{
 "meta": {
  "date": "2026-10-03",
  "tokenizer": "tiktoken cl100k_base",
  "secondary_tokenizer": "tiktoken o200k_base (median only, per benchmark under meta.benchmarks)",
  "stats_method": "numpy; percentiles linear-interpolated; pct_under_N = % with tokens < N",
  "script": "scripts/measure_problems.py",
  "benchmarks": {
   "SWE-bench Verified": {
    "field": "problem_statement",
    "source": "hf:SWE-bench/SWE-bench_Verified (test)",
    "revision": "78f471bf655a3137b2e8a75af1501690ec009ec3",
    "notes": "Control re-measurement of the 2026-05 note's figure (median 294.5).",
    "o200k_median": 297.5,
    "count": 500
   },
   "SWE-bench Multilingual": {
    "field": "problem_statement",
    "source": "hf:SWE-bench/SWE-bench_Multilingual (test)",
    "revision": "846e647b9f33c0b51b739d005d13d85493c9af09",
    "notes": "9 languages, 42 repos.",
    "o200k_median": 372.0,
    "count": 300
   },
   "SWE-bench Multimodal": {
    "field": "problem_statement (text only)",
    "source": "hf:SWE-bench/SWE-bench_Multimodal (test)",
    "revision": "4e6662d51c48e475f7f346e4fa09a6f8b31fcaa5",
    "notes": "Issue images (image_assets) are also given to the model and are NOT counted here, so this understates input.",
    "o200k_median": 249.5,
    "count": 480
   },
   "SWE-bench Pro (V2, public)": {
    "field": "v2/tasks/<id>/instruction.md (= wrapper + problem_statement + requirements + interface + constraints)",
    "source": "github:scaleapi/SWE-bench_Pro-os v2/tasks",
    "revision": "66f92766bba642462d4bbe5479e83f91f9211862",
    "notes": "Full agent-facing instruction. V2 released 2026-09-22 (642 tasks).",
    "o200k_median": 710.0,
    "count": 642
   },
   "SWE-bench Pro (V2, problem_statement only)": {
    "field": "problem_statement",
    "source": "hf:ScaleAI/SWE-bench_Pro (default=V2, test)",
    "revision": "2d52cb3df914a3fcf80c7f66738b3a88ae37fc50",
    "notes": "Issue text alone, comparable to the SWE-bench problem_statement field; excludes requirements/interface.",
    "o200k_median": 183.0,
    "count": 642
   },
   "Multi-SWE-bench": {
    "field": "resolved_issues[*].title + body",
    "source": "hf:ByteDance-Seed/Multi-SWE-bench (7 original languages: c,cpp,go,java,js,ts,rust)",
    "revision": "56ff018c04a38e27ada1e9d0a6d5839a51f88f0d",
    "notes": "Repo also carries kotlin (105) and python (500) files added later; excluded to match the published 7-language set.",
    "o200k_median": 307.0,
    "count": 1632
   },
   "SWE-PolyBench": {
    "field": "problem_statement",
    "source": "hf:AmazonScience/SWE-PolyBench (test.csv)",
    "revision": "d56445f9940eae4e9d2974ec66820c2f1d7754e6",
    "notes": "Java/JS/TS/Python.",
    "o200k_median": 306.0,
    "count": 2110
   },
   "SWE-rebench (leaderboard, all HF months)": {
    "field": "problem_statement",
    "source": "hf:nebius/SWE-rebench-leaderboard (test = 2025-01..2026-03)",
    "revision": "34d5a58864acf91613740a09ec5d205228dcfa39",
    "notes": "The current leaderboard window (2026-05-15..07-01, 111 tasks) is distributed only via Harbor Hub (ibragim-badertdinov/swe-rebench-07-2026) and was not measured.",
    "o200k_median": 348.5,
    "count": 860
   },
   "SWE-rebench (2026-01..03, latest on HF)": {
    "field": "problem_statement",
    "source": "hf:nebius/SWE-rebench-leaderboard splits 2026_01,2026_02,2026_03",
    "revision": "34d5a58864acf91613740a09ec5d205228dcfa39",
    "notes": null,
    "o200k_median": 456.0,
    "count": 215
   },
   "SWE-Lancer Diamond (IC SWE)": {
    "field": "title + description",
    "source": "github:openai/preparedness project/swelancer/all_swelancer_tasks.csv",
    "revision": "51052cede8cc608f95bb00346635e03759013e5a",
    "notes": "Literal '\\n' escapes in the CSV converted to newlines.",
    "o200k_median": 659.0,
    "count": 198
   },
   "SWE-Lancer Diamond (SWE Manager)": {
    "field": "title + description + proposals",
    "source": "github:openai/preparedness project/swelancer/all_swelancer_tasks.csv",
    "revision": "51052cede8cc608f95bb00346635e03759013e5a",
    "notes": "Manager tasks include the competing proposals the model must choose between.",
    "o200k_median": 2135.0,
    "count": 265
   },
   "Terminal-Bench 2.0": {
    "field": "instruction.md",
    "source": "github:harbor-framework/terminal-bench-2",
    "revision": "2fd12b88aafdd04a52c298e3940bcb189f9766d6",
    "notes": null,
    "o200k_median": 165.0,
    "count": 89
   },
   "Terminal-Bench 4.0": {
    "field": "instruction.md",
    "source": "github:harbor-framework/terminal-bench tag v4.0.0",
    "revision": "452bf305c6daa62fc59061d22133a7cbc7c1572e",
    "notes": "Released 2026-08-26; cited in the Claude Opus 5.5 launch (2026-09-22).",
    "o200k_median": 388.5,
    "count": 66
   },
   "DeepSWE": {
    "field": "instruction.md",
    "source": "github:datacurve-ai/deep-swe",
    "revision": "0b9fabbb63b9104d678fe965e1632f2dd9eaa2ea",
    "notes": "arXiv 2607.07946 (2026-07-08).",
    "o200k_median": 438.0,
    "count": 113
   },
   "LiveCodeBench (release_v6)": {
    "field": "question_content",
    "source": "hf:livecodebench/code_generation_lite test.jsonl..test6.jsonl",
    "revision": "0fe84c3912ea0c4d4a78037083943e8f0c4dd505",
    "notes": "release_v6 (May 2023 - Apr 2025) is still the latest release on HF as of 2026-10-03.",
    "o200k_median": 415.0,
    "count": 1055
   },
   "LiveCodeBench (release_v1, control)": {
    "field": "question_content",
    "source": "hf:livecodebench/code_generation_lite test.jsonl",
    "revision": "0fe84c3912ea0c4d4a78037083943e8f0c4dd505",
    "notes": "Control: the 400-problem set the 2026-05 note appears to have used (median 421).",
    "o200k_median": 420.0,
    "count": 400
   },
   "Aider Polyglot": {
    "field": ".docs/introduction.md + instructions.md + instructions.append.md",
    "source": "github:Aider-AI/polyglot-benchmark",
    "revision": "7e0611e77b54e2dea774cdc0aa00cf9f7ed6144f",
    "notes": "Excludes Aider's fixed addendum and the stub source files it adds to the chat.",
    "o200k_median": 432.0,
    "count": 225
   }
  },
  "not_measured": {
   "SWE-bench Pro Verified (arXiv 2609.08149)": "No public dataset link found (hf:ScaleAI/SWE-bench_Pro_Verified does not exist / not public).",
   "FrontierCode v1.1 (Cognition)": "Cited in the Claude Opus 5.5 launch; task texts not public.",
   "CursorBench 4.0": "Cited in the Claude Opus 5.5 launch; internal to Cursor, not public.",
   "SWE-rebench 2026-05..07 window": "Harbor Hub only (ibragim-badertdinov/swe-rebench-07-2026); harbor CLI not used.",
   "Terminal-Bench 2.1 / 3.0": "2.1 referenced by third parties; 3.0 superseded by 4.0 (same repo, tag v3.0.0); not measured separately."
