"allowance_tokens": 43710,
"length_stops": 0,
"errors": 0,
"seconds": 6.175,
"budget_s": 6.477031306439568,
"last_prompt_tokens": 253
},
"gpqa_diamond:gpqa_diamond/recKm6LNWykGapmCr#1": {
"requests": 1,
"prompt_tokens": 223,
"completion_tokens": 4283,
"allowance_tokens": 43715,
"length_stops": 0,
"errors": 0,
"seconds": 33.302,
"budget_s": 29.663362551919313,
"last_prompt_tokens": 223
},
"gpqa_diamond:gpqa_diamond/recKv4hFyNpViUXnL#1": {
"requests": 1,
"prompt_tokens": 304,
"completion_tokens": 8048,
"allowance_tokens": 43699,
"length_stops": 0,
"errors": 0,
"seconds": 57.078,
"budget_s": 55.583981734432705,
"last_prompt_tokens": 304
},
"gpqa_diamond:gpqa_diamond/recL9MFV5zmdlle5T#1": {
"requests": 1,
"prompt_tokens": 281,
"completion_tokens": 7087,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 56.068,
"budget_s": 48.964719317653476,
"last_prompt_tokens": 281
},
"gpqa_diamond:gpqa_diamond/recLAgwx9vbgB5EHk#1": {
"requests": 1,
"prompt_tokens": 237,
"completion_tokens": 14506,
"allowance_tokens": 43713,
"length_stops": 0,
"errors": 0,
"seconds": 113.061,
"budget_s": 99.76711907997837,
"last_prompt_tokens": 237
},
"gpqa_diamond:gpqa_diamond/recLB0EkQ54bYVhnd#1": {
"requests": 1,
"prompt_tokens": 262,
"completion_tokens": 6992,
"allowance_tokens": 43708,
"length_stops": 0,
"errors": 0,
"seconds": 47.741,
"budget_s": 48.287808197312394,
"last_prompt_tokens": 262
},
"gpqa_diamond:gpqa_diamond/recLSzwBUS3olCjhl#1": {
"requests": 1,
"prompt_tokens": 252,
"completion_tokens": 2081,
"allowance_tokens": 43710,
"length_stops": 0,
"errors": 0,
"seconds": 14.899,
"budget_s": 14.60643258191458,
"last_prompt_tokens": 252
},
"gpqa_diamond:gpqa_diamond/recLrRirj7iXoB0rU#1": {
"requests": 1,
"prompt_tokens": 314,
"completion_tokens": 30925,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 282.066,
"budget_s": 212.43319632532857,
"last_prompt_tokens": 314
},
"gpqa_diamond:gpqa_diamond/recMicVBcqy1xM1jq#1": {
"requests": 1,
"prompt_tokens": 271,
"completion_tokens": 8114,
"allowance_tokens": 43706,
"length_stops": 0,
"errors": 0,
"seconds": 58.373,
"budget_s": 55.991939262564436,
"last_prompt_tokens": 271
},
"gpqa_diamond:gpqa_diamond/recN4DY9Q5V03glmQ#1": {
"requests": 1,
"prompt_tokens": 241,
"completion_tokens": 6125,
"allowance_tokens": 43712,
"length_stops": 0,
"errors": 0,
"seconds": 40.414,
"budget_s": 42.31567058756923,
"last_prompt_tokens": 241
},
"gpqa_diamond:gpqa_diamond/recNAiPUKOulQbKVP#1": {
"requests": 1,
"prompt_tokens": 138,
"completion_tokens": 345,
"allowance_tokens": 43732,
"length_stops": 0,
"errors": 0,
"seconds": 2.794,
"budget_s": 2.5513278633507244,
"last_prompt_tokens": 138
},
"gpqa_diamond:gpqa_diamond/recNFJjE5PPTqVJGv#1": {
"requests": 1,
"prompt_tokens": 188,
"completion_tokens": 1083,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 6.282,
"budget_s": 7.6782092310312375,
"last_prompt_tokens": 188
},
"gpqa_diamond:gpqa_diamond/recNu3MXkvWUzHZr9#1": {
"requests": 1,
"prompt_tokens": 256,
"completion_tokens": 22480,
"allowance_tokens": 43709,
"length_stops": 0,
"errors": 0,
"seconds": 176.239,
"budget_s": 154.4593593380212,
"last_prompt_tokens": 256
},
"gpqa_diamond:gpqa_diamond/recNuT2oSnO86bxOx#1": {
"requests": 1,
"prompt_tokens": 280,
"completion_tokens": 6054,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 48.604,
"budget_s": 41.88152821382145,
"last_prompt_tokens": 280
},
"gpqa_diamond:gpqa_diamond/recO3hvCWRGiG0odN#1": {
"requests": 1,
"prompt_tokens": 304,
"completion_tokens": 21539,
"allowance_tokens": 43699,
"length_stops": 0,
"errors": 0,
"seconds": 176.705,
"budget_s": 148.07297848487488,
"last_prompt_tokens": 304
},
"gpqa_diamond:gpqa_diamond/recOYsaYs6RmtlTDy#1": {
"requests": 1,
"prompt_tokens": 298,
"completion_tokens": 7430,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 53.053,
"budget_s": 51.339123293744876,
"last_prompt_tokens": 298
},
"gpqa_diamond:gpqa_diamond/recOkA2zsy4GSMD9R#1": {
"requests": 1,
"prompt_tokens": 292,
"completion_tokens": 23057,
"allowance_tokens": 43702,
"length_stops": 0,
"errors": 0,
"seconds": 193.734,
"budget_s": 158.4636038354107,
"last_prompt_tokens": 292
},
"gpqa_diamond:gpqa_diamond/recOvqPKUtyy9ISA1#1": {
"requests": 1,
"prompt_tokens": 340,
"completion_tokens": 33695,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 298.357,
"budget_s": 231.4582987641464,
"last_prompt_tokens": 340
},
"gpqa_diamond:gpqa_diamond/recPIzpnuYpB4yvmp#1": {
"requests": 1,
"prompt_tokens": 329,
"completion_tokens": 3456,
"allowance_tokens": 43695,
"length_stops": 0,
"errors": 0,
"seconds": 22.342,
"budget_s": 24.136755093468008,
"last_prompt_tokens": 329
},
"gpqa_diamond:gpqa_diamond/recPL4ZPpVYxgMu57#1": {
"requests": 1,
"prompt_tokens": 175,
"completion_tokens": 21744,
"allowance_tokens": 43725,
"length_stops": 0,
"errors": 0,
"seconds": 197.925,
"budget_s": 149.30437436772996,
"last_prompt_tokens": 175
},
"gpqa_diamond:gpqa_diamond/recPSTGXK3P39yNYT#1": {
"requests": 1,
"prompt_tokens": 293,
"completion_tokens": 462,
"allowance_tokens": 43702,
"length_stops": 0,
"errors": 0,
"seconds": 2.982,
"budget_s": 3.5625079909477377,
"last_prompt_tokens": 293
},
"gpqa_diamond:gpqa_diamond/recPzW1WqRnPs57D6#1": {
"requests": 1,
"prompt_tokens": 212,
"completion_tokens": 2809,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 22.647,
"budget_s": 19.5433600217397,
"last_prompt_tokens": 212
},
"gpqa_diamond:gpqa_diamond/recQ8oxSY2aCwFRS8#1": {
"requests": 1,
"prompt_tokens": 253,
"completion_tokens": 10491,
"allowance_tokens": 43710,
"length_stops": 0,
"errors": 0,
"seconds": 81.751,
"budget_s": 72.26343800848116,
"last_prompt_tokens": 253
},
"gpqa_diamond:gpqa_diamond/recQiWOxhkXRz9NVE#1": {
"requests": 1,
"prompt_tokens": 221,
"completion_tokens": 43716,
"allowance_tokens": 43716,
"length_stops": 1,
"errors": 0,
"seconds": 416.694,
"budget_s": 299.997823583941,
"last_prompt_tokens": 221
},
"gpqa_diamond:gpqa_diamond/recRTiyaRymerDJ4y#1": {
"requests": 1,
"prompt_tokens": 223,
"completion_tokens": 601,
"allowance_tokens": 43715,
"length_stops": 0,
"errors": 0,
"seconds": 3.643,
"budget_s": 4.421016837359375,
"last_prompt_tokens": 223
},
"gpqa_diamond:gpqa_diamond/recRZjaElf8ft7xTq#1": {
"requests": 1,
"prompt_tokens": 277,
"completion_tokens": 5019,
"allowance_tokens": 43705,
"length_stops": 0,
"errors": 0,
"seconds": 36.03,
"budget_s": 34.7819281654573,
"last_prompt_tokens": 277
},
"gpqa_diamond:gpqa_diamond/recReg13iV2HwJTaA#1": {
"requests": 1,
"prompt_tokens": 294,
"completion_tokens": 432,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 3.376,
"budget_s": 3.358188639978778,
"last_prompt_tokens": 294
},
"gpqa_diamond:gpqa_diamond/recRgabRzMaEoBRcM#1": {
"requests": 1,
"prompt_tokens": 250,
"completion_tokens": 43710,
"allowance_tokens": 43710,
"length_stops": 1,
"errors": 0,
"seconds": 416.684,
"budget_s": 299.99580702761733,
"last_prompt_tokens": 250
},
"gpqa_diamond:gpqa_diamond/recRhwQwHijW0gCLo#1": {
"requests": 1,
"prompt_tokens": 363,
"completion_tokens": 4141,
"allowance_tokens": 43688,
"length_stops": 0,
"errors": 0,
"seconds": 25.617,
"budget_s": 28.87870743844969,
"last_prompt_tokens": 363
},
"gpqa_diamond:gpqa_diamond/recS48OsU6kVadBPW#1": {
"requests": 1,
"prompt_tokens": 238,
"completion_tokens": 2408,
"allowance_tokens": 43712,
"length_stops": 0,
"errors": 0,
"seconds": 14.363,
"budget_s": 16.829332025774946,
"last_prompt_tokens": 238
},
"gpqa_diamond:gpqa_diamond/recSBcGLPatKb3Ygu#1": {
"requests": 1,
"prompt_tokens": 224,
"completion_tokens": 727,
"allowance_tokens": 43715,
"length_stops": 0,
"errors": 0,
"seconds": 3.903,
"budget_s": 5.286172209766665,
"last_prompt_tokens": 224
},
"gpqa_diamond:gpqa_diamond/recTs7qzfJs6kfLUK#1": {
"requests": 1,
"prompt_tokens": 688,
"completion_tokens": 40715,
"allowance_tokens": 43624,
"length_stops": 0,
"errors": 0,
"seconds": 308.159,