  }
 },
 "SWE-bench Verified": {
  "benchmark": "SWE-bench Verified",
  "status": "ok",
  "stats": {
   "count": 500,
   "min": 24,
   "max": 6939,
   "mean": 447.716,
   "median": 294.5,
   "p25": 163.0,
   "p75": 539.25,
   "p95": 1266.2999999999997,
   "p99": 2513.989999999999,
   "pct_under_1024": 91.8,
   "pct_under_2048": 98.0,
   "pct_under_4096": 99.6,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   322,
   684,
   469,
   1230,
   2162,
   1418,
   894,
   243,
   508,
   1272,
   444,
   688,
   759,
   436,
   748,
   737,
   35,
   384,
   273,
   502,
   193,
   288,
   560,
   812,
   55,
   209,
   77,
   216,
   406,
   2407,
   85,
   165,
   80,
   182,
   890,
   176,
   181,
   95,
   62,
   154,
   214,
   267,
   1034,
   254,
   74,
   737,
   318,
   188,
   135,
   441,
   44,
   122,
   674,
   1260,
   162,
   78,
   114,
   220,
   478,
   272,
   114,
   354,
   98,
   158,
   261,
   287,
   151,
   500,
   142,
   287,
   66,
   360,
   351,
   179,
   155,
   264,
   226,
   218,
   146,
   122,
   97,
   186,
   264,
   156,
   735,
   234,
   59,
   78,
   183,
   277,
   208,
   670,
   326,
   112,
   666,
   1028,
   396,
   409,
   456,
   292,
   77,
   257,
   560,
   92,
   116,
   354,
   58,
   241,
   289,
   142,
   382,
   283,
   786,
   338,
   251,
   1755,
   110,
   288,
   139,
   123,
   163,
   503,
   192,
   301,
   224,
   203,
   153,
   60,
   373,
   96,
   473,
   433,
   146,
   363,
   884,
   268,
   372,
   283,
   424,
   356,
   309,
   718,
   68,
   120,
   280,
   109,
   425,
   676,
   165,
   155,
   564,
   2355,
   48,
   245,
   78,
   36,
   356,
   63,
   369,
   109,
   122,
   383,
   136,
   299,
   1734,
   82,
   633,
   129,
   299,
   175,
   422,
   209,
   251,
   55,
   282,
   120,
   726,
   88,
   1108,
   55,
   654,
   100,
   357,
   326,
   693,
   292,
   594,
   186,
   321,
   461,
   430,
   92,
   185,
   52,
   497,
   1117,
   314,
   73,
   440,
   154,
   359,
   566,
   309,
   255,
   143,
   83,
   738,
   148,
   189,
   367,
   173,
   181,
   1508,
   33,
   220,
   57,
   53,
   165,
   577,
   346,
   163,
   387,
   567,
   121,
   317,
   131,
   261,
   474,
   64,
   219,
   490,
   125,
   159,
   404,
   361,
   198,
   181,
   67,
   289,
   142,
   424,
   146,
   24,
   97,
   169,
   292,
   985,
   359,
   236,
   171,
   262,
   107,
   91,
   438,
   329,
   520,
   385,
   676,
   636,
   374,
   2513,
   398,
   389,
   470,
   232,
   575,
   1074,
   604,
   881,
   510,
   388,
   134,
   532,
   347,
   421,
   288,
   539,
   206,
   248,
   1731,
   153,
   220,
   2636,
   612,
   984,
   152,
   419,
   262,
   377,
   48,
   78,
   2067,
   205,
   166,
   214,
   79,
   426,
   375,
   655,
   540,
   718,
   596,
   401,
   212,
   719,
   568,
   204,
   865,
   1297,
   1266,
   1234,
   267,
   1602,
   2649,
   440,
   919,
   405,
   918,
   529,
   763,
   240,
   202,
   221,
   147,
   217,
   553,
   817,
   6939,
   282,
   947,
   422,
   702,
   1216,
   1177,
   626,
   796,
   268,
   176,
   862,
   657,
   1137,
   693,
   130,
   207,
   4184,
   1074,
   120,
   125,
   244,
   386,
   580,
   490,
   282,
   1766,
   323,
   129,
   397,
   2612,
   1542,
   975,
   1339,
   374,
   325,
   142,
   821,
   670,
   35,
   585,
   513,
   1639,
   567,
   411,
   606,
   556,
   322,
   1673,
   819,
   460,
   317,
   841,
   936,
   780,
   770,
   1042,
   796,
   783,
   340,
   527,
   1484,
   257,
   751,
   340,
   158,
   85,
   195,
   311,
   318,
   445,
   160,
   447,
   482,
   509,
   316,
   346,
   176,
   94,
   543,
   175,
   186,
   537,
   694,
   144,
   984,
   362,
   125,
   211,
   292,
   138,
   529,
   468,
   354,
   755,
   336,
   236,
   393,
   74,
   176,
   333,
   90,
   262,
   291,
   430,
   354,
   152,
   204,
   66,
   657,
   148,
   228,
   576,
   1319,
   877,
   370,
   186,
   224,
   267,
   241,
   288,
   74,
   227,
   575,
   81,
   142,
   381,
   248,
   85,
   151,
   470,
   48,
   636,
   870,
   1076,
   487,
   308,
   96,
   192,
   215,
   207,
   385,
   146,
   625,
   65,
   96,
   308,
   116,
   1238,
   431,
   184,
   161,
   74,
   466,
   261,
   246,
   297,
   192,
   203,
   75,
   472,
   169,
   282,
   124,
   174,
   561,
   218,
   147,
   265,
   209,
   225,
   79,
   100
  ]
 },
 "SWE-bench Multilingual": {
  "benchmark": "SWE-bench Multilingual",
  "status": "ok",
  "stats": {
   "count": 300,
   "min": 33,
   "max": 22492,
   "mean": 614.383,
   "median": 374.0,
   "p25": 217.75,
   "p75": 604.0,
   "p95": 1525.1000000000017,
   "p99": 4862.5099999999975,
   "pct_under_1024": 90.0,
   "pct_under_2048": 97.0,
   "pct_under_4096": 98.67,
   "pct_under_8192": 99.67,
   "pct_under_16384": 99.67,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   183,
   261,
   268,
   378,
   559,
   87,
   221,
   293,
   906,
   185,
   375,
   421,
   571,
   399,
   82,
   301,
   599,
   258,
   377,
   286,
   226,
   387,
   586,
   374,
   414,
   189,
   833,
   231,
   777,
   1517,
   332,
   850,
   381,
   638,
   811,
   33,
   730,
   755,
   818,
   808,
   330,
   872,
   1328,
   524,
   412,
   1078,
   1209,
   206,
   70,
   475,
   309,
   134,
   291,
   232,
   82,
   562,
   212,
   104,
   680,
   790,
   462,
   363,
   470,
   265,
   180,
   22492,
   4860,
   2992,
   3019,
   590,
   2563,
   5111,
   2244,
   1789,
   2940,
   188,
   545,
   563,
   892,
   1056,
   290,
   326,
   433,
   247,
   203,
   140,
   175,
   218,
   1173,
   107,
   312,
   185,
   99,
   153,
   81,
   177,
   179,
   562,
   567,
   374,
   118,
   778,
   362,
   669,
   242,
   162,
   437,
   427,
   242,
   250,
   232,
   209,
   320,
   206,
   36,
   430,
   242,
   383,
   297,
   211,
   588,
   980,
   230,
   1134,
   422,
   193,
   216,
   734,
   284,
   472,
   562,
   301,
   466,
   146,
   101,
   119,
   305,
   697,
   176,
   87,
   151,
   216,
   1679,
   362,
   203,
   397,
   317,
   222,
   194,
   720,
   407,
   496,
   488,
   270,
   409,
   794,
   203,
   219,
   312,
   1142,
   183,
   175,
   325,
   225,
   98,
   716,
   467,
   410,
   142,
   499,
   852,
   121,
   173,
   132,
   419,
   220,
   505,
   271,
   306,
   409,
   442,
   438,
   994,
   376,
   697,
   632,
   432,
   226,
   227,
   400,
   531,
   261,
   446,
   124,
   118,
   250,
   632,
   395,
   566,
   323,
   43,
   1900,
   315,
   262,
   656,
   469,
   353,
   202,
   582,
   173,
   672,
   338,
   177,
   217,
   2015,
   283,
   289,
   375,
   201,
   55,
   206,
   752,
   1267,
   721,
   230,
   610,
   108,
   5908,
   530,
   594,
   400,
   357,
   108,
   861,
   644,
   225,
   423,
   265,
   369,
   748,
   176,
   158,
   319,
   1906,
   1918,
   148,
   432,
   229,
   1323,
   1004,
   380,
   254,
   350,
   400,
   629,
   1102,
   429,
   222,
   126,
   468,
   388,
   408,
   123,
   814,
   838,
   183,
   1400,
   786,
   349,
   150,
   257,
   179,
   417,
   602,
   136,
   448,
   407,
   871,
   367,
   285,
   279,
   437,
   312,
   450,
   485,
   721,
   35,
   136,
   346,
   96,
   139,
   363,
   296,
   1244,
   1488,
   981,
   1438,
   736,
   871,
   168
  ]
 },
 "SWE-bench Multimodal": {
  "benchmark": "SWE-bench Multimodal",
  "status": "ok",
  "stats": {
   "count": 480,
   "min": 52,
   "max": 60719,
   "mean": 441.156,
   "median": 251.5,
   "p25": 164.0,
   "p75": 380.0,
   "p95": 794.3499999999988,
   "p99": 1376.499999999999,
   "pct_under_1024": 97.71,
   "pct_under_2048": 99.38,
   "pct_under_4096": 99.79,
   "pct_under_8192": 99.79,
   "pct_under_16384": 99.79,
   "pct_under_32768": 99.79
  },
  "per_problem_tokens": [
   451,
   151,
   426,
   472,
   236,
   205,
   182,
   839,
   304,
   134,
   283,
   92,
   154,
   441,
   103,
   330,
   495,
   109,
   97,
   81,
   55,
   82,
   199,
   108,
   110,
   151,
   74,
   154,
   258,
   87,
   215,
   386,
   157,
   295,
   472,
   255,
   206,
   256,
   67,
   478,
   276,
   374,
   178,
   171,
   282,
   455,
   213,
   52,
   66,
   66,
   264,
   497,
   377,
   147,
   158,
   215,
   118,
   69,
   438,
   156,
   155,
   640,
   233,
   239,
   273,
   291,
   108,