"budget_s": 280.0540663586748,
"last_prompt_tokens": 688
},
"gpqa_diamond:gpqa_diamond/recUBgVlkKzcRPDdK#1": {
"requests": 1,
"prompt_tokens": 273,
"completion_tokens": 10136,
"allowance_tokens": 43706,
"length_stops": 0,
"errors": 0,
"seconds": 80.819,
"budget_s": 69.85667475337877,
"last_prompt_tokens": 273
},
"gpqa_diamond:gpqa_diamond/recUOePh79cp4T2Bg#1": {
"requests": 1,
"prompt_tokens": 615,
"completion_tokens": 43638,
"allowance_tokens": 43638,
"length_stops": 1,
"errors": 0,
"seconds": 400.511,
"budget_s": 299.99453905783696,
"last_prompt_tokens": 615
},
"gpqa_diamond:gpqa_diamond/recUc29lMDBEvurYo#1": {
"requests": 1,
"prompt_tokens": 229,
"completion_tokens": 15614,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 111.718,
"budget_s": 107.35234093831072,
"last_prompt_tokens": 229
},
"gpqa_diamond:gpqa_diamond/recV1nqYQvpII94oC#1": {
"requests": 1,
"prompt_tokens": 571,
"completion_tokens": 1278,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 9.394,
"budget_s": 9.531667955121412,
"last_prompt_tokens": 571
},
"gpqa_diamond:gpqa_diamond/recVE8cUNHpHZIAvL#1": {
"requests": 1,
"prompt_tokens": 335,
"completion_tokens": 22493,
"allowance_tokens": 43693,
"length_stops": 0,
"errors": 0,
"seconds": 184.966,
"budget_s": 154.65504257176568,
"last_prompt_tokens": 335
},
"gpqa_diamond:gpqa_diamond/recVEXvhYxAhELVqB#1": {
"requests": 1,
"prompt_tokens": 441,
"completion_tokens": 12299,
"allowance_tokens": 43673,
"length_stops": 0,
"errors": 0,
"seconds": 95.295,
"budget_s": 84.9119624603315,
"last_prompt_tokens": 441
},
"gpqa_diamond:gpqa_diamond/recVvpD8miVjmmyfe#1": {
"requests": 1,
"prompt_tokens": 171,
"completion_tokens": 43726,
"allowance_tokens": 43726,
"length_stops": 1,
"errors": 0,
"seconds": 376.123,
"budget_s": 299.99893640270557,
"last_prompt_tokens": 171
},
"gpqa_diamond:gpqa_diamond/recWPMm91mGDLXONm#1": {
"requests": 1,
"prompt_tokens": 298,
"completion_tokens": 9186,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 70.051,
"budget_s": 63.37756953892881,
"last_prompt_tokens": 298
},
"gpqa_diamond:gpqa_diamond/recWXwn9v4IG9ZrM6#1": {
"requests": 1,
"prompt_tokens": 330,
"completion_tokens": 528,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 3.935,
"budget_s": 4.064886073624876,
"last_prompt_tokens": 330
},
"gpqa_diamond:gpqa_diamond/recWxGU8Q4YReJ1tb#1": {
"requests": 1,
"prompt_tokens": 847,
"completion_tokens": 43593,
"allowance_tokens": 43593,
"length_stops": 1,
"errors": 0,
"seconds": 393.461,
"budget_s": 299.9989734288509,
"last_prompt_tokens": 847
},
"gpqa_diamond:gpqa_diamond/recWzUUYBN0NuXO2k#1": {
"requests": 1,
"prompt_tokens": 244,
"completion_tokens": 2093,
"allowance_tokens": 43711,
"length_stops": 0,
"errors": 0,
"seconds": 11.149,
"budget_s": 14.677908947808662,
"last_prompt_tokens": 244
},
"gpqa_diamond:gpqa_diamond/recXsYa3i2UhGF5fe#1": {
"requests": 1,
"prompt_tokens": 163,
"completion_tokens": 5625,
"allowance_tokens": 43727,
"length_stops": 0,
"errors": 0,
"seconds": 44.472,
"budget_s": 38.782655511939446,
"last_prompt_tokens": 163
},
"gpqa_diamond:gpqa_diamond/recXsuOHRBLcyenF2#1": {
"requests": 1,
"prompt_tokens": 178,
"completion_tokens": 1293,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 10.023,
"budget_s": 9.104398092619151,
"last_prompt_tokens": 178
},
"gpqa_diamond:gpqa_diamond/recXvQ6gWAmyakrpD#1": {
"requests": 1,
"prompt_tokens": 339,
"completion_tokens": 15087,
"allowance_tokens": 43693,
"length_stops": 0,
"errors": 0,
"seconds": 113.729,
"budget_s": 103.8878111004581,
"last_prompt_tokens": 339
},
"gpqa_diamond:gpqa_diamond/recYA3LPsCvF1fTMI#1": {
"requests": 1,
"prompt_tokens": 386,
"completion_tokens": 39014,
"allowance_tokens": 43683,
"length_stops": 0,
"errors": 0,
"seconds": 341.37,
"budget_s": 267.9853212599428,
"last_prompt_tokens": 386
},
"gpqa_diamond:gpqa_diamond/recYCMJWH7IpcdqwE#1": {
"requests": 1,
"prompt_tokens": 488,
"completion_tokens": 15917,
"allowance_tokens": 43663,
"length_stops": 0,
"errors": 0,
"seconds": 126.4,
"budget_s": 109.77894597207106,
"last_prompt_tokens": 488
},
"gpqa_diamond:gpqa_diamond/recYOzCsevNz61Lyn#1": {
"requests": 1,
"prompt_tokens": 363,
"completion_tokens": 17361,
"allowance_tokens": 43688,
"length_stops": 0,
"errors": 0,
"seconds": 138.729,
"budget_s": 119.5098346373857,
"last_prompt_tokens": 363
},
"gpqa_diamond:gpqa_diamond/recYt8xx80OTyDsL0#1": {
"requests": 1,
"prompt_tokens": 219,
"completion_tokens": 576,
"allowance_tokens": 43716,
"length_stops": 0,
"errors": 0,
"seconds": 4.493,
"budget_s": 4.244231197071392,
"last_prompt_tokens": 219
},
"gpqa_diamond:gpqa_diamond/recZ13cwgDQf9jRd9#1": {
"requests": 1,
"prompt_tokens": 309,
"completion_tokens": 43699,
"allowance_tokens": 43699,
"length_stops": 1,
"errors": 0,
"seconds": 396.449,
"budget_s": 299.999978387236,
"last_prompt_tokens": 309
},
"gpqa_diamond:gpqa_diamond/recZSGUkn56v9kEp1#1": {
"requests": 1,
"prompt_tokens": 257,
"completion_tokens": 20852,
"allowance_tokens": 43709,
"length_stops": 0,
"errors": 0,
"seconds": 174.106,
"budget_s": 143.29977967964678,
"last_prompt_tokens": 257
},
"gpqa_diamond:gpqa_diamond/recZWeueB7lSPR6wN#1": {
"requests": 1,
"prompt_tokens": 285,
"completion_tokens": 43703,
"allowance_tokens": 43703,
"length_stops": 1,
"errors": 0,
"seconds": 422.375,
"budget_s": 299.99502805448213,
"last_prompt_tokens": 285
},
"gpqa_diamond:gpqa_diamond/recZbxrocrxh9YENH#1": {
"requests": 1,
"prompt_tokens": 256,
"completion_tokens": 4367,
"allowance_tokens": 43709,
"length_stops": 0,
"errors": 0,
"seconds": 29.243,
"budget_s": 30.28374610395705,
"last_prompt_tokens": 256
},
"gpqa_diamond:gpqa_diamond/recZdZxsN0AxDx0pB#1": {
"requests": 1,
"prompt_tokens": 453,
"completion_tokens": 13855,
"allowance_tokens": 43670,
"length_stops": 0,
"errors": 0,
"seconds": 105.893,
"budget_s": 95.5954736460687,
"last_prompt_tokens": 453
},
"gpqa_diamond:gpqa_diamond/recZt4x514UQNnsgy#1": {
"requests": 1,
"prompt_tokens": 247,
"completion_tokens": 43711,
"allowance_tokens": 43711,
"length_stops": 1,
"errors": 0,
"seconds": 384.336,
"budget_s": 299.9986160396236,
"last_prompt_tokens": 247
},
"gpqa_diamond:gpqa_diamond/reca44yABeO2fx7UB#1": {
"requests": 1,
"prompt_tokens": 308,
"completion_tokens": 43699,
"allowance_tokens": 43699,
"length_stops": 1,
"errors": 0,
"seconds": 406.841,
"budget_s": 299.9986295221711,
"last_prompt_tokens": 308
},
"gpqa_diamond:gpqa_diamond/recaXdGn3FAIkxLGM#1": {
"requests": 1,
"prompt_tokens": 202,
"completion_tokens": 12573,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 88.841,
"budget_s": 86.46802008292175,
"last_prompt_tokens": 202
},
"gpqa_diamond:gpqa_diamond/recafnH3RRnMBXEb1#1": {
"requests": 1,
"prompt_tokens": 321,
"completion_tokens": 898,
"allowance_tokens": 43696,
"length_stops": 0,
"errors": 0,
"seconds": 6.521,
"budget_s": 6.589320952458494,
"last_prompt_tokens": 321
},
"gpqa_diamond:gpqa_diamond/recakFKZioXUuldcd#1": {
"requests": 1,
"prompt_tokens": 229,
"completion_tokens": 18902,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 154.731,
"budget_s": 129.8935774156255,
"last_prompt_tokens": 229
},
"gpqa_diamond:gpqa_diamond/recatj4YXzbOaq3Ar#1": {
"requests": 1,
"prompt_tokens": 235,
"completion_tokens": 264,
"allowance_tokens": 43713,
"length_stops": 0,
"errors": 0,
"seconds": 1.986,
"budget_s": 2.1268635913578438,
"last_prompt_tokens": 235
},
"gpqa_diamond:gpqa_diamond/recb2M22zaD3tL6Qc#1": {
"requests": 1,
"prompt_tokens": 410,
"completion_tokens": 9707,
"allowance_tokens": 43679,
"length_stops": 0,
"errors": 0,
"seconds": 67.483,
"budget_s": 67.10041377799008,
"last_prompt_tokens": 410
},
"gpqa_diamond:gpqa_diamond/recb4cGsC6BJUCU3V#1": {
"requests": 1,
"prompt_tokens": 281,
"completion_tokens": 23122,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 192.208,
"budget_s": 158.89438078776988,
"last_prompt_tokens": 281
},
"gpqa_diamond:gpqa_diamond/recb80OwMgNnceA9t#1": {
"requests": 1,
"prompt_tokens": 253,
"completion_tokens": 29467,
"allowance_tokens": 43710,
"length_stops": 0,
"errors": 0,
"seconds": 252.229,
"budget_s": 202.3554402571203,
"last_prompt_tokens": 253
},
"gpqa_diamond:gpqa_diamond/reccOKzFNmyqeJ6ry#1": {
"requests": 1,
"prompt_tokens": 273,
"completion_tokens": 15965,
"allowance_tokens": 43706,
"length_stops": 0,
"errors": 0,
"seconds": 133.393,
"budget_s": 109.81800912876439,
"last_prompt_tokens": 273
},
"gpqa_diamond:gpqa_diamond/reccVBrYdwsB84fGy#1": {
"requests": 1,
"prompt_tokens": 390,
"completion_tokens": 18784,
"allowance_tokens": 43683,
"length_stops": 0,
"errors": 0,
"seconds": 165.086,
"budget_s": 129.30178304134662,
"last_prompt_tokens": 390
},
"gpqa_diamond:gpqa_diamond/reccVFW11Elovnf8T#1": {
"requests": 1,
"prompt_tokens": 490,
"completion_tokens": 32796,
"allowance_tokens": 43663,
"length_stops": 0,
"errors": 0,
"seconds": 289.486,
"budget_s": 225.49743765007088,
"last_prompt_tokens": 490
},
"gpqa_diamond:gpqa_diamond/recclFbsjbaiVVnnV#1": {
"requests": 1,
"prompt_tokens": 396,
"completion_tokens": 24321,
"allowance_tokens": 43681,
"length_stops": 0,
"errors": 0,
"seconds": 212.546,
"budget_s": 167.26937330439196,
"last_prompt_tokens": 396
},
"gpqa_diamond:gpqa_diamond/recdya6FuYraBU5Rh#1": {
"requests": 1,
"prompt_tokens": 272,
"completion_tokens": 1739,
"allowance_tokens": 43706,
"length_stops": 0,
"errors": 0,
"seconds": 12.012,
"budget_s": 12.288792220426874,
"last_prompt_tokens": 272
},
"gpqa_diamond:gpqa_diamond/receYQxnUBvxPcvbQ#1": {
"requests": 1,
"prompt_tokens": 292,
"completion_tokens": 3063,
"allowance_tokens": 43702,
"length_stops": 0,
"errors": 0,
"seconds": 23.342,
"budget_s": 21.392593456021423,
"last_prompt_tokens": 292
},
"gpqa_diamond:gpqa_diamond/receo3UUzRvWCqyfA#1": {
"requests": 1,
"prompt_tokens": 349,
"completion_tokens": 12353,
"allowance_tokens": 43691,
"length_stops": 0,
"errors": 0,
"seconds": 95.968,
"budget_s": 85.15806966321854,
"last_prompt_tokens": 349
},
"gpqa_diamond:gpqa_diamond/recf6ayQmL1SxKbvW#1": {
"requests": 1,
"prompt_tokens": 335,
"completion_tokens": 521,
"allowance_tokens": 43693,
"length_stops": 0,
"errors": 0,
"seconds": 3.942,
"budget_s": 4.02364114854164,
"last_prompt_tokens": 335
},
"gpqa_diamond:gpqa_diamond/recfTlTMjZBuOducT#1": {
"requests": 1,
"prompt_tokens": 196,
"completion_tokens": 4514,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 30.617,
"budget_s": 31.21058845862707,
"last_prompt_tokens": 196
},
"gpqa_diamond:gpqa_diamond/recgC4GJ8wUemlUQD#1": {
"requests": 1,
"prompt_tokens": 138,
"completion_tokens": 825,
"allowance_tokens": 43732,
"length_stops": 0,
"errors": 0,
"seconds": 6.074,
"budget_s": 5.84201931989303,
"last_prompt_tokens": 138
},
"gpqa_diamond:gpqa_diamond/recgI6tUQ7RLJRWGx#1": {
"requests": 1,
"prompt_tokens": 244,
"completion_tokens": 1648,
"allowance_tokens": 43711,
"length_stops": 0,
"errors": 0,
"seconds": 11.936,
"budget_s": 11.6271637433059,
"last_prompt_tokens": 244
},
"gpqa_diamond:gpqa_diamond/recgM7o1tcc7tP778#1": {
"requests": 1,
"prompt_tokens": 332,
"completion_tokens": 21288,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 178.101,
"budget_s": 146.38998929920947,
"last_prompt_tokens": 332
},
"gpqa_diamond:gpqa_diamond/recgXxEgllSGEpELP#1": {
"requests": 1,
"prompt_tokens": 572,
"completion_tokens": 11861,
"allowance_tokens": 43647,
"length_stops": 0,
"errors": 0,
"seconds": 90.296,
"budget_s": 82.08590782974305,
"last_prompt_tokens": 572
},
"gpqa_diamond:gpqa_diamond/rechKl68Uc6H7vU0N#1": {
"requests": 1,
"prompt_tokens": 391,
"completion_tokens": 21516,
"allowance_tokens": 43682,
"length_stops": 0,
"errors": 0,
"seconds": 174.005,
"budget_s": 148.03265077989818,
"last_prompt_tokens": 391
},
"gpqa_diamond:gpqa_diamond/rechgQucGlrnt8KRV#1": {
"requests": 1,
"prompt_tokens": 301,
"completion_tokens": 1937,
"allowance_tokens": 43700,
"length_stops": 0,
"errors": 0,
"seconds": 10.961,
"budget_s": 13.685319533133672,
"last_prompt_tokens": 301
},
"gpqa_diamond:gpqa_diamond/rechtUKxC6G67H7Pr#1": {
"requests": 1,
"prompt_tokens": 295,
"completion_tokens": 2632,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 18.367,
"budget_s": 18.441873347529278,
"last_prompt_tokens": 295
},
"gpqa_diamond:gpqa_diamond/recihePFulRgNKsIn#1": {
"requests": 1,
"prompt_tokens": 237,
"completion_tokens": 892,
"allowance_tokens": 43713,
"length_stops": 0,
"errors": 0,
"seconds": 5.903,
"budget_s": 6.434882643797229,
"last_prompt_tokens": 237
},
"gpqa_diamond:gpqa_diamond/reciuppdQde4FGX1z#1": {
"requests": 1,
"prompt_tokens": 236,
"completion_tokens": 2413,
"allowance_tokens": 43713,
"length_stops": 0,
"errors": 0,
"seconds": 16.777,
"budget_s": 16.860912331650724,
"last_prompt_tokens": 236
},
"gpqa_diamond:gpqa_diamond/recixxJmdux0d8LZQ#1": {
"requests": 1,
"prompt_tokens": 346,
"completion_tokens": 21917,
"allowance_tokens": 43691,
"length_stops": 0,
"errors": 0,
"seconds": 187.256,
"budget_s": 150.7210503396292,
"last_prompt_tokens": 346
},
"gpqa_diamond:gpqa_diamond/recjJ54TXc04enRkZ#1": {
"requests": 1,
"prompt_tokens": 319,
"completion_tokens": 43697,
"allowance_tokens": 43697,
"length_stops": 1,
"errors": 0,
"seconds": 392.371,
"budget_s": 299.99975582348304,
"last_prompt_tokens": 319
},
"gpqa_diamond:gpqa_diamond/recjgMJaMxz4ESDF2#1": {
"requests": 1,
"prompt_tokens": 277,
"completion_tokens": 8136,
"allowance_tokens": 43705,
"length_stops": 0,
"errors": 0,
"seconds": 67.63,
"budget_s": 56.1508558113789,
"last_prompt_tokens": 277
},
"gpqa_diamond:gpqa_diamond/reck1zKeCssmN82Ga#1": {
"requests": 1,
"prompt_tokens": 221,
"completion_tokens": 4030,
"allowance_tokens": 43716,
"length_stops": 0,
"errors": 0,
"seconds": 31.778,
"budget_s": 27.9261961999036,
"last_prompt_tokens": 221
},
"gpqa_diamond:gpqa_diamond/reck4G4xxv3YnpbtQ#1": {
"requests": 1,
"prompt_tokens": 367,
"completion_tokens": 40647,
"allowance_tokens": 43687,
"length_stops": 0,
"errors": 0,
"seconds": 367.71,
"budget_s": 279.15489938315403,
"last_prompt_tokens": 367
},
"gpqa_diamond:gpqa_diamond/reckEnrOPFT9Ru7tW#1": {
"requests": 1,
"prompt_tokens": 338,
"completion_tokens": 21306,
"allowance_tokens": 43693,
"length_stops": 0,
"errors": 0,
"seconds": 183.986,
"budget_s": 146.5214834192194,
"last_prompt_tokens": 338
},
"gpqa_diamond:gpqa_diamond/reckYqR92oJkqJXkE#1": {
"requests": 1,
"prompt_tokens": 173,
"completion_tokens": 6045,
"allowance_tokens": 43725,
"length_stops": 0,
"errors": 0,
"seconds": 45.113,
"budget_s": 41.67549918706331,
"last_prompt_tokens": 173
},
"gpqa_diamond:gpqa_diamond/reckl6PkaEMWM50yZ#1": {
"requests": 1,
"prompt_tokens": 344,
"completion_tokens": 42826,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 379.035,
"budget_s": 294.0622435779224,
"last_prompt_tokens": 344
},
"gpqa_diamond:gpqa_diamond/recl1UtgTVKishAq4#1": {
"requests": 1,
"prompt_tokens": 262,
"completion_tokens": 37078,
"allowance_tokens": 43708,
"length_stops": 0,
"errors": 0,
"seconds": 352.388,
"budget_s": 254.54560645050367,
"last_prompt_tokens": 262
},
"gpqa_diamond:gpqa_diamond/recmI7EiLv72PxmYK#1": {
"requests": 1,
"prompt_tokens": 280,
"completion_tokens": 1955,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 12.385,
"budget_s": 13.780394296390387,
"last_prompt_tokens": 280
},
"gpqa_diamond:gpqa_diamond/recmkvk6EFAmqyMxR#1": {
"requests": 1,
"prompt_tokens": 213,
"completion_tokens": 1106,
"allowance_tokens": 43717,
"length_stops": 0,
"errors": 0,
"seconds": 6.829,
"budget_s": 7.869609823280582,
"last_prompt_tokens": 213
},
"gpqa_diamond:gpqa_diamond/recmwwQJnx7ll7bqL#1": {
"requests": 1,
"prompt_tokens": 297,
"completion_tokens": 717,
"allowance_tokens": 43701,
"length_stops": 0,
"errors": 0,
"seconds": 4.287,
"budget_s": 5.316083287495576,
"last_prompt_tokens": 297
},
"gpqa_diamond:gpqa_diamond/recn3NhOhqAPLda16#1": {
"requests": 1,