   126,
   263,
   270,
   390,
   68,
   60719,
   501,
   507,
   593,
   91,
   790,
   349,
   258,
   183,
   148,
   278,
   548,
   189,
   239,
   162,
   225,
   792,
   288,
   317,
   165,
   213,
   86,
   86,
   120,
   213,
   144,
   145,
   249,
   233,
   175,
   75,
   90,
   637,
   166,
   85,
   248,
   172,
   95,
   269,
   81,
   86,
   89,
   162,
   79,
   167,
   105,
   64,
   160,
   124,
   111,
   106,
   156,
   81,
   108,
   213,
   60,
   143,
   252,
   232,
   283,
   287,
   263,
   272,
   269,
   230,
   229,
   303,
   89,
   112,
   107,
   205,
   175,
   163,
   155,
   143,
   110,
   273,
   490,
   422,
   390,
   610,
   207,
   157,
   198,
   158,
   159,
   885,
   563,
   254,
   125,
   210,
   544,
   252,
   197,
   399,
   230,
   239,
   167,
   167,
   298,
   184,
   318,
   156,
   292,
   401,
   143,
   222,
   174,
   462,
   534,
   565,
   128,
   292,
   341,
   91,
   146,
   280,
   363,
   336,
   319,
   386,
   220,
   354,
   205,
   75,
   325,
   484,
   392,
   299,
   184,
   185,
   217,
   181,
   182,
   179,
   181,
   182,
   472,
   183,
   842,
   417,
   216,
   98,
   1008,
   502,
   375,
   166,
   409,
   527,
   386,
   566,
   1008,
   177,
   119,
   195,
   201,
   230,
   143,
   551,
   164,
   108,
   434,
   271,
   108,
   395,
   271,
   142,
   416,
   271,
   155,
   195,
   159,
   152,
   377,
   108,
   245,
   439,
   158,
   583,
   215,
   225,
   315,
   218,
   247,
   333,
   284,
   102,
   125,
   453,
   363,
   379,
   123,
   373,
   239,
   290,
   370,
   257,
   342,
   109,
   273,
   290,
   283,
   498,
   477,
   96,
   355,
   133,
   680,
   447,
   266,
   75,
   823,
   165,
   269,
   374,
   749,
   314,
   642,
   419,
   95,
   295,
   289,
   208,
   374,
   72,
   1098,
   175,
   510,
   664,
   92,
   447,
   511,
   319,
   100,
   920,
   363,
   488,
   293,
   310,
   118,
   357,
   285,
   2261,
   1366,
   1366,
   523,
   201,
   222,
   1092,
   1510,
   367,
   1416,
   844,
   176,
   206,
   81,
   202,
   239,
   297,
   308,
   523,
   258,
   416,
   187,
   307,
   283,
   182,
   277,
   226,
   211,
   301,
   189,
   380,
   378,
   711,
   342,
   744,
   210,
   915,
   473,
   332,
   158,
   330,
   188,
   182,
   270,
   225,
   386,
   384,
   740,
   274,
   517,
   215,
   301,
   250,
   302,
   340,
   222,
   380,
   541,
   300,
   262,
   265,
   610,
   292,
   367,
   414,
   793,
   163,
   232,
   224,
   336,
   250,
   229,
   134,
   121,
   245,
   289,
   288,
   562,
   122,
   236,
   138,
   82,
   437,
   169,
   160,
   820,
   289,
   195,
   324,
   380,
   269,
   402,
   199,
   296,
   127,
   201,
   366,
   192,
   306,
   671,
   251,
   116,
   98,
   237,
   149,
   307,
   143,
   650,
   268,
   78,
   317,
   193,
   232,
   148,
   285,
   176,
   205,
   104,
   388,
   216,
   1249,
   485,
   375,
   191,
   375,
   164,
   97,
   97,
   223,
   473,
   389,
   333,
   189,
   78,
   201,
   336,
   241,
   220,
   223,
   565,
   252,
   245,
   412,
   203,
   266,
   208,
   326,
   766,
   727,
   630,
   560,
   440,
   2383,
   868,
   836,
   1130,
   425,
   502,
   224,
   574,
   902,
   494,
   185,
   232,
   157,
   277
  ]
 },
 "SWE-bench Pro (V2, public)": {
  "benchmark": "SWE-bench Pro (V2, public)",
  "status": "ok",
  "stats": {
   "count": 642,
   "min": 194,
   "max": 5649,
   "mean": 840.766,
   "median": 707.0,
   "p25": 513.25,
   "p75": 1006.0,
   "p95": 1884.349999999999,
   "p99": 2640.230000000003,
   "pct_under_1024": 75.86,
   "pct_under_2048": 96.57,
   "pct_under_4096": 99.84,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   807,
   700,
   496,
   551,
   570,
   490,
   645,
   441,
   446,
   411,
   507,
   406,
   803,
   422,
   567,
   594,
   709,
   341,
   1872,
   1141,
   391,
   513,
   574,
   621,
   482,
   1250,
   656,
   404,
   721,
   762,
   566,
   662,
   701,
   723,
   1108,
   594,
   935,
   296,
   581,
   397,
   623,
   434,
   506,
   340,
   429,
   1934,
   761,
   1218,
   568,
   1044,
   450,
   651,
   1912,
   1162,
   416,
   916,
   570,
   5649,
   976,
   1527,
   475,
   567,
   343,
   526,
   692,
   848,
   1146,
   636,
   1176,
   505,
   1040,
   822,
   1205,
   1936,
   1468,
   321,
   350,
   533,
   459,
   603,
   739,
   280,
   588,
   1116,
   522,
   447,
   509,
   556,
   707,
   1118,
   525,
   768,
   595,
   745,
   2164,
   547,
   1069,
   637,
   1885,
   736,
   1022,
   1914,
   586,
   969,
   2328,
   663,
   1008,
   993,
   403,
   1098,
   1895,
   1183,
   1176,
   564,
   438,
   1232,
   264,
   1452,
   867,
   810,
   799,
   765,
   450,
   453,
   995,
   1275,
   541,
   757,
   529,
   535,
   477,
   1217,
   1479,
   472,
   364,
   430,
   941,
   870,
   773,
   532,
   1656,
   568,
   684,
   486,
   434,
   1553,
   312,
   972,
   742,
   468,
   1023,
   561,
   1532,
   1603,
   1285,
   2332,
   867,
   445,
   470,
   856,
   1130,
   1212,
   1166,
   489,
   703,
   819,
   511,
   581,
   592,
   291,
   831,
   2027,
   1196,
   659,
   787,
   1330,
   618,
   611,
   371,
   426,
   482,
   333,
   1441,
   792,
   552,
   415,
   894,
   2277,
   992,
   1156,
   836,
   733,
   548,
   1731,
   738,
   654,
   732,
   532,
   1378,
   1040,
   770,
   1003,
   518,
   911,
   380,
   1438,
   464,
   1995,
   874,
   360,
   717,
   222,
   554,
   832,
   336,
   594,
   474,
   798,
   541,
   655,
   798,
   763,
   925,
   515,
   419,
   857,
   2058,
   401,
   809,
   1070,
   1468,
   1399,
   588,
   415,
   676,
   345,
   840,
   1378,
   2089,
   858,
   1300,
   716,
   1272,
   1249,
   375,
   1075,
   1797,
   1113,
   1132,
   1783,
   641,
   918,
   670,
   1231,
   2185,
   638,
   701,
   306,
   1166,
   1195,
   879,
   610,
   707,
   675,
   621,
   899,
   1700,
   727,
   1450,
   2944,
   1085,
   789,
   1112,
   638,
   194,
   1187,
   1316,
   411,
   1025,
   297,
   485,
   568,
   437,
   717,
   1370,
   310,
   505,
   423,
   331,
   1583,
   430,
   1888,
   1103,
   644,
   574,
   490,
   1322,
   851,
   707,
   422,
   954,
   420,
   2528,
   700,
   562,
   1087,
   404,
   401,
   2241,
   676,
   354,
   483,
   480,
   632,
   485,
   617,
   1256,
   2680,
   237,
   460,
   786,
   1742,
   496,
   654,
   737,
   801,
   730,
   457,
   870,
   732,
   488,
   658,
   1120,
   569,
   568,
   1586,
   1576,
   2724,
   795,
   740,
   1826,
   503,
   444,
   3488,
   578,
   526,
   528,
   873,
   502,
   361,
   477,
   795,
   715,
   422,
   288,
   454,
   471,
   1080,
   656,
   1854,
   417,
   1051,
   539,
   1165,
   445,
   2768,
   1183,
   264,
   885,
   708,
   783,
   783,
   1489,
   1895,
   555,
   1221,
   915,
   595,
   528,
   1081,
   2171,
   892,
   855,
   870,
   588,
   602,
   699,
   1095,
   1396,
   383,
   321,
   719,
   1280,
   2093,
   537,
   408,
   854,
   788,
   297,
   514,
   534,
   509,
   673,
   525,
   836,
   401,
   830,
   1186,
   888,
   740,
   464,
   3205,
   476,
   869,
   776,
   462,
   497,
   1250,
   607,
   918,
   1375,
   1267,
   2583,
   826,
   656,
   531,
   1308,
   624,
   667,
   496,
   1320,
   710,
   760,
   671,
   1052,
   433,
   2447,
   765,
   499,
   374,
   1251,
   418,
   523,
   756,
   989,
   840,
   575,
   625,
   731,
   1233,
   767,
   290,
   620,
   975,
   1068,
   913,
   500,
   371,
   773,
   668,
   313,
   660,
   1261,
   1016,
   592,
   723,
   554,
   481,
   1421,
   527,
   515,
   604,
   680,
   591,
   1033,
   790,
   781,
   870,
   575,
   641,
   849,
   740,
   567,
   719,
   904,
   920,
   589,
   1609,
   814,
   845,
   472,
   1500,
   622,
   569,
   637,
   996,
   489,
   927,
   584,
   414,
   828,
   444,
   525,
   857,
   774,
   1458,
   455,
   438,
   1100,
   911,
   762,
   699,
   267,
   957,
   423,
   485,
   467,
   724,
   1055,
   964,
   1446,
   456,
   269,
   349,
   812,
   730,
   899,
   813,
   1576,
   1373,
   2061,
   2052,
   465,
   596,
   1353,
   519,
   971,
   698,
   624,
   980,
   445,
   372,
   762,
   547,
   784,
   864,
   369,
   405,
   773,
   572,
   827,
   1036,
   392,
   719,
   542,