"prompt_tokens": 317,
"completion_tokens": 12402,
"allowance_tokens": 43697,
"length_stops": 0,
"errors": 0,
"seconds": 101.799,
"budget_s": 85.45083073399601,
"last_prompt_tokens": 317
},
"gpqa_diamond:gpqa_diamond/recnGEpF1srQpaqWq#1": {
"requests": 1,
"prompt_tokens": 194,
"completion_tokens": 10840,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 81.632,
"budget_s": 74.57646188284434,
"last_prompt_tokens": 194
},
"gpqa_diamond:gpqa_diamond/recnTTKdBzfuoZ7w7#1": {
"requests": 1,
"prompt_tokens": 2841,
"completion_tokens": 43200,
"allowance_tokens": 43200,
"length_stops": 1,
"errors": 0,
"seconds": 347.986,
"budget_s": 299.99435673828606,
"last_prompt_tokens": 2841
},
"gpqa_diamond:gpqa_diamond/recnawZPumSCLMVgp#1": {
"requests": 1,
"prompt_tokens": 335,
"completion_tokens": 10821,
"allowance_tokens": 43693,
"length_stops": 0,
"errors": 0,
"seconds": 83.623,
"budget_s": 74.63639532017862,
"last_prompt_tokens": 335
},
"gpqa_diamond:gpqa_diamond/recnjViFrqlZNL3fY#1": {
"requests": 1,
"prompt_tokens": 177,
"completion_tokens": 2791,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 21.102,
"budget_s": 19.372748814846666,
"last_prompt_tokens": 177
},
"gpqa_diamond:gpqa_diamond/reco8WSc71p8zAv4q#1": {
"requests": 1,
"prompt_tokens": 409,
"completion_tokens": 43679,
"allowance_tokens": 43679,
"length_stops": 1,
"errors": 0,
"seconds": 383.277,
"budget_s": 299.9977527497069,
"last_prompt_tokens": 409
},
"gpqa_diamond:gpqa_diamond/recoiTJPGUmzAkief#1": {
"requests": 1,
"prompt_tokens": 376,
"completion_tokens": 2518,
"allowance_tokens": 43685,
"length_stops": 0,
"errors": 0,
"seconds": 21.986,
"budget_s": 17.769592196860167,
"last_prompt_tokens": 376
},
"gpqa_diamond:gpqa_diamond/recooG6bivTUJpDBz#1": {
"requests": 1,
"prompt_tokens": 370,
"completion_tokens": 12802,
"allowance_tokens": 43687,
"length_stops": 0,
"errors": 0,
"seconds": 95.626,
"budget_s": 88.26456346288946,
"last_prompt_tokens": 370
},
"gpqa_diamond:gpqa_diamond/recoy9ZLBsc7HIRBy#1": {
"requests": 1,
"prompt_tokens": 301,
"completion_tokens": 10954,
"allowance_tokens": 43700,
"length_stops": 0,
"errors": 0,
"seconds": 75.177,
"budget_s": 75.5023296657211,
"last_prompt_tokens": 301
},
"gpqa_diamond:gpqa_diamond/recpJmTOXx6T48nDJ#1": {
"requests": 1,
"prompt_tokens": 192,
"completion_tokens": 8792,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 61.449,
"budget_s": 60.53348060480063,
"last_prompt_tokens": 192
},
"gpqa_diamond:gpqa_diamond/recpki12iG9RUGrz9#1": {
"requests": 1,
"prompt_tokens": 416,
"completion_tokens": 2078,
"allowance_tokens": 43677,
"length_stops": 0,
"errors": 0,
"seconds": 15.08,
"budget_s": 14.807079630960427,
"last_prompt_tokens": 416
},
"gpqa_diamond:gpqa_diamond/recqFDvYKKRmbnoUb#1": {
"requests": 1,
"prompt_tokens": 236,
"completion_tokens": 647,
"allowance_tokens": 43713,
"length_stops": 0,
"errors": 0,
"seconds": 4.017,
"budget_s": 4.753910014455492,
"last_prompt_tokens": 236
},
"gpqa_diamond:gpqa_diamond/recqGD3fxPCI59vPQ#1": {
"requests": 1,
"prompt_tokens": 283,
"completion_tokens": 2472,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 18.292,
"budget_s": 17.3287898145693,
"last_prompt_tokens": 283
},
"gpqa_diamond:gpqa_diamond/recqLRu4BcJvlSANc#1": {
"requests": 1,
"prompt_tokens": 222,
"completion_tokens": 516,
"allowance_tokens": 43716,
"length_stops": 0,
"errors": 0,
"seconds": 3.467,
"budget_s": 3.8369413601984075,
"last_prompt_tokens": 222
},
"gpqa_diamond:gpqa_diamond/recr3VHM4zYf6dMFY#1": {
"requests": 1,
"prompt_tokens": 344,
"completion_tokens": 34675,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 310.57,
"budget_s": 238.18218928151333,
"last_prompt_tokens": 344
},
"gpqa_diamond:gpqa_diamond/recrHBEJJoDTV05JR#1": {
"requests": 1,
"prompt_tokens": 283,
"completion_tokens": 22260,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 174.183,
"budget_s": 152.98754511052584,
"last_prompt_tokens": 283
},
"gpqa_diamond:gpqa_diamond/recrNbtgTNoabJJi6#1": {
"requests": 1,
"prompt_tokens": 150,
"completion_tokens": 8801,
"allowance_tokens": 43730,
"length_stops": 0,
"errors": 0,
"seconds": 71.829,
"budget_s": 60.53852873688355,
"last_prompt_tokens": 150
},
"gpqa_diamond:gpqa_diamond/recrs0kUo7Ua1xhKO#1": {
"requests": 1,
"prompt_tokens": 207,
"completion_tokens": 251,
"allowance_tokens": 43719,
"length_stops": 0,
"errors": 0,
"seconds": 1.494,
"budget_s": 1.9999724759249942,
"last_prompt_tokens": 207
},
"gpqa_diamond:gpqa_diamond/recs3PLPUEMiqg4P8#1": {
"requests": 1,
"prompt_tokens": 448,
"completion_tokens": 8721,
"allowance_tokens": 43671,
"length_stops": 0,
"errors": 0,
"seconds": 65.815,
"budget_s": 60.392041950143614,
"last_prompt_tokens": 448
},
"gpqa_diamond:gpqa_diamond/rect4iLrSfUwkNTno#1": {
"requests": 1,
"prompt_tokens": 225,
"completion_tokens": 1242,
"allowance_tokens": 43715,
"length_stops": 0,
"errors": 0,
"seconds": 6.838,
"budget_s": 8.818158783413448,
"last_prompt_tokens": 225
},
"gpqa_diamond:gpqa_diamond/rectXfsCM1dj4Kv2c#1": {
"requests": 1,
"prompt_tokens": 157,
"completion_tokens": 6555,
"allowance_tokens": 43728,
"length_stops": 0,
"errors": 0,
"seconds": 51.922,
"budget_s": 45.150277018600555,
"last_prompt_tokens": 157
},
"gpqa_diamond:gpqa_diamond/rectlyG9pCAAuWhoB#1": {
"requests": 1,
"prompt_tokens": 348,
"completion_tokens": 43691,
"allowance_tokens": 43691,
"length_stops": 1,
"errors": 0,
"seconds": 386.223,
"budget_s": 299.9977392671594,
"last_prompt_tokens": 348
},
"gpqa_diamond:gpqa_diamond/recuYEkVjdVUwA3c0#1": {
"requests": 1,
"prompt_tokens": 191,
"completion_tokens": 1565,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 11.364,
"budget_s": 10.986658497170605,
"last_prompt_tokens": 191
},
"gpqa_diamond:gpqa_diamond/recuyeuT5rQ6qDt8F#1": {
"requests": 1,
"prompt_tokens": 279,
"completion_tokens": 43704,
"allowance_tokens": 43704,
"length_stops": 1,
"errors": 0,
"seconds": 376.977,
"budget_s": 299.9937904712936,
"last_prompt_tokens": 279
},
"gpqa_diamond:gpqa_diamond/recv7GsQg3f0fvB1f#1": {
"requests": 1,
"prompt_tokens": 301,
"completion_tokens": 6163,
"allowance_tokens": 43700,
"length_stops": 0,
"errors": 0,
"seconds": 50.685,
"budget_s": 42.65711556510822,
"last_prompt_tokens": 301
},
"gpqa_diamond:gpqa_diamond/recvZlMbpPz0yLDle#1": {
"requests": 1,
"prompt_tokens": 305,
"completion_tokens": 10172,
"allowance_tokens": 43699,
"length_stops": 0,
"errors": 0,
"seconds": 80.734,
"budget_s": 70.14664029469733,
"last_prompt_tokens": 305
},
"gpqa_diamond:gpqa_diamond/recvlnu8BuLmXZhSX#1": {
"requests": 1,
"prompt_tokens": 248,
"completion_tokens": 1245,
"allowance_tokens": 43711,
"length_stops": 0,
"errors": 0,
"seconds": 6.974,
"budget_s": 8.869749501510327,
"last_prompt_tokens": 248
},
"gpqa_diamond:gpqa_diamond/recw4rROcnHKNZhtK#1": {
"requests": 1,
"prompt_tokens": 245,
"completion_tokens": 2957,
"allowance_tokens": 43711,
"length_stops": 0,
"errors": 0,
"seconds": 21.752,
"budget_s": 20.602502434649747,
"last_prompt_tokens": 245
},
"gpqa_diamond:gpqa_diamond/recwW1A85nfyQpReG#1": {
"requests": 1,
"prompt_tokens": 179,
"completion_tokens": 8219,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 60.967,
"budget_s": 56.5876824327091,
"last_prompt_tokens": 179
},
"gpqa_diamond:gpqa_diamond/recwlwlcPvXVNPmvl#1": {
"requests": 1,
"prompt_tokens": 273,
"completion_tokens": 591,
"allowance_tokens": 43706,
"length_stops": 0,
"errors": 0,
"seconds": 3.473,
"budget_s": 4.419904018594796,
"last_prompt_tokens": 273
},
"gpqa_diamond:gpqa_diamond/recxTy0x7M6T9ikc0#1": {
"requests": 1,
"prompt_tokens": 582,
"completion_tokens": 18339,
"allowance_tokens": 43645,
"length_stops": 0,
"errors": 0,
"seconds": 147.849,
"budget_s": 126.51001992931127,
"last_prompt_tokens": 582
},
"gpqa_diamond:gpqa_diamond/recxsX66ktJ1Lwt4f#1": {
"requests": 1,
"prompt_tokens": 300,
"completion_tokens": 896,
"allowance_tokens": 43700,
"length_stops": 0,
"errors": 0,
"seconds": 6.337,
"budget_s": 6.5472835716926125,
"last_prompt_tokens": 300
},
"gpqa_diamond:gpqa_diamond/recyPffUDqC2k7ZZO#1": {
"requests": 1,
"prompt_tokens": 482,
"completion_tokens": 837,
"allowance_tokens": 43664,
"length_stops": 0,
"errors": 0,
"seconds": 4.583,
"budget_s": 6.388296188644009,
"last_prompt_tokens": 482
},
"gpqa_diamond:gpqa_diamond/recyl3usDqb7ruXJx#1": {
"requests": 1,
"prompt_tokens": 320,
"completion_tokens": 24018,
"allowance_tokens": 43696,
"length_stops": 0,
"errors": 0,
"seconds": 202.663,
"budget_s": 165.08961057751463,
"last_prompt_tokens": 320
},
"gpqa_diamond:gpqa_diamond/recypVp2NmPlBKVTp#1": {
"requests": 1,
"prompt_tokens": 262,
"completion_tokens": 310,
"allowance_tokens": 43708,
"length_stops": 0,
"errors": 0,
"seconds": 2.644,
"budget_s": 2.4786408793630423,
"last_prompt_tokens": 262
},
"gpqa_diamond:gpqa_diamond/recyrk6XBVwugG5u8#1": {
"requests": 1,
"prompt_tokens": 256,
"completion_tokens": 12828,
"allowance_tokens": 43709,
"length_stops": 0,
"errors": 0,
"seconds": 103.587,
"budget_s": 88.28903863271631,
"last_prompt_tokens": 256
},
"gpqa_diamond:gpqa_diamond/recywRj5a8EEjj2Ib#1": {
"requests": 1,
"prompt_tokens": 277,
"completion_tokens": 1413,
"allowance_tokens": 43705,
"length_stops": 0,
"errors": 0,
"seconds": 9.506,
"budget_s": 10.060608598183231,
"last_prompt_tokens": 277
},
"gpqa_diamond:gpqa_diamond/recz3MfYHPRhsEQkW#1": {
"requests": 1,
"prompt_tokens": 320,
"completion_tokens": 18583,
"allowance_tokens": 43696,
"length_stops": 0,
"errors": 0,
"seconds": 156.187,
"budget_s": 127.82938543937412,
"last_prompt_tokens": 320
},
"gpqa_diamond:gpqa_diamond/reczQ4I0VpENdMtIj#1": {
"requests": 1,
"prompt_tokens": 261,
"completion_tokens": 15639,
"allowance_tokens": 43708,
"length_stops": 0,
"errors": 0,
"seconds": 130.078,
"budget_s": 107.56689480041688,
"last_prompt_tokens": 261
},
"gpqa_diamond:gpqa_diamond/reczUoM8JsxU6pYxr#1": {
"requests": 1,
"prompt_tokens": 268,
"completion_tokens": 19403,
"allowance_tokens": 43707,
"length_stops": 0,
"errors": 0,
"seconds": 142.945,
"budget_s": 133.38084236092396,
"last_prompt_tokens": 268
},
"gpqa_diamond:gpqa_diamond/reczjcMtrB1YGS2fO#1": {
"requests": 1,
"prompt_tokens": 247,
"completion_tokens": 14194,
"allowance_tokens": 43711,
"length_stops": 0,
"errors": 0,
"seconds": 112.682,
"budget_s": 97.64165828387522,
"last_prompt_tokens": 247
},
"gpqa_diamond:gpqa_diamond/reczkBiPPNrNN49Hp#1": {
"requests": 1,
"prompt_tokens": 252,
"completion_tokens": 4737,
"allowance_tokens": 43710,
"length_stops": 0,
"errors": 0,
"seconds": 32.487,
"budget_s": 32.814925308115335,
"last_prompt_tokens": 252
},
"gpqa_diamond:gpqa_diamond/reczzzihL7btBH7RO#1": {
"requests": 1,
"prompt_tokens": 349,
"completion_tokens": 22030,
"allowance_tokens": 43691,
"length_stops": 0,
"errors": 0,
"seconds": 191.861,
"budget_s": 151.49978054855168,
"last_prompt_tokens": 349
},
"aime_2025:aime_2025/I-1#1": {
"requests": 1,
"prompt_tokens": 121,
"completion_tokens": 697,
"allowance_tokens": 43735,
"length_stops": 0,
"errors": 0,
"seconds": 3.44,
"budget_s": 4.941570892044531,
"last_prompt_tokens": 121
},
"aime_2025:aime_2025/I-1#2": {
"requests": 1,
"prompt_tokens": 121,
"completion_tokens": 723,
"allowance_tokens": 43735,
"length_stops": 0,
"errors": 0,
"seconds": 3.841,
"budget_s": 5.119816679273906,
"last_prompt_tokens": 121
},
"aime_2025:aime_2025/I-1#3": {
"requests": 1,
"prompt_tokens": 121,
"completion_tokens": 789,
"allowance_tokens": 43735,
"length_stops": 0,
"errors": 0,
"seconds": 4.111,
"budget_s": 5.572286754548473,
"last_prompt_tokens": 121
},
"aime_2025:aime_2025/I-1#4": {
"requests": 1,
"prompt_tokens": 121,
"completion_tokens": 933,
"allowance_tokens": 43735,
"length_stops": 0,
"errors": 0,
"seconds": 4.916,
"budget_s": 6.559494191511164,
"last_prompt_tokens": 121
},
"aime_2025:aime_2025/I-2#1": {
"requests": 1,
"prompt_tokens": 231,
"completion_tokens": 27351,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 201.711,
"budget_s": 187.81930038810108,
"last_prompt_tokens": 231
},
"aime_2025:aime_2025/I-2#2": {
"requests": 1,
"prompt_tokens": 231,
"completion_tokens": 28516,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 202.845,
"budget_s": 195.80608277741732,
"last_prompt_tokens": 231
},
"aime_2025:aime_2025/I-2#3": {
"requests": 1,
"prompt_tokens": 231,
"completion_tokens": 23534,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 169.652,
"budget_s": 161.65144770138863,
"last_prompt_tokens": 231
},
"aime_2025:aime_2025/I-2#4": {
"requests": 1,
"prompt_tokens": 231,
"completion_tokens": 21224,
"allowance_tokens": 43714,
"length_stops": 0,
"errors": 0,
"seconds": 149.383,
"budget_s": 145.81499506677878,
"last_prompt_tokens": 231
},
"aime_2025:aime_2025/I-3#1": {
"requests": 1,
"prompt_tokens": 200,
"completion_tokens": 1364,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 7.314,
"budget_s": 9.620821235327925,
"last_prompt_tokens": 200
},
"aime_2025:aime_2025/I-3#2": {
"requests": 1,
"prompt_tokens": 200,
"completion_tokens": 1014,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 5.188,
"budget_s": 7.221358714932493,
"last_prompt_tokens": 200
},
"aime_2025:aime_2025/I-3#3": {
"requests": 1,
"prompt_tokens": 200,
"completion_tokens": 1118,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 6.015,
"budget_s": 7.934341863849993,
"last_prompt_tokens": 200
},
"aime_2025:aime_2025/I-3#4": {
"requests": 1,
"prompt_tokens": 200,
"completion_tokens": 970,
"allowance_tokens": 43720,
"length_stops": 0,
"errors": 0,
"seconds": 5.111,
"budget_s": 6.919711998082782,
"last_prompt_tokens": 200
},
"aime_2025:aime_2025/I-4#1": {
"requests": 1,
"prompt_tokens": 145,
"completion_tokens": 1377,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 7.279,
"budget_s": 9.635756550371221,
"last_prompt_tokens": 145
},
"aime_2025:aime_2025/I-4#2": {
"requests": 1,
"prompt_tokens": 145,
"completion_tokens": 1630,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 9.52,
"budget_s": 11.370225172257062,
"last_prompt_tokens": 145
},
"aime_2025:aime_2025/I-4#3": {
"requests": 1,
"prompt_tokens": 145,
"completion_tokens": 1644,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 9.152,
"budget_s": 11.46620367307288,
"last_prompt_tokens": 145
},
"aime_2025:aime_2025/I-4#4": {
"requests": 1,
"prompt_tokens": 145,
"completion_tokens": 2239,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 12.857,
"budget_s": 15.545289957745112,
"last_prompt_tokens": 145
},
"aime_2025:aime_2025/I-5#1": {
"requests": 1,
"prompt_tokens": 163,
"completion_tokens": 27623,
"allowance_tokens": 43727,
"length_stops": 0,
"errors": 0,
"seconds": 202.804,
"budget_s": 189.59230272239284,
"last_prompt_tokens": 163
},
"aime_2025:aime_2025/I-5#2": {
"requests": 1,
"prompt_tokens": 163,
"completion_tokens": 7077,
"allowance_tokens": 43727,
"length_stops": 0,
"errors": 0,
"seconds": 45.298,
"budget_s": 48.73699716797992,
"last_prompt_tokens": 163
},
"aime_2025:aime_2025/I-5#3": {
"requests": 1,
"prompt_tokens": 163,
"completion_tokens": 14490,
"allowance_tokens": 43727,
"length_stops": 0,
"errors": 0,
"seconds": 96.975,
"budget_s": 99.55761334995515,
"last_prompt_tokens": 163
},
"aime_2025:aime_2025/I-5#4": {
"requests": 1,
"prompt_tokens": 163,
"completion_tokens": 5594,
"allowance_tokens": 43727,
"length_stops": 0,
"errors": 0,
"seconds": 34.462,
"budget_s": 38.57013168870442,
"last_prompt_tokens": 163
},
"aime_2025:aime_2025/I-6#1": {
"requests": 1,
"prompt_tokens": 174,
"completion_tokens": 4056,
"allowance_tokens": 43725,
"length_stops": 0,
"errors": 0,
"seconds": 26.11,
"budget_s": 28.04104532908106,
"last_prompt_tokens": 174
},
"aime_2025:aime_2025/I-6#2": {
"requests": 1,
"prompt_tokens": 174,
"completion_tokens": 2123,
"allowance_tokens": 43725,
"length_stops": 0,
"errors": 0,
"seconds": 12.739,
"budget_s": 14.789156609297152,