   662,
   963,
   871,
   1893,
   1211,
   632,
   964,
   591,
   526,
   601,
   481,
   256,
   575,
   332,
   915,
   1339,
   899,
   830,
   604,
   386,
   496,
   487,
   808,
   1162,
   531,
   453,
   528,
   1809,
   771,
   1767,
   481,
   565,
   535,
   1401,
   847,
   374,
   434,
   506,
   1193,
   357,
   501,
   1007,
   550,
   486,
   1163,
   310,
   757,
   942,
   597,
   493,
   652,
   661,
   771,
   744,
   358,
   957,
   666,
   676,
   540,
   729,
   577,
   994,
   791,
   689,
   541,
   1571,
   1387,
   589,
   1007,
   639,
   515,
   454,
   1378,
   959,
   686,
   403,
   1179,
   967,
   597,
   1001,
   273,
   769,
   657,
   1390,
   388,
   1329,
   1337
  ]
 },
 "SWE-bench Pro (V2, problem_statement only)": {
  "benchmark": "SWE-bench Pro (V2, problem_statement only)",
  "status": "ok",
  "stats": {
   "count": 642,
   "min": 34,
   "max": 2432,
   "mean": 200.963,
   "median": 182.0,
   "p25": 117.0,
   "p75": 253.0,
   "p95": 371.8499999999998,
   "p99": 567.4200000000012,
   "pct_under_1024": 99.53,
   "pct_under_2048": 99.84,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   79,
   50,
   208,
   84,
   211,
   155,
   196,
   182,
   44,
   186,
   155,
   135,
   302,
   99,
   228,
   282,
   117,
   148,
   121,
   465,
   181,
   76,
   128,
   39,
   259,
   120,
   111,
   166,
   232,
   122,
   306,
   53,
   191,
   276,
   149,
   96,
   98,
   133,
   306,
   98,
   89,
   67,
   160,
   94,
   196,
   222,
   88,
   539,
   292,
   498,
   99,
   308,
   57,
   341,
   48,
   638,
   239,
   226,
   273,
   212,
   110,
   236,
   108,
   292,
   218,
   307,
   297,
   368,
   280,
   78,
   274,
   284,
   512,
   65,
   216,
   113,
   63,
   110,
   169,
   58,
   153,
   72,
   220,
   526,
   89,
   183,
   308,
   179,
   360,
   222,
   136,
   363,
   215,
   168,
   137,
   232,
   165,
   226,
   112,
   248,
   124,
   100,
   282,
   355,
   148,
   248,
   230,
   46,
   155,
   655,
   1462,
   481,
   536,
   54,
   126,
   356,
   112,
   215,
   248,
   385,
   117,
   116,
   89,
   151,
   303,
   290,
   273,
   193,
   82,
   109,
   193,
   348,
   158,
   132,
   85,
   97,
   163,
   49,
   135,
   112,
   139,
   215,
   304,
   194,
   86,
   78,
   102,
   188,
   406,
   122,
   122,
   80,
   196,
   204,
   266,
   96,
   285,
   75,
   190,
   244,
   53,
   300,
   162,
   178,
   175,
   254,
   166,
   162,
   320,
   89,
   321,
   55,
   212,
   153,
   285,
   78,
   179,
   311,
   113,
   195,
   204,
   60,
   433,
   107,
   247,
   121,
   353,
   156,
   251,
   246,
   287,
   277,
   112,
   79,
   267,
   335,
   294,
   221,
   87,
   340,
   446,
   119,
   55,
   281,
   88,
   589,
   80,
   111,
   101,
   146,
   378,
   62,
   306,
   116,
   109,
   253,
   183,
   136,
   228,
   155,
   250,
   267,
   242,
   341,
   211,
   255,
   85,
   84,
   68,
   150,
   115,
   141,
   187,
   178,
   52,
   175,
   234,
   150,
   126,
   244,
   223,
   193,
   242,
   48,
   142,
   355,
   197,
   48,
   154,
   164,
   215,
   115,
   151,
   289,
   91,
   278,
   403,
   112,
   239,
   361,
   217,
   83,
   305,
   111,
   186,
   190,
   1096,
   141,
   83,
   150,
   286,
   132,
   308,
   52,
   44,
   348,
   162,
   189,
   545,
   132,
   184,
   276,
   165,
   300,
   35,
   142,
   107,
   87,
   154,
   335,
   242,
   471,
   428,
   197,
   235,
   280,
   41,
   293,
   266,
   214,
   151,
   196,
   203,
   234,
   210,
   80,
   52,
   144,
   251,
   361,
   135,
   118,
   142,
   282,
   193,
   311,
   331,
   152,
   53,
   194,
   261,
   60,
   224,
   284,
   217,
   253,
   180,
   210,
   208,
   289,
   233,
   235,
   80,
   244,
   281,
   125,
   141,
   2432,
   131,
   239,
   57,
   138,
   76,
   167,
   149,
   85,
   132,
   58,
   136,
   59,
   99,
   237,
   203,
   224,
   60,
   60,
   86,
   300,
   67,
   124,
   48,
   388,
   220,
   290,
   146,
   87,
   346,
   75,
   77,
   208,
   250,
   163,
   162,
   159,
   37,
   153,
   205,
   198,
   110,
   94,
   167,
   161,
   165,
   163,
   192,
   327,
   350,
   280,
   267,
   134,
   105,
   236,
   103,
   89,
   63,
   109,
   107,
   203,
   66,
   254,
   200,
   174,
   197,
   127,
   216,
   172,
   253,
   157,
   291,
   72,
   158,
   140,
   188,
   34,
   268,
   131,
   159,
   192,
   202,
   104,
   285,
   112,
   128,
   412,
   209,
   165,
   113,
   95,
   182,
   216,
   130,
   201,
   245,
   56,
   273,
   240,
   307,
   288,
   213,
   99,
   169,
   163,
   178,
   152,
   526,
   109,
   203,
   213,
   151,
   94,
   59,
   170,
   163,
   182,
   123,
   249,
   222,
   179,
   260,
   178,
   178,
   229,
   583,
   512,
   149,
   47,
   142,
   178,
   141,
   225,
   67,
   146,
   117,
   193,
   167,
   179,
   74,
   50,
   274,
   195,
   276,
   150,
   265,
   70,
   56,
   339,
   125,
   242,
   367,
   275,
   130,
   299,
   262,
   147,
   195,
   113,
   183,
   108,
   277,
   134,
   303,
   220,
   192,
   342,
   199,
   80,
   228,
   125,
   411,
   136,
   420,
   315,
   95,
   86,
   121,
   145,
   185,
   203,
   86,
   175,
   57,
   162,
   109,
   195,
   312,
   268,
   221,
   249,
   63,
   142,
   111,
   62,
   184,
   206,
   98,
   185,
   419,
   308,
   212,
   261,
   226,
   114,
   192,
   254,
   123,
   226,
   195,
   103,
   288,
   301,
   340,
   121,
   80,
   85,
   147,
   247,
   175,
   234,
   79,
   134,
   253,
   346,
   177,
   286,
   206,
   193,
   132,
   332,
   84,
   372,
   124,
   186,
   171,
   210,
   171,
   130,
   119,
   132,
   189,
   294,
   73,
   175,
   255,
   210,
   281,
   209,
   208,
   217,
   175,
   155,
   195,
   112,
   211,
   349,
   183,
   160,
   327,
   268,
   163,
   369,
   94,
   217,
   282,
   231,
   203,
   261,
   228,
   289,
   306,
   160,
   234,
   97,
   169,
   245,
   200,
   75,
   331,
   284,
   314,
   90,
   210,
   432,
   260,
   83,
   239,
   165,
   169,
   161,
   235,
   270,
   98,
   120,
   269,
   119,
   237,
   81,
   405,
   225,
   100,
   182,
   100,
   174
  ]
 },
 "Multi-SWE-bench": {
  "benchmark": "Multi-SWE-bench",
  "status": "ok",
  "stats": {
   "count": 1632,
   "min": 15,
   "max": 11400,
   "mean": 489.915,
   "median": 306.5,
   "p25": 174.0,
   "p75": 558.5,
   "p95": 1458.0,
   "p99": 3188.900000000006,
   "pct_under_1024": 91.79,
   "pct_under_2048": 97.37,
   "pct_under_4096": 99.45,
   "pct_under_8192": 99.82,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   416,
   61,
   253,
   399,
   273,
   865,
   501,
   296,
   106,
   118,
   118,
   102,
   35,
   257,
   79,
   203,
   74,
   744,
   4147,
   364,
   253,
   547,
   80,
   111,
   1019,
   200,
   321,
   624,
   317,
   419,
   273,
   161,
   361,
   164,
   1678,
   180,
   84,
   151,
   506,
   176,
   211,
   773,
   237,
   120,
   555,
   193,
   830,
   451,
   187,
   574,
   94,
   1559,
   131,
   250,
   951,
   1380,
   651,
   405,
   58,
   686,
   1047,
   324,
   258,
   63,
   713,
   194,
   127,
   720,
   799,
   130,
   394,
   164,
   239,
   120,
   548,
   74,
   3002,
   592,
   287,
   117,
   917,
   455,
   125,
   345,
   772,
   178,
   166,
   71,
   40,
   141,
   47,
   101,
   145,
   787,
   163,
   673,
   176,
   835,
   696,
   51,
   413,
   121,
   1174,
   265,
   530,
   304,
   708,
   806,
   65,
   368,
   580,
   301,
   688,
   57,
   84,
   274,
   49,
   224,
   136,
   58,
   142,
   80,
   82,
   159,
   139,
   153,
   201,
   316,
   206,
   745,
   199,
   257,
   124,
   627,
   212,
   479,
   182,
   319,
   197,
   263,
   644,
   506,
   108,
   192,
   111,
   111,
   152,
   101,
   236,
   99,
   323,
   1748,
   184,
   932,
   169,
   139,
   174,
   814,
   42,
   312,
   331,
   255,
   106,
   1173,
   114,
   70,
   1116,
   174,
   139,
   352,
   139,
   141,
   235,
   126,
   67,
   97,
   104,
   549,
   121,
   53,
   1730,
   565,
   345,
   661,
   241,
   255,
   281,
   311,
   489,
   2302,
   184,
   434,
   599,
   441,
   1716,
   303,
   7947,
   602,
   72,
   10578,
   533,
   395,
   110,
   247,
   625,
   946,
   282,
   474,
   736,
   292,
   596,
   172,
   274,
   79,
   1146,