"last_prompt_tokens": 174
},
"aime_2025:aime_2025/I-6#3": {
"requests": 1,
"prompt_tokens": 174,
"completion_tokens": 2079,
"allowance_tokens": 43725,
"length_stops": 0,
"errors": 0,
"seconds": 12.062,
"budget_s": 14.487509892447441,
"last_prompt_tokens": 174
},
"aime_2025:aime_2025/I-6#4": {
"requests": 1,
"prompt_tokens": 174,
"completion_tokens": 1930,
"allowance_tokens": 43725,
"length_stops": 0,
"errors": 0,
"seconds": 11.367,
"budget_s": 13.466024419479101,
"last_prompt_tokens": 174
},
"aime_2025:aime_2025/I-7#1": {
"requests": 1,
"prompt_tokens": 209,
"completion_tokens": 21505,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 170.863,
"budget_s": 147.7117456588677,
"last_prompt_tokens": 209
},
"aime_2025:aime_2025/I-7#2": {
"requests": 1,
"prompt_tokens": 209,
"completion_tokens": 7855,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 59.726,
"budget_s": 54.13270736344589,
"last_prompt_tokens": 209
},
"aime_2025:aime_2025/I-7#3": {
"requests": 1,
"prompt_tokens": 209,
"completion_tokens": 17210,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 134.253,
"budget_s": 118.2669127300152,
"last_prompt_tokens": 209
},
"aime_2025:aime_2025/I-7#4": {
"requests": 1,
"prompt_tokens": 209,
"completion_tokens": 17853,
"allowance_tokens": 43718,
"length_stops": 0,
"errors": 0,
"seconds": 141.878,
"budget_s": 122.67506816034167,
"last_prompt_tokens": 209
},
"aime_2025:aime_2025/I-8#1": {
"requests": 1,
"prompt_tokens": 186,
"completion_tokens": 3343,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 19.021,
"budget_s": 23.169183775454723,
"last_prompt_tokens": 186
},
"aime_2025:aime_2025/I-8#2": {
"requests": 1,
"prompt_tokens": 186,
"completion_tokens": 4008,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 22.907,
"budget_s": 27.72816256420604,
"last_prompt_tokens": 186
},
"aime_2025:aime_2025/I-8#3": {
"requests": 1,
"prompt_tokens": 186,
"completion_tokens": 9011,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 54.003,
"budget_s": 62.02676539145845,
"last_prompt_tokens": 186
},
"aime_2025:aime_2025/I-8#4": {
"requests": 1,
"prompt_tokens": 186,
"completion_tokens": 3739,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 21.119,
"budget_s": 25.884004227102125,
"last_prompt_tokens": 186
},
"aime_2025:aime_2025/I-9#1": {
"requests": 1,
"prompt_tokens": 188,
"completion_tokens": 12901,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 86.146,
"budget_s": 88.69777513398326,
"last_prompt_tokens": 188
},
"aime_2025:aime_2025/I-9#2": {
"requests": 1,
"prompt_tokens": 188,
"completion_tokens": 38381,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 269.586,
"budget_s": 263.37864661877063,
"last_prompt_tokens": 188
},
"aime_2025:aime_2025/I-9#3": {
"requests": 1,
"prompt_tokens": 188,
"completion_tokens": 34741,
"allowance_tokens": 43722,
"length_stops": 0,
"errors": 0,
"seconds": 242.619,
"budget_s": 238.42423640665817,
"last_prompt_tokens": 188
},
"aime_2025:aime_2025/I-9#4": {
"requests": 1,
"prompt_tokens": 188,
"completion_tokens": 43722,
"allowance_tokens": 43722,
"length_stops": 1,
"errors": 0,
"seconds": 304.304,
"budget_s": 299.9944446800049,
"last_prompt_tokens": 188
},
"aime_2025:aime_2025/I-10#1": {
"requests": 1,
"prompt_tokens": 330,
"completion_tokens": 24816,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 183.631,
"budget_s": 170.57387377466551,
"last_prompt_tokens": 330
},
"aime_2025:aime_2025/I-10#2": {
"requests": 1,
"prompt_tokens": 330,
"completion_tokens": 22060,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 166.654,
"budget_s": 151.67982032835178,
"last_prompt_tokens": 330
},
"aime_2025:aime_2025/I-10#3": {
"requests": 1,
"prompt_tokens": 330,
"completion_tokens": 30154,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 239.785,
"budget_s": 207.1691050142964,
"last_prompt_tokens": 330
},
"aime_2025:aime_2025/I-10#4": {
"requests": 1,
"prompt_tokens": 330,
"completion_tokens": 25099,
"allowance_tokens": 43694,
"length_stops": 0,
"errors": 0,
"seconds": 190.355,
"budget_s": 172.51401061258525,
"last_prompt_tokens": 330
},
"aime_2025:aime_2025/I-11#1": {
"requests": 1,
"prompt_tokens": 287,
"completion_tokens": 26603,
"allowance_tokens": 43703,
"length_stops": 0,
"errors": 0,
"seconds": 199.646,
"budget_s": 182.76684264529234,
"last_prompt_tokens": 287
},
"aime_2025:aime_2025/I-11#2": {
"requests": 1,
"prompt_tokens": 287,
"completion_tokens": 25701,
"allowance_tokens": 43703,
"length_stops": 0,
"errors": 0,
"seconds": 188.731,
"budget_s": 176.58308494987324,
"last_prompt_tokens": 287
},
"aime_2025:aime_2025/I-11#3": {
"requests": 1,
"prompt_tokens": 287,
"completion_tokens": 31430,
"allowance_tokens": 43703,
"length_stops": 0,
"errors": 0,
"seconds": 233.276,
"budget_s": 215.85885860514588,
"last_prompt_tokens": 287
},
"aime_2025:aime_2025/I-11#4": {
"requests": 1,
"prompt_tokens": 287,
"completion_tokens": 34164,
"allowance_tokens": 43703,
"length_stops": 0,
"errors": 0,
"seconds": 267.404,
"budget_s": 234.60208869303477,
"last_prompt_tokens": 287
},
"aime_2025:aime_2025/I-12#1": {
"requests": 1,
"prompt_tokens": 195,
"completion_tokens": 25583,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 185.503,
"budget_s": 175.65002771416596,
"last_prompt_tokens": 195
},
"aime_2025:aime_2025/I-12#2": {
"requests": 1,
"prompt_tokens": 195,
"completion_tokens": 29821,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 227.599,
"budget_s": 204.70409103255406,
"last_prompt_tokens": 195
},
"aime_2025:aime_2025/I-12#3": {
"requests": 1,
"prompt_tokens": 195,
"completion_tokens": 14478,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 100.146,
"budget_s": 99.5185097456195,
"last_prompt_tokens": 195
},
"aime_2025:aime_2025/I-12#4": {
"requests": 1,
"prompt_tokens": 195,
"completion_tokens": 36636,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 279.894,
"budget_s": 251.42505410825368,
"last_prompt_tokens": 195
},
"aime_2025:aime_2025/I-13#1": {
"requests": 1,
"prompt_tokens": 167,
"completion_tokens": 36349,
"allowance_tokens": 43726,
"length_stops": 0,
"errors": 0,
"seconds": 321.489,
"budget_s": 249.41972661971124,
"last_prompt_tokens": 167
},
"aime_2025:aime_2025/I-13#2": {
"requests": 1,
"prompt_tokens": 167,
"completion_tokens": 35514,
"allowance_tokens": 43726,
"length_stops": 0,
"errors": 0,
"seconds": 309.762,
"budget_s": 243.69529460676787,
"last_prompt_tokens": 167
},
"aime_2025:aime_2025/I-13#3": {
"requests": 1,
"prompt_tokens": 167,
"completion_tokens": 43726,
"allowance_tokens": 43726,
"length_stops": 1,
"errors": 0,
"seconds": 392.155,
"budget_s": 299.9935409424458,
"last_prompt_tokens": 167
},
"aime_2025:aime_2025/I-13#4": {
"requests": 1,
"prompt_tokens": 167,
"completion_tokens": 43726,
"allowance_tokens": 43726,
"length_stops": 1,
"errors": 0,
"seconds": 387.353,
"budget_s": 299.9935409424458,
"last_prompt_tokens": 167
},
"aime_2025:aime_2025/I-14#1": {
"requests": 1,
"prompt_tokens": 216,
"completion_tokens": 43717,
"allowance_tokens": 43717,
"length_stops": 1,
"errors": 0,
"seconds": 359.263,
"budget_s": 299.99793486581746,
"last_prompt_tokens": 216
},
"aime_2025:aime_2025/I-14#2": {
"requests": 1,
"prompt_tokens": 216,
"completion_tokens": 43717,
"allowance_tokens": 43717,
"length_stops": 1,
"errors": 0,
"seconds": 336.516,
"budget_s": 299.99793486581746,
"last_prompt_tokens": 216
},
"aime_2025:aime_2025/I-14#3": {
"requests": 1,
"prompt_tokens": 216,
"completion_tokens": 43717,
"allowance_tokens": 43717,
"length_stops": 1,
"errors": 0,
"seconds": 345.347,
"budget_s": 299.99793486581746,
"last_prompt_tokens": 216
},
"aime_2025:aime_2025/I-14#4": {
"requests": 1,
"prompt_tokens": 216,
"completion_tokens": 43717,
"allowance_tokens": 43717,
"length_stops": 1,
"errors": 0,
"seconds": 345.332,
"budget_s": 299.99793486581746,
"last_prompt_tokens": 216
},
"aime_2025:aime_2025/I-15#1": {
"requests": 1,
"prompt_tokens": 158,
"completion_tokens": 43728,
"allowance_tokens": 43728,
"length_stops": 1,
"errors": 0,
"seconds": 376.901,
"budget_s": 299.9951123712637,
"last_prompt_tokens": 158
},
"aime_2025:aime_2025/I-15#2": {
"requests": 1,
"prompt_tokens": 158,
"completion_tokens": 43728,
"allowance_tokens": 43728,
"length_stops": 1,
"errors": 0,
"seconds": 366.494,
"budget_s": 299.9951123712637,
"last_prompt_tokens": 158
},
"aime_2025:aime_2025/I-15#3": {
"requests": 1,
"prompt_tokens": 158,
"completion_tokens": 43728,
"allowance_tokens": 43728,
"length_stops": 1,
"errors": 0,
"seconds": 373.521,
"budget_s": 299.9951123712637,
"last_prompt_tokens": 158
},
"aime_2025:aime_2025/I-15#4": {
"requests": 1,
"prompt_tokens": 158,
"completion_tokens": 43728,
"allowance_tokens": 43728,
"length_stops": 1,
"errors": 0,
"seconds": 352.871,
"budget_s": 299.9951123712637,
"last_prompt_tokens": 158
},
"aime_2025:aime_2025/II-1#1": {
"requests": 1,
"prompt_tokens": 197,
"completion_tokens": 2024,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 11.824,
"budget_s": 14.141475392878792,
"last_prompt_tokens": 197
},
"aime_2025:aime_2025/II-1#2": {
"requests": 1,
"prompt_tokens": 197,
"completion_tokens": 1635,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 8.412,
"budget_s": 11.4746441916393,
"last_prompt_tokens": 197
},
"aime_2025:aime_2025/II-1#3": {
"requests": 1,
"prompt_tokens": 197,
"completion_tokens": 2125,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 11.987,
"budget_s": 14.833891720192902,
"last_prompt_tokens": 197
},
"aime_2025:aime_2025/II-1#4": {
"requests": 1,
"prompt_tokens": 197,
"completion_tokens": 1399,
"allowance_tokens": 43721,
"length_stops": 0,
"errors": 0,
"seconds": 7.392,
"budget_s": 9.856720892172666,
"last_prompt_tokens": 197
},
"aime_2025:aime_2025/II-2#1": {
"requests": 1,
"prompt_tokens": 127,
"completion_tokens": 965,
"allowance_tokens": 43734,
"length_stops": 0,
"errors": 0,
"seconds": 4.71,
"budget_s": 6.786966812336925,
"last_prompt_tokens": 127
},
"aime_2025:aime_2025/II-2#2": {
"requests": 1,
"prompt_tokens": 127,
"completion_tokens": 1390,
"allowance_tokens": 43734,
"length_stops": 0,
"errors": 0,
"seconds": 7.678,
"budget_s": 9.70059987281709,
"last_prompt_tokens": 127
},
"aime_2025:aime_2025/II-2#3": {
"requests": 1,
"prompt_tokens": 127,
"completion_tokens": 1127,
"allowance_tokens": 43734,
"length_stops": 0,
"errors": 0,
"seconds": 5.671,
"budget_s": 7.897575178919953,
"last_prompt_tokens": 127
},
"aime_2025:aime_2025/II-2#4": {
"requests": 1,
"prompt_tokens": 127,
"completion_tokens": 934,
"allowance_tokens": 43734,
"length_stops": 0,
"errors": 0,
"seconds": 4.782,
"budget_s": 6.574442989101901,
"last_prompt_tokens": 127
},
"aime_2025:aime_2025/II-3#1": {
"requests": 1,
"prompt_tokens": 152,
"completion_tokens": 20899,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 155.477,
"budget_s": 143.48036238628177,
"last_prompt_tokens": 152
},
"aime_2025:aime_2025/II-3#2": {
"requests": 1,
"prompt_tokens": 152,
"completion_tokens": 9842,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 69.626,
"budget_s": 67.67791356338954,
"last_prompt_tokens": 152
},
"aime_2025:aime_2025/II-3#3": {
"requests": 1,
"prompt_tokens": 152,
"completion_tokens": 8988,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 62.684,
"budget_s": 61.8232250136247,
"last_prompt_tokens": 152
},
"aime_2025:aime_2025/II-3#4": {
"requests": 1,
"prompt_tokens": 152,
"completion_tokens": 12325,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 90.175,
"budget_s": 84.70038624379485,
"last_prompt_tokens": 152
},
"aime_2025:aime_2025/II-4#1": {
"requests": 1,
"prompt_tokens": 279,
"completion_tokens": 3166,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 16.973,
"budget_s": 22.081185751893646,
"last_prompt_tokens": 279
},
"aime_2025:aime_2025/II-4#2": {
"requests": 1,
"prompt_tokens": 279,
"completion_tokens": 1835,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 9.5,
"budget_s": 12.956372567189876,
"last_prompt_tokens": 279
},
"aime_2025:aime_2025/II-4#3": {
"requests": 1,
"prompt_tokens": 279,
"completion_tokens": 1891,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 8.933,
"budget_s": 13.340286570453145,
"last_prompt_tokens": 279
},
"aime_2025:aime_2025/II-4#4": {
"requests": 1,
"prompt_tokens": 279,
"completion_tokens": 1968,
"allowance_tokens": 43704,
"length_stops": 0,
"errors": 0,
"seconds": 10.609,
"budget_s": 13.86816832494014,
"last_prompt_tokens": 279
},
"aime_2025:aime_2025/II-5#1": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 35146,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 278.306,
"budget_s": 241.36936545623254,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-5#2": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 43698,
"allowance_tokens": 43698,
"length_stops": 1,
"errors": 0,
"seconds": 359.657,
"budget_s": 299.9985182402946,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-5#3": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 43698,
"allowance_tokens": 43698,
"length_stops": 1,
"errors": 0,
"seconds": 356.049,
"budget_s": 299.9985182402946,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-5#4": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 43698,
"allowance_tokens": 43698,
"length_stops": 1,
"errors": 0,
"seconds": 368.071,
"budget_s": 299.9985182402946,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-6#1": {
"requests": 1,
"prompt_tokens": 311,
"completion_tokens": 14867,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 108.095,
"budget_s": 102.34180929439137,
"last_prompt_tokens": 311
},
"aime_2025:aime_2025/II-6#2": {
"requests": 1,
"prompt_tokens": 311,
"completion_tokens": 20350,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 149.821,
"budget_s": 139.93110357818608,
"last_prompt_tokens": 311
},
"aime_2025:aime_2025/II-6#3": {
"requests": 1,
"prompt_tokens": 311,
"completion_tokens": 10573,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 77.502,
"budget_s": 72.90383197274,
"last_prompt_tokens": 311
},
"aime_2025:aime_2025/II-6#4": {
"requests": 1,
"prompt_tokens": 311,
"completion_tokens": 13061,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 94.519,
"budget_s": 89.96058268915094,
"last_prompt_tokens": 311
},
"aime_2025:aime_2025/II-7#1": {
"requests": 1,
"prompt_tokens": 181,
"completion_tokens": 2646,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 15.109,
"budget_s": 18.384081230942577,
"last_prompt_tokens": 181
},
"aime_2025:aime_2025/II-7#2": {
"requests": 1,
"prompt_tokens": 181,
"completion_tokens": 1957,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 11.437,
"budget_s": 13.660567869364145,
"last_prompt_tokens": 181
},
"aime_2025:aime_2025/II-7#3": {
"requests": 1,
"prompt_tokens": 181,
"completion_tokens": 2203,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 12.339,
"budget_s": 15.347047240842077,
"last_prompt_tokens": 181
},
"aime_2025:aime_2025/II-7#4": {
"requests": 1,
"prompt_tokens": 181,
"completion_tokens": 2753,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 15.341,
"budget_s": 19.117631201463468,
"last_prompt_tokens": 181
},
"aime_2025:aime_2025/II-8#1": {
"requests": 1,
"prompt_tokens": 344,
"completion_tokens": 36051,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 270.059,
"budget_s": 247.61550479026795,
"last_prompt_tokens": 344
},
"aime_2025:aime_2025/II-8#2": {
"requests": 1,
"prompt_tokens": 344,
"completion_tokens": 22264,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 165.084,
"budget_s": 153.09724830829134,
"last_prompt_tokens": 344
},
"aime_2025:aime_2025/II-8#3": {
"requests": 1,
"prompt_tokens": 344,
"completion_tokens": 30352,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 226.586,
"budget_s": 208.5453993510292,
"last_prompt_tokens": 344
},
"aime_2025:aime_2025/II-8#4": {