   647,
   682,
   154,
   964,
   1971,
   90,
   539,
   771,
   212,
   355,
   303,
   493,
   540,
   256,
   584,
   238,
   191,
   145,
   86,
   57,
   165,
   349,
   308,
   214,
   326,
   428,
   1455,
   15,
   340,
   295,
   38,
   231,
   93,
   318,
   174,
   272,
   148,
   229,
   173,
   502,
   57,
   223,
   1491,
   279,
   392,
   1035,
   331,
   223,
   627,
   673,
   869,
   253,
   230,
   1493,
   748,
   321,
   321,
   407,
   317,
   101,
   802,
   466,
   117,
   391,
   348,
   300,
   432,
   200,
   400,
   443,
   1827,
   252,
   248,
   412,
   226,
   342,
   230,
   252,
   433,
   272,
   211,
   401,
   665,
   504,
   781,
   331,
   251,
   252,
   322,
   224,
   240,
   128,
   204,
   219,
   216,
   98,
   90,
   578,
   404,
   141,
   75,
   266,
   896,
   2266,
   118,
   469,
   208,
   365,
   90,
   291,
   291,
   115,
   341,
   222,
   8500,
   123,
   76,
   363,
   325,
   308,
   212,
   271,
   229,
   75,
   171,
   402,
   426,
   164,
   148,
   166,
   240,
   114,
   69,
   260,
   268,
   208,
   171,
   377,
   277,
   178,
   349,
   89,
   261,
   193,
   116,
   338,
   333,
   468,
   74,
   265,
   55,
   195,
   260,
   311,
   408,
   175,
   161,
   113,
   168,
   554,
   386,
   202,
   240,
   746,
   96,
   143,
   160,
   721,
   278,
   92,
   79,
   221,
   486,
   191,
   811,
   152,
   264,
   184,
   195,
   108,
   120,
   407,
   451,
   1375,
   79,
   154,
   2712,
   79,
   96,
   167,
   168,
   290,
   78,
   277,
   503,
   135,
   76,
   472,
   291,
   265,
   285,
   138,
   156,
   234,
   206,
   111,
   115,
   201,
   213,
   294,
   149,
   359,
   277,
   49,
   233,
   183,
   527,
   221,
   446,
   392,
   428,
   144,
   384,
   80,
   56,
   1122,
   147,
   147,
   73,
   101,
   434,
   250,
   287,
   282,
   307,
   209,
   330,
   273,
   108,
   84,
   158,
   116,
   386,
   227,
   506,
   237,
   269,
   113,
   64,
   22,
   323,
   353,
   3352,
   411,
   154,
   237,
   354,
   360,
   313,
   174,
   170,
   668,
   116,
   395,
   344,
   312,
   429,
   637,
   238,
   143,
   357,
   142,
   37,
   37,
   471,
   421,
   421,
   124,
   257,
   135,
   300,
   121,
   125,
   96,
   259,
   516,
   284,
   177,
   138,
   272,
   457,
   85,
   72,
   140,
   476,
   169,
   239,
   198,
   140,
   141,
   125,
   91,
   203,
   526,
   327,
   258,
   122,
   315,
   177,
   195,
   49,
   49,
   593,
   226,
   55,
   55,
   142,
   142,
   270,
   281,
   47,
   242,
   254,
   430,
   211,
   392,
   1728,
   97,
   168,
   345,
   49,
   68,
   168,
   79,
   248,
   204,
   53,
   219,
   226,
   57,
   380,
   333,
   201,
   261,
   175,
   152,
   145,
   125,
   142,
   171,
   113,
   111,
   106,
   95,
   125,
   179,
   178,
   201,
   142,
   126,
   102,
   142,
   250,
   138,
   134,
   31,
   249,
   356,
   219,
   67,
   178,
   86,
   400,
   500,
   138,
   52,
   60,
   88,
   27,
   1728,
   131,
   177,
   779,
   143,
   123,
   303,
   116,
   97,
   86,
   232,
   248,
   174,
   174,
   131,
   42,
   145,
   55,
   195,
   287,
   22,
   244,
   129,
   26,
   144,
   233,
   91,
   324,
   140,
   59,
   149,
   318,
   164,
   225,
   238,
   406,
   147,
   200,
   29,
   263,
   519,
   267,
   81,
   103,
   274,
   148,
   113,
   105,
   78,
   89,
   527,
   570,
   386,
   184,
   1538,
   941,
   120,
   120,
   259,
   53,
   92,
   484,
   24,
   1006,
   392,
   93,
   378,
   75,
   317,
   91,
   290,
   110,
   51,
   27,
   59,
   396,
   157,
   218,
   46,
   142,
   803,
   54,
   231,
   90,
   44,
   189,
   154,
   344,
   33,
   142,
   64,
   74,
   787,
   601,
   303,
   823,
   54,
   1317,
   394,
   252,
   1458,
   1458,
   1458,
   1458,
   11400,
   1019,
   1019,
   1019,
   185,
   473,
   2703,
   473,
   563,
   329,
   329,
   151,
   151,
   2612,
   2612,
   2316,
   2316,
   1103,
   1103,
   2316,
   2316,
   2316,
   554,
   134,
   69,
   318,
   69,
   114,
   282,
   282,
   300,
   282,
   300,
   3777,
   231,
   88,
   132,
   83,
   461,
   125,
   80,
   100,
   306,
   184,
   529,
   744,
   196,
   129,
   601,
   148,
   109,
   198,
   589,
   208,
   119,
   510,
   678,
   278,
   415,
   206,
   782,
   93,
   604,
   1040,
   637,
   840,
   290,
   823,
   715,
   393,
   879,
   184,
   538,
   141,
   77,
   1216,
   296,
   548,
   650,
   239,
   171,
   476,
   758,
   539,
   285,
   174,
   381,
   308,
   219,
   455,
   941,
   396,
   704,
   691,
   1739,
   198,
   453,
   341,
   194,
   288,
   344,
   95,
   252,
   209,
   243,
   287,
   303,
   1913,
   1997,
   596,
   134,
   570,
   358,
   87,
   269,
   635,
   76,
   183,
   119,
   465,
   119,
   271,
   572,
   360,
   360,
   103,
   117,
   213,
   246,
   167,
   147,
   1233,
   107,
   19,
   24,
   632,
   472,
   84,
   560,
   89,
   315,
   136,
   128,
   655,
   254,
   655,
   126,
   103,
   405,
   320,
   338,
   323,
   266,
   129,
   171,
   206,
   307,
   41,
   374,
   20,
   171,
   266,
   284,
   208,
   276,
   75,
   175,
   293,
   377,
   218,
   83,
   223,
   123,
   661,
   134,
   238,
   104,
   359,
   121,
   156,
   147,
   238,
   179,
   143,
   496,
   672,
   105,
   343,
   28,
   520,
   227,
   343,
   983,
   983,
   368,
   149,
   61,
   113,
   260,
   590,
   421,
   280,
   243,
   497,
   205,
   204,
   454,
   151,
   741,
   156,
   175,
   367,
   315,
   681,
   179,
   359,
   388,
   280,
   414,
   564,
   997,
   356,
   490,
   282,
   274,
   247,
   722,
   280,
   719,
   271,
   505,
   322,
   235,
   174,
   335,
   2351,
   628,
   1802,
   998,
   739,
   1018,
   295,
   370,
   235,
   403,
   438,
   330,
   248,
   363,
   477,
   496,
   962,
   66,
   308,
   1233,
   359,
   711,
   405,
   641,
   434,
   274,
   664,
   250,
   306,
   68,
   508,
   336,
   556,
   488,
   481,
   524,
   1019,
   623,
   118,
   424,
   347,
   818,
   680,
   139,
   291,
   320,
   66,
   380,
   3856,
   442,
   282,
   141,
   440,
   314,
   546,
   438,
   394,
   1043,
   388,
   993,
   968,
   237,
   414,
   544,
   627,
   847,
   311,
   885,
   447,
   585,
   518,
   298,
   545,
   71,
   503,
   452,
   110,
   791,
   505,
   608,
   558,
   1356,
   407,
   535,
   231,
   454,
   907,
   303,
   442,
   179,
   266,
   1887,
   179,
   676,
   1086,
   497,
   287,
   2265,
   181,
   714,
   153,
   153,
   894,
   134,
   548,
   532,
   757,
   385,
   496,
   888,
   663,
   569,
   1122,
   277,
   714,
   393,
   247,
   273,
   246,
   204,
   211,
   896,
   228,
   303,
   531,
   1407,
   697,
   4111,
   656,
   482,
   415,
   296,
   674,
   502,
   378,
   369,
   104,
   848,
   580,
   714,
   1294,
   528,
   366,
   202,
   726,
   263,
   483,
   452,
   339,
   329,
   148,
   261,
   192,
   471,
   336,
   1328,
   729,
   354,
   649,
   1579,
   2704,
   507,
   251,
   917,
   402,
   502,
   898,
   840,
   143,
   2116,
   1038,
   1850,
   668,
   484,
   532,
   230,
   624,
   1005,
   288,
   491,
   205,
   1139,
   515,
   90,
   750,
   325,
   682,
   359,
   529,
   753,
   509,
   445,
   636,
   637,
   183,
   193,
   465,
   359,
   513,
   1235,
   188,
   358,
   916,
   276,
   605,
   350,
   830,
   538,
   298,
   2094,
   447,
   177,
   507,
   695,
   138,
   257,
   338,
   925,
   327,
   317,
   301,
   323,
   1792,
   510,
   700,
   725,
   711,
   231,
   466,
   382,
   230,
   233,
   766,
   381,
   282,
   326,
   582,
   40,
   523,
   422,
   1231,
   1327,
   236,
   526,
   912,
   124,
   194,
   60,
   327,
   595,
   5351,
   1625,
   893,
   2720,
   3032,
   4813,
   5484,
   365,
   1189,
   470,
   614,
   969,
   724,
   895,
   523,
   439,
   153,
   620,
   2611,
   636,
   1672,
   189,
   620,
   204,
   165,
   447,
   216,
   2023,
   264,
   210,
   240,
   68,
   122,
   111,
   287,
   899,
   3376,
   3376,
   244,
   136,
   769,
   341,
   46,
   600,
   3363,
   204,
   469,
   205,
   159,
   215,
   489,
   1898,
   567,
   745,
   679,
   268,
   322,
   153,
   818,
   302,
   266,
   3223,
   966,
   344,
   3113,
   571,
   486,
   1282,
   300,
   153,
   366,
   623,
   455,