"requests": 1,
"prompt_tokens": 344,
"completion_tokens": 30996,
"allowance_tokens": 43692,
"length_stops": 0,
"errors": 0,
"seconds": 239.294,
"budget_s": 212.9604103885568,
"last_prompt_tokens": 344
},
"aime_2025:aime_2025/II-9#1": {
"requests": 1,
"prompt_tokens": 179,
"completion_tokens": 5081,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 32.343,
"budget_s": 35.07478703556378,
"last_prompt_tokens": 179
},
"aime_2025:aime_2025/II-9#2": {
"requests": 1,
"prompt_tokens": 179,
"completion_tokens": 11391,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 81.192,
"budget_s": 78.33366847469284,
"last_prompt_tokens": 179
},
"aime_2025:aime_2025/II-9#3": {
"requests": 1,
"prompt_tokens": 179,
"completion_tokens": 10304,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 73.154,
"budget_s": 70.88162344706474,
"last_prompt_tokens": 179
},
"aime_2025:aime_2025/II-9#4": {
"requests": 1,
"prompt_tokens": 179,
"completion_tokens": 6903,
"allowance_tokens": 43724,
"length_stops": 0,
"errors": 0,
"seconds": 47.237,
"budget_s": 47.56570335602228,
"last_prompt_tokens": 179
},
"aime_2025:aime_2025/II-10#1": {
"requests": 1,
"prompt_tokens": 155,
"completion_tokens": 4362,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 27.968,
"budget_s": 30.11323269639303,
"last_prompt_tokens": 155
},
"aime_2025:aime_2025/II-10#2": {
"requests": 1,
"prompt_tokens": 155,
"completion_tokens": 9901,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 71.177,
"budget_s": 68.08644098345101,
"last_prompt_tokens": 155
},
"aime_2025:aime_2025/II-10#3": {
"requests": 1,
"prompt_tokens": 155,
"completion_tokens": 8097,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 55.483,
"budget_s": 55.71892559261285,
"last_prompt_tokens": 155
},
"aime_2025:aime_2025/II-10#4": {
"requests": 1,
"prompt_tokens": 155,
"completion_tokens": 18013,
"allowance_tokens": 43729,
"length_stops": 0,
"errors": 0,
"seconds": 134.781,
"budget_s": 123.69912659901598,
"last_prompt_tokens": 155
},
"aime_2025:aime_2025/II-11#1": {
"requests": 1,
"prompt_tokens": 143,
"completion_tokens": 20682,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 159.685,
"budget_s": 141.98055583805223,
"last_prompt_tokens": 143
},
"aime_2025:aime_2025/II-11#2": {
"requests": 1,
"prompt_tokens": 143,
"completion_tokens": 11168,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 79.65,
"budget_s": 76.75630892650325,
"last_prompt_tokens": 143
},
"aime_2025:aime_2025/II-11#3": {
"requests": 1,
"prompt_tokens": 143,
"completion_tokens": 7582,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 54.006,
"budget_s": 52.17210150325179,
"last_prompt_tokens": 143
},
"aime_2025:aime_2025/II-11#4": {
"requests": 1,
"prompt_tokens": 143,
"completion_tokens": 6835,
"allowance_tokens": 43731,
"length_stops": 0,
"errors": 0,
"seconds": 48.618,
"budget_s": 47.05096292400783,
"last_prompt_tokens": 143
},
"aime_2025:aime_2025/II-12#1": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 13719,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 103.404,
"budget_s": 94.47426995762423,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-12#2": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 19911,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 148.837,
"budget_s": 136.92418974701997,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-12#3": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 24324,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 186.601,
"budget_s": 167.1779843256058,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-12#4": {
"requests": 1,
"prompt_tokens": 313,
"completion_tokens": 27689,
"allowance_tokens": 43698,
"length_stops": 0,
"errors": 0,
"seconds": 218.302,
"budget_s": 190.2471025574076,
"last_prompt_tokens": 313
},
"aime_2025:aime_2025/II-13#1": {
"requests": 1,
"prompt_tokens": 219,
"completion_tokens": 42438,
"allowance_tokens": 43716,
"length_stops": 0,
"errors": 0,
"seconds": 321.176,
"budget_s": 291.2336598507672,
"last_prompt_tokens": 219
},
"aime_2025:aime_2025/II-13#2": {
"requests": 1,
"prompt_tokens": 219,
"completion_tokens": 43716,
"allowance_tokens": 43716,
"length_stops": 1,
"errors": 0,
"seconds": 328.697,
"budget_s": 299.9951258538111,
"last_prompt_tokens": 219
},
"aime_2025:aime_2025/II-13#3": {
"requests": 1,
"prompt_tokens": 219,
"completion_tokens": 43716,
"allowance_tokens": 43716,
"length_stops": 1,
"errors": 0,
"seconds": 336.707,
"budget_s": 299.9951258538111,
"last_prompt_tokens": 219
},
"aime_2025:aime_2025/II-13#4": {
"requests": 1,
"prompt_tokens": 219,
"completion_tokens": 43716,
"allowance_tokens": 43716,
"length_stops": 1,
"errors": 0,
"seconds": 341.699,
"budget_s": 299.9951258538111,
"last_prompt_tokens": 219
},
"aime_2025:aime_2025/II-14#1": {
"requests": 1,
"prompt_tokens": 184,
"completion_tokens": 40495,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 295.463,
"budget_s": 277.86600478169936,
"last_prompt_tokens": 184
},
"aime_2025:aime_2025/II-14#2": {
"requests": 1,
"prompt_tokens": 184,
"completion_tokens": 43723,
"allowance_tokens": 43723,
"length_stops": 1,
"errors": 0,
"seconds": 335.792,
"budget_s": 299.99590482694634,
"last_prompt_tokens": 184
},
"aime_2025:aime_2025/II-14#3": {
"requests": 1,
"prompt_tokens": 184,
"completion_tokens": 30859,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 220.581,
"budget_s": 211.80537379161254,
"last_prompt_tokens": 184
},
"aime_2025:aime_2025/II-14#4": {
"requests": 1,
"prompt_tokens": 184,
"completion_tokens": 40882,
"allowance_tokens": 43723,
"length_stops": 0,
"errors": 0,
"seconds": 305.879,
"budget_s": 280.5191247685366,
"last_prompt_tokens": 184
},
"aime_2025:aime_2025/II-15#1": {
"requests": 1,
"prompt_tokens": 170,
"completion_tokens": 33689,
"allowance_tokens": 43726,
"length_stops": 0,
"errors": 0,
"seconds": 273.251,
"budget_s": 231.18785805990078,
"last_prompt_tokens": 170
},
"aime_2025:aime_2025/II-15#2": {
"requests": 1,
"prompt_tokens": 170,
"completion_tokens": 41109,
"allowance_tokens": 43726,
"length_stops": 0,
"errors": 0,
"seconds": 323.511,
"budget_s": 282.05646349228397,
"last_prompt_tokens": 170
},
"aime_2025:aime_2025/II-15#3": {
"requests": 1,
"prompt_tokens": 170,
"completion_tokens": 33844,
"allowance_tokens": 43726,
"length_stops": 0,
"errors": 0,
"seconds": 259.934,
"budget_s": 232.25047717607592,
"last_prompt_tokens": 170
},
"aime_2025:aime_2025/II-15#4": {
"requests": 1,
"prompt_tokens": 170,
"completion_tokens": 33683,
"allowance_tokens": 43726,
"length_stops": 0,
"errors": 0,
"seconds": 256.305,
"budget_s": 231.146724416694,
"last_prompt_tokens": 170
}
},
"proxy_count_mismatches": 0,
"parallel": 1,
"warmup": {
"seconds": 0.76,
"replies": 2,
"tool_calls": true
},
"limited": false,
"launch_overrides": {},
"sessions": [
{
"started_at": "2026-09-17T23:05:15Z",
"seconds": 66775.7,
"lab_version": "0.1.0+80d380e",
"throttled": false
}
],
"progress": {
"livecodebench": {
"done": 100,
"planned": 100
},
"bfcl": {
"done": 400,
"planned": 400
},
"gpqa_diamond": {
"done": 198,
"planned": 198
},
"aime_2025": {
"done": 30,
"planned": 30
}
},
"telemetry_summary": {
"vram_baseline_mb": 0.9375,
"vram_peak_mb": 23229.125,
"ram_baseline_mb": 20963.20703125,
"ram_peak_mb": 24417.12890625,
"proc_rss_peak_mb": 1758.6015625,
"temp_max_c": 65,
"power_max_w": 250.739,
"clock_max_mhz": 1620,
"throttled": false,
"power_capped_frac": 0.9976040730757711,
"phases": {
"livecodebench": {
"duration_s": 21290.69203403697,
"energy_j": 5305475.058,
"power_avg_w": 249.19223149337992
},
"bfcl": {
"duration_s": 3198.7030250079697,
"energy_j": 792107.277,
"power_avg_w": 247.63389123878622
},
"gpqa_diamond": {
"duration_s": 24382.26750847092,
"energy_j": 6083684.148,
"power_avg_w": 249.51264872663702
},
"aime_2025": {
"duration_s": 17859.98123091401,
"energy_j": 4456047.103,
"power_avg_w": 249.49898017177006
}
}
}
}