   340,
   448,
   699,
   767,
   891,
   381,
   1571,
   2016,
   256,
   260,
   815,
   237,
   1084,
   333,
   203,
   279,
   491,
   1097,
   404,
   68,
   252,
   230,
   1510,
   1518,
   469,
   566,
   608,
   720,
   227,
   205,
   1036,
   123,
   1651,
   159,
   557,
   227,
   3825,
   2266,
   1117,
   643,
   291,
   2619,
   1541,
   1486,
   354,
   177,
   65,
   2043,
   1492,
   279,
   180,
   636,
   144,
   121,
   295,
   498,
   141,
   260,
   301,
   468,
   2112,
   343,
   238,
   342,
   114,
   452,
   234,
   430,
   820,
   344,
   820,
   1507,
   1507,
   128,
   153,
   227,
   78,
   851,
   348,
   266,
   1725,
   131,
   752,
   174,
   568,
   198,
   823,
   330,
   376,
   265,
   133,
   226,
   91,
   87,
   41,
   205,
   41,
   54,
   84,
   41,
   205,
   300,
   76,
   119,
   190,
   190,
   311,
   321,
   201,
   382,
   267,
   177,
   962,
   209,
   577,
   220,
   164,
   343,
   643,
   1021,
   298,
   152,
   950,
   357,
   282,
   426,
   533,
   243,
   303,
   2673,
   1201,
   303,
   303,
   540,
   209,
   262,
   445,
   645,
   445,
   151,
   103,
   1319,
   512,
   492,
   527,
   619,
   424,
   424,
   527,
   101,
   494,
   298,
   915,
   439,
   773,
   104,
   216,
   589,
   175,
   278,
   278,
   404,
   481,
   253,
   847,
   398,
   207,
   333,
   845,
   346,
   912,
   181,
   195,
   105,
   356,
   360,
   357,
   155,
   298,
   151,
   195,
   568,
   232,
   751,
   268,
   464,
   754,
   587,
   938,
   126,
   470,
   1168,
   132,
   208,
   242,
   834,
   328,
   379,
   656,
   856,
   162,
   237,
   247,
   147,
   331,
   1118,
   367,
   1296,
   259,
   224,
   728,
   541,
   656,
   1136,
   242,
   791,
   626,
   529,
   707,
   237,
   335,
   64,
   162,
   81,
   184,
   184,
   273,
   709,
   89,
   257,
   615,
   86,
   186,
   650,
   596,
   1010,
   264,
   155,
   1130,
   162,
   1058,
   162,
   259,
   776,
   266,
   187,
   37,
   358,
   147,
   311,
   160,
   356,
   649,
   133,
   632,
   491,
   410,
   630,
   1094,
   263,
   382,
   794,
   774,
   522,
   251,
   316,
   545,
   363,
   397,
   409,
   688,
   515,
   770,
   233,
   1199,
   609,
   479,
   371,
   509,
   463,
   393,
   100,
   211,
   710,
   437,
   157,
   862,
   248,
   324,
   890,
   175,
   265,
   237,
   859,
   524,
   736,
   384,
   688,
   111,
   317,
   574,
   1887,
   870,
   334,
   443,
   208,
   135,
   429,
   550,
   968,
   525,
   507,
   507,
   705,
   259,
   871,
   269,
   193,
   886,
   148,
   229,
   747,
   237,
   525,
   475,
   459,
   389,
   254,
   871,
   602,
   587,
   2173,
   661,
   1336,
   669,
   255,
   673,
   984,
   318,
   1149,
   537,
   550,
   424,
   812,
   717,
   575,
   672,
   465,
   929,
   668,
   588,
   608,
   623,
   532,
   420,
   943,
   889,
   219,
   299,
   522,
   1050,
   253,
   400,
   517,
   614,
   498,
   636,
   166,
   1204,
   775,
   238,
   1345,
   394,
   638,
   437,
   341
  ]
 },
 "SWE-PolyBench": {
  "benchmark": "SWE-PolyBench",
  "status": "ok",
  "stats": {
   "count": 2110,
   "min": 7,
   "max": 16222,
   "mean": 452.066,
   "median": 306.5,
   "p25": 158.0,
   "p75": 554.0,
   "p95": 1210.55,
   "p99": 2527.5999999999767,
   "pct_under_1024": 92.56,
   "pct_under_2048": 98.39,
   "pct_under_4096": 99.67,
   "pct_under_8192": 99.95,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   504,
   176,
   521,
   118,
   256,
   11,
   230,
   440,
   556,
   212,
   282,
   225,
   258,
   190,
   429,
   118,
   897,
   125,
   77,
   375,
   607,
   240,
   344,
   272,
   187,
   870,
   294,
   716,
   296,
   1108,
   183,
   210,
   1508,
   285,
   296,
   241,
   276,
   376,
   139,
   396,
   781,
   259,
   551,
   36,
   683,
   61,
   1095,
   319,
   1516,
   296,
   126,
   326,
   759,
   547,
   15,
   228,
   132,
   93,
   496,
   687,
   318,
   94,
   143,
   242,
   216,
   236,
   183,
   66,
   31,
   579,
   55,
   316,
   1169,
   179,
   586,
   120,
   116,
   3321,
   778,
   869,
   366,
   245,
   1317,
   1332,
   250,
   183,
   869,
   390,
   44,
   15,
   319,
   44,
   56,
   245,
   533,
   250,
   41,
   458,
   1064,
   237,
   1415,
   112,
   370,
   318,
   51,
   3186,
   54,
   384,
   554,
   574,
   473,
   169,
   554,
   65,
   94,
   548,
   563,
   1999,
   59,
   79,
   129,
   54,
   48,
   394,
   225,
   71,
   91,
   26,
   141,
   224,
   109,
   147,
   1830,
   437,
   102,
   3674,
   252,
   876,
   451,
   267,
   124,
   53,
   436,
   159,
   89,
   714,
   313,
   990,
   1155,
   112,
   1083,
   327,
   43,
   39,
   173,
   883,
   166,
   111,
   69,
   77,
   128,
   650,
   90,
   50,
   13,
   122,
   179,
   472,
   306,
   75,
   305,
   309,
   254,
   236,
   101,
   57,
   52,
   73,
   269,
   59,
   169,
   1486,
   179,
   438,
   175,
   56,
   77,
   44,
   43,
   99,
   120,
   225,
   196,
   323,
   558,
   195,
   218,
   280,
   236,
   522,
   124,
   62,
   164,
   98,
   165,
   1809,
   121,
   76,
   149,
   149,
   315,
   122,
   158,
   83,
   372,
   112,
   80,
   147,
   288,
   106,
   175,
   145,
   260,
   852,
   65,
   58,
   75,
   130,
   26,
   294,
   58,
   304,
   128,
   102,
   252,
   42,
   278,
   219,
   143,
   128,
   91,
   471,
   347,
   73,
   125,
   97,
   172,
   168,
   150,
   170,
   26,
   242,
   130,
   73,
   474,
   96,
   109,
   68,
   206,
   266,
   69,
   338,
   167,
   138,
   98,
   219,
   143,
   79,
   246,
   99,
   207,
   124,
   282,
   95,
   66,
   594,
   798,
   160,
   325,
   248,
   740,
   295,
   101,
   49,
   166,
   71,
   266,
   101,
   148,
   107,
   148,
   266,
   21,
   87,
   216,
   102,
   112,
   281,
   156,
   482,
   226,
   109,
   102,
   94,
   74,
   65,
   54,
   1140,
   246,
   336,
   200,
   101,
   209,
   172,
   224,
   224,
   336,
   278,
   105,
   230,
   160,
   107,
   128,
   200,
   73,
   232,
   115,
   324,
   339,
   179,
   142,
   196,
   194,
   224,
   296,
   212,
   315,
   156,
   846,
   194,
   252,
   102,
   399,
   208,
   183,
   642,
   216,
   249,
   98,
   82,
   77,
   516,
   186,
   331,
   76,
   189,
   85,
   187,
   68,
   75,
   95,
   192,
   100,
   115,
   102,
   66,
   323,
   76,
   75,
   114,
   55,
   338,
   77,
   69,
   69,
   244,
   52,
   63,
   349,
   81,
   63,
   87,
   142,
   56,
   65,
   89,
   126,
   188,
   34,
   1122,
   120,
   169,
   37,
   82,
   122,
   220,
   327,
   193,
   142,
   135,
   50,
   135,
   180,
   178,
   271,
   30,
   630,
   214,
   135,
   173,
   150,
   86,
   220,
   285,
   74,
   64,
   102,
   81,
   210,
   88,
   251,
   131,
   496,
   140,
   140,
   93,
   91,
   229,
   57,
   115,
   110,
   111,
   315,
   186,
   80,
   249,
   90,
   175,
   179,
   572,
   48,
   418,
   323,
   67,
   110,
   66,
   102,
   70,
   222,
   423,
   123,
   286,
   388,
   88,
   98,
   203,
   509,
   61,
   256,
   126,
   365,
   211,
   219,
   159,
   506,
   150,
   92,
   97,
   273,
   220,
   74,
   106,
   686,
   75,
   139,
   722,
   307,
   785,
   191,
   262,
   53,
   116,
   155,
   308,
   115,
   246,
   179,
   145,
   88,
   260,
   123,
   157,
   273,
   398,
   227,
   171,
   319,
   191,
   217,
   185,
   398,
   285,
   218,
   879,
   107,
   453,
   147,
   188,
   181,
   267,
   213,
   164,
   150,
   58,
   310,
   361,
   229,
   203,
   1896,
   135,
   328,
   171,
   290,
   280,
   194,
   445,
   281,
   138,
   252,
   345,
   329,
   220,
   300,
   230,
   337,
   246,
   260,
   715,
   48,
   211,
   98,
   125,
   179,
   190,
   124,
   516,
   265,
   158,
   618,
   204,
   832,
   306,
   190,
   632,
   501,
   237,
   190,
   304,
   239,
   382,
   116,
   49,
   414,
   389,
   522,
   87,
   142,
   186,
   396,
   122,
   227,
   723,
   303,
   127,
   99,
   167,
   206,
   168,
   708,
   641,
   417,
   273,
   230,
   156,
   632,
   755,
   128,
   216,
   309,
   651,
   393,
   408,
   370,
   515,
   79,
   280,
   230,
   109,
   723,
   110,
   606,
   337,
   37,
   103,
   238,
   378,
   20,
   412,
   142,
   153,
   555,
   253,
   171,
   343,
   245,
   331,
   221,
   527,
   186,
   192,
   549,
   152,
   221,
   116,
   251,
   146,
   121,
   1833,
   194,
   476,
   167,
   130,
   863,
   436,
   374,
   374,
   282,
   552,
   67,
   111,
   263,
   116,
   702,
   680,
   67,
   138,
   457,
   286,
   298,
   362,
   360,
   341,
   280,
   444,
   165,
   194,
   184,
   241,
   129,
   615,
   167,
   309,
   747,
   467,
   956,
   270,
   230,
   376,
   594,
   369,
   367,
   214,
   103,
   389,
   519,
   318,
   495,
   284,
   237,
   1050,
   409,
   963,
   47,
   1137,
   746,
   541,
   26,
   858,
   827,
   1488,
   716,
   666,
   396,
   636,
   335,
   766,
   541,
   2062,
   100,
   677,
   201,
   672,
   114,
   1010,
   1271,
   502,
   545,
   808,
   590,
   622,
   1130,
   107,
   315,
   575,
   892,
   653,
   469,
   521,
   505,
   298,
   676,
   351,
   985,
   69,
   565,
   636,
   1029,
   201,
   587,
   141,
   666,
   820,
   1823,
   462,
   668,
   682,
   622,
   1723,
   612,
   719,
   1704,
   574,
   623,
   840,
   921,
   418,
   610,
   871,
   743,
   704,
   523,
   1060,
   1025,
   1097,
   411,
   451,
   386,
   117,
   505,
   479,
   508,
   502,
   652,
   502,
   301,
   435,
   800,
   190,
   810,
   521,
   644,
   511,
   488,
   1218,
   57,
   1386,
   130,
   96,
   430,
   830,
   1479,
   237,
   496,
   448,
   942,
   583,
   470,
   619,
   608,
   419,
   477,
   131,
   842,
   364,
   383,
   516,
   782,
   1783,
   475,
   1478,
   462,
   492,
   159,
   463,
   150,
   138,
   413,
   444,
   526,
   963,
   499,
   764,
   530,
   251,
   201,
   140,
   80,
   37,
   314,
   264,
   118,
   569,
   193,
   199,
   334,
   445,
   372,
   1908,
   208,
   487,
   376,
   593,
   92,
   835,
   178,
   363,
   495,
   196,
   626,
   595,
   455,
   494,
   318,
   199,
   42,
   142,
   897,
   56,
   478,
   672,
   139,
   282,
   1211,
   99,
   1055,
   211,
   256,
   248,
   446,
   291,
   142,
   375,
   415,
   66,
   519,
   63,
   237,
   229,
   181,
   95,
   483,
   220,
   249,
   488,
   232,
   520,
   469,
   2002,
   1060,
   67,
   3007,
   179,
   230,
   189,
   6080,
   171,
   260,
   291,
   251,
   170,
   430,
   104,
   474,
   256,
   519,
   552,
   1853,
   117,
   482,
   464,
   535,
   240,
   295,
   506,
   307,
   545,
   222,
   294,
   229,
   187,
   164,
   461,
   833,
   376,
   1592,
   94,
   652,
   1107,
   516,
   161,
   278,
   278,
   1716,
   227,
   78,
   398,
   98,
   94,
   941,
   2317,
   821,
   1720,
   818,
   1324,
   1290,
   44,
   1116,
   5155,
   16222,
   533,
   319,
   304,
   184,
   529,
   197,
   589,
   470,
   208,
   86,
   343,
   255,
   162,
   183,
   1132,
   419,
   393,
   880,
   115,
   737,
   658,
   678,
   529,
   417,
   810,
   576,
   562,
   1144,
   164,
   219,
   364,
   1416,
   796,
   429,
   476,
   744,
   295,
   475,
   207,
   540,
   1564,
   556,
   1356,
   29,
   414,
   90,
   343,
   107,
   205,
   1132,
   255,
   229,
   254,
   797,
   108,
   303,
   242,
   677,
   475,
   406,
   1154,
   182,
   128,
   55,
   176,
   860,
   448,
   743,
   547,
   305,
   430,
   979,
   517,
   83,
   460,
   961,
   476,
   244,
   812,
   100,
   230,
   223,
   214,
   456,
   52,
   516,
   191,
   326,
   523,
   415,
   337,
   306,
   330,
   380,
   299,
   197,
   861,
   674,
   177,
   542,
   527,
   271,
   536,
   358,
   518,
   374,
   507,
   337,
   376,
   301,
   2382,
   194,
   161,
   1016,
   550,
   542,
   278,
   618,
   437,
   1759,
   426,
   3128,
   496,
   280,
   1903,
   475,
   399,
   113,
   1210,
   337,
   502,
   343,
   197,
   175,
   162,
   151,
   347,
   274,
   155,
   373,
   718,
   121,
   889,
   101,
   1122,
   219,
   182,
   557,
   2674,
   107,
   446,
   161,
   355,
   153,
   267,
   328,
   221,
   1354,
   132,
   80,
   107,
   277,
   572,
   208,
   151,
   61,
   298,
   61,
   132,
   767,
   1999,
   438,
   344,
   147,
   371,
   762,
   250,
   452,
   104,
   273,
   132,
   488,
   157,
   592,
   344,
   83,
   286,
   335,
   487,
   1200,
   114,
   41,
   48,
   1119,
   998,
   830,
   822,
   564,
   167,
   86,
   2112,
   584,
   548,
   104,
   112,
   378,
   913,
   781,
   449,
   81,
   117,
   63,
   1143,
   432,
   472,
   401,
   312,
   566,
   279,
   584,
   80,
   726,
   76,
   112,
   81,
   825,
   562,
   460,
   305,
   300,
   213,
   222,
   372,
   87,
   141,
   102,
   411,
   189,
   488,
   79,
   495,
   111,
   619,
   649,
   370,
   461,
   1332,
   76,
   189,
   159,
   159,
   349,
   632,
   323,
   291,
   462,
   378,
   518,
   380,
   549,
   358,
   722,
   292,
   381,
   302,
   822,
   92,
   206,
   444,
   232,
   908,
   1694,
   884,
   314,
   121,
   478,
   819,
   135,
   22,
   836,
   318,
   246,
   224,
   765,
   302,
   44,
   86,
   10,
   1100,
   1465,
   1304,
   810,
   324,
   310,
   1282,
   1246,
   577,
   475,
   717,
   77,
   115,
   45,
   60,
   1613,
   160,
   14,
   166,
   4246,
   1304,
   162,
   193,
   129,
   178,
   1086,
   58,
   86,
   193,
   519,
   206,
   109,
   109,
   147,
   403,
   107,
   77,
   178,
   500,
   473,
   117,
   60,
   340,
   135,
   108,
   514,
   210,
   72,
   975,
   330,
   188,
   100,
   161,
   194,
   90,
   273,
   10,
   86,
   62,
   424,
   66,
   162,
   896,
   90,
   273,
   104,
   474,
   75,
   1323,
   333,
   478,
   90,
   73,
   70,
   149,
   428,
   551,
   71,
   155,
   606,
   864,
   69,
   493,
   165,
   898,
   134,
   121,
   442,
   950,
   2186,
   7,
   618,
   1747,
   497,
   186,
   78,
   439,
   40,
   76,
   587,
   80,
   352,
   127,
   632,
   402,
   597,
   1120,
   492,
   116,
   89,
   102,
   134,
   268,
   421,
   288,
   96,
   2752,
   2752,
   685,
   579,
   627,
   627,
   1539,
   1365,
   847,
   325,
   51,
   782,
   500,
   174,
   554,
   493,
   55,
   35,
   289,
   211,
   512,
   75,
   4190,
   537,
   227,
   65,
   82,
   35,
   263,
   260,
   56,
   140,
   57,
   127,
   84,
   24,
   177,
   151,
   363,
   463,
   640,
   326,
   151,
   47,
   666,
   772,
   154,
   278,
   221,
   646,
   622,
   641,
   182,
   129,
   271,
   413,
   97,
   406,
   267,
   289,
   175,
   288,
   431,
   288,
   323,
   143,
   467,
   331,
   96,
   432,
   354,
   439,
   195,
   288,
   376,
   193,
   641,
   211,
   397,
   266,
   107,
   134,
   173,
   538,
   91,
   142,
   350,
   202,
   178,
   375,
   429,
   478,
   574,
   576,
   474,
   587,
   203,
   408,
   116,
   565,
   480,
   330,
   1184,
   486,
   270,
   59,
   623,
   225,
   869,
   469,
   473,
   104,
   488,
   617,
   306,
   829,
   267,
   237,
   275,
   800,
   424,
   170,
   100,
   548,
   245,
   251,
   306,
   571,
   116,
   381,
   259,
   80,
   278,
   610,
   2371,
   255,
   180,
   528,
   347,
   353,
   301,
   345,
   87,
   790,
   665,
   665,
   450,
   114,
   687,
   736,
   967,
   233,
   158,
   575,
   622,
   494,
   516,
   474,
   521,
   537,
   679,
   200,
   560,
   479,
   14,
   202,
   420,
   498,
   257,
   614,
   576,
   657,
   539,
   562,
   327,
   561,
   427,
   491,
   399,
   250,
   50,
   791,
   326,
   1212,
   240,
   631,
   326,
   725,
   78,
   245,
   431,
   590,
   101,
   545,
   347,
   40,
   586,
   106,
   229,
   271,
   431,
   170,
   228,
   279,
   667,
   573,
   598,
   345,
   539,
   492,
   646,
   154,
   816,
   89,
   575,
   251,
   390,
   998,
   254,
   265,
   609,
   61,
   197,
   258,
   591,
   291,
   306,
   344,
   273,
   320,
   316,
   191,
   413,
   827,
   101,
   432,
   211,
   156,
   739,
   480,
   462,
   95,
   546,
   529,
   151,
   349,
   1064,
   360,
   302,
   855,
   350,
   177,
   50,
   558,
   242,
   425,
   404,
   624,
   591,
   313,
   253,
   1284,
   261,
   44,
   69,
   1466,
   200,
   1240,
   940,
   402,
   843,
   133,
   443,
   729,
   187,
   612,
   72,
   560,
   280,
   336,
   126,
   787,
   551,
   778,
   586,
   310,
   209,
   532,
   245,
   85,
   287,
   277,
   108,
   417,
   203,
   426,
   440,
   541,
   392,
   246,
   197,
   151,
   612,
   645,
   388,
   112,
   695,
   478,
   825,
   777,
   229,
   183,
   476,
   570,
   485,
   369,
   275,
   349,
   552,
   63,
   229,
   674,
   421,
   221,
   354,
   388,
   576,
   181,
   630,
   407,
   945,
   123,
   309,
   433,
   331,
   736,
   191,
   374,
   179,
   590,
   319,
   74,
   792,
   543,
   345,
   471,
   546,
   545,
   620,
   204,
   390,
   248,
   460,
   476,
   525,
   238,
   1027,
   748,
   314,
   143,
   230,
   149,
   887,
   70,
   193,
   643,
   561,
   270,
   264,
   872,
   260,
   507,
   833,
   192,
   526,
   84,
   430,
   135,
   114,
   209,
   444,
   160,
   270,
   96,
   262,
   871,
   530,
   1887,
   575,
   317,
   112,
   286,
   672,
   737,
   525,
   860,
   238,
   151,
   266,
   419,
   175,
   891,
   325,
   249,
   767,
   799,
   303,
   265,
   298,
   173,
   432,
   423,
   199,
   74,
   257,
   314,
   199,
   725,
   446,
   440,
   40,
   703,
   594,
   332,
   1014,
   414,
   1062,
   763,
   871,
   101,
   696,
   464,
   510,
   371,
   479,
   234,
   515,
   364,
   546,
   391,
   251,
   443,
   790,
   523,
   775,
   675,
   1095,
   631,
   743,
   633,
   430,
   358,
   455,
   187,
   538,
   1118,
   931,
   260,
   162,
   1059,
   162,
   1131,
   155,
   264,
   1011,
   651,
   929,
   842,
   981,
   86,
   616,
   257,
   710,
   274,
   184,
   81,
   336,
   238,
   708,
   524,
   530,
   627,
   792,
   1169,
   225,
   363,
   1297,
   368,
   1118,
   331,
   148,
   857,
   657,
   379,
   328,
   835,
   242,
   209,
   1169,
   126,
   755,
   1163,
   465,
   232,
   569,
   226,
   195,
   157,
   275,
   298,
   198,
   594,
   360,
   433,
   356,
   105,
   182,
   346,
   605,
   846,
   333,
   847,
   63,
   405,
   175,
   590,
   104,
   773,
   761,
   795,
   226,
   329,
   2542,
   567,
   968,
   78,
   204,
   100,
   145,
   74,
   141,
   104,
   110,
   234,
   175,
   48,
   81,
   126,
   232,
   181,
   360,
   169,
   57,
   147,
   387,
   691,
   578,
   60,
   60,
   446,
   193,
   60,
   102,
   81,
   127,
   312,
   393,
   194,
   4058,
   442,
   636,
   457,
   565,
   299,
   1370,
   81,
   693,
   625,
   848,
   198,
   225,
   390,
   979,
   3140,
   300,
   1620,
   1114,
   92,
   291,
   138,
   658,
   188,
   1068,
   180,
   114,
   1960,
   369,
   213,
   337,
   335,
   892,
   569,
   590,
   1390,
   980,
   1309,
   518,
   134,
   281,
   5531,
   169,
   741,
   1016,
   635,
   74,
   169,
   953,
   441,
   120,
   622,
   1001,
   62,
   532,
   569,
   333,
   1044,
   2046,
   539,
   864,
   656,
   570,
   1292,
   481,
   561,
   530,
   416,
   793,
   923,
   312,
   708,
   409,
   1098,
   349,
   375,
   311,
   1429,
   43,
   2204,
   3752,
   948,
   849,
   947,
   898,
   109,
   578,
   630,
   576,
   714,
   143,
   422,
   703,
   2286,
   506,
   138,
   581,
   586,
   538,
   338,
   1602,
   723,
   1138,
   73,
   495,
   993,
   430,
   1477,
   783,
   826,
   332,
   108,
   376,
   1704,
   1127,
   2237,
   323,
   464,
   297,
   404,
   328,
   109,
   2278,
   76,
   863,
   402,
   420,
   192,
   146,
   460,
   467,
   237,
   237,
   544,
   470,
   363,
   178,
   569,
   554,
   846,
   384,
   502,
   390,
   291,
   660,
   276,
   2616,
   354,
   650,
   767,
   220,
   3358,
   7743,
   2152,
   2622,
   1995,
   1053,
   1488,
   2300,
   1400,
   66,
   128,
   97,
   109,
   171,
   192,
   241,
   74,
   708,
   316,
   260,
   724,
   25,
   474,
   279,
   23,
   950,
   205,
   351,
   152,
   1318,
   183,
   164,
   793,
   176,
   209,
   492,
   255,
   404,
   1144,
   85,
   171,
   992,
   399,
   776,
   138,
   456,
   1585,
   1794
  ]
 },
 "SWE-rebench (leaderboard, all HF months)": {
  "benchmark": "SWE-rebench (leaderboard, all HF months)",
  "status": "ok",
  "stats": {
   "count": 860,
   "min": 15,
   "max": 15154,
   "mean": 571.934,
   "median": 350.0,
   "p25": 173.5,
   "p75": 640.0,
   "p95": 1574.2999999999997,
   "p99": 4234.619999999997,
   "pct_under_1024": 88.14,
   "pct_under_2048": 96.98,
   "pct_under_4096": 98.72,
   "pct_under_8192": 99.65,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   222,
   583,
   225,
   90,
   43,
   214,
   174,
   779,
   865,
   143,
   207,
   156,
   837,
   121,
   1200,
   337,
   579,
   446,
   254,
   251,
   795,
   1304,
   153,
   171,
   248,
   350,
   233,
   424,
   232,
   198,
   16,
   114,
   199,
   274,
   828,
   103,
   415,
   688,
   85,
   1670,
   236,
   866,
   1411,
   318,
   776,
   303,
   626,
   1328,
   294,
   387,
   1709,
   508,
   269,
   381,
   275,
   448,
   142,
   88,
   635,
   208,
   596,
   188,
   1178,
   1146,
   80,
   141,
   321,
   485,
   739,
   437,
   436,
   1446,
   105,
   770,
   545,
   54,
   117,
   88,
   243,
   253,
   597,
   1807,
   102,
   71,
   84,
   34,
   83,
   752,
   1101,
   999,
   233,
   197,
   1168,
   50,
   678,
   206,
   108,
   163,
   885,
   642,
   58,
   94,
   297,
   889,
   256,
   617,
   309,
   37,
   475,
   2051,
   146,
   513,
   425,
   28,
   254,
   99,
   46,
   532,
   1008,
   41,
   401,
   259,
   333,
   35,
   1323,
   697,
   180,
   164,
   72,
   237,
   269,
   80,
   1580,
   247,
   96,
   148,
   59,
   727,
   1008,
   70,
   221,
   101,
   99,
   315,
   766,
   1115,
   53,
   170,
   178,
   394,
   274,
   62,
   329,
   59,
   336,
   386,
   342,
   529,
   49,
   171,
   891,
   2886,
   963,
   132,
   135,
   187,
   112,
   626,
   178,
   1342,
   427,
   245,
   58,
   150,
   340,
   649,
   111,
   1375,
   363,
   448,
   92,
   103,
   138,
   588,
   210,
   226,
   479,
   1085,
   317,
   412,
   407,
   951,
   714,
   1448,
   635,
   101,
   325,
   305,
   49,
   201,
   214,
   409,
   67,
   2419,
   648,
   126,
   281,
   808,
   603,
   258,
   73,
   647,
   394,
   110,
   966,
   546,
   472,
   37,
   312,
   131,
   49,
   141,
   61,
   674,
   187,
   796,
   200,
   412,
   113,
   630,
   184,
   1467,
   264,
   544,
   504,
   95,
   183,
   290,
   177,
   467,
   310,
   664,
   719,
   442,
   72,
   256,
   491,
   168,
   388,
   273,
   216,
   127,
   402,
   648,
   277,
   179,
   986,
   482,
   146,
   976,
   1158,
   323,
   717,
   37,
   345,
   1044,
   766,
   244,
   1722,
   442,
   127,
   1805,
   300,
   51,
   790,
   875,
   157,
   958,
   397,
   171,
   707,
   2950,
   274,
   45,
   370,
   282,
   361,
   131,
   155,
   144,
   783,
   553,
   912,
   480,
   198,
   1810,
   252,
   35,
   456,
   671,
   319,
   123,
   445,
   618,
   467,
   463,
   950,
   967,
   349,
   614,
   217,
   52,
   166,
   183,
   68,
   107,
   82,
   44,
   178,
   76,
   168,
   396,
   189,
   369,
   370,
   343,
   1224,
   153,
   174,
   117,
   138,
   343,
   117,
   159,
   158,
   43,
   972,
   408,
   260,
   329,
   149,
   223,
   102,
   245,
   170,
   168,
   78,
   43,
   498,
   304,
   59,
   124,
   94,
   312,
   123,
   160,
   966,
   292,
   100,
   68,
   50,
   147,
   165,
   1037,
   88,
   5829,
   127,
   3467,
   340,
   346,
   1350,
   105,
   269,
   301,
   434,
   458,
   2346,
   204,
   533,
   186,
   256,
   1123,
   95,
   616,
   168,
   392,
   815,
   158,
   64,
   33,
   199,
   44,
   521,
   117,
   155,
   515,
   146,
   58,
   163,
   612,
   688,
   100,
   133,
   522,
   358,
   405,
   200,
   133,
   130,
   61,
   571,
   425,
   1122,
   136,
   180,
   124,
   250,
   9189,
   1741,
   793,
   999,
   168,
   107,
   431,
   216,
   50,
   183,
   274,
   429,
   1018,
   910,
   164,
   149,
   371,
   71,
   6698,
   63,
   909,
   360,
   375,
   252,
   34,
   454,
   304,
   559,
   409,
   190,
   105,
   131,
   532,
   321,
   494,
   494,
   478,
   318,
   30,
   288,
   135,
   80,
   488,
   156,
   382,
   386,
   764,
   86,
   470,
   75,
   1856,
   196,
   1920,
   481,
   49,
   522,
   216,
   175,
   284,
   283,
   544,
   161,
   59,
   188,
   205,
   505,
   515,
   854,
   339,
   639,
   245,
   377,
   258,
   553,
   690,
   86,
   64,
   61,
   34,
   865,
   1188,
   177,
   132,
   115,
   397,
   993,
   180,
   42,
   781,
   275,
   249,
   1116,
   1955,
   578,
   792,
   168,
   813,
   294,
   258,
   249,
   314,
   368,
   250,
   265,
   771,
   1434,
   2563,
   1920,
   308,
   334,
   257,
   1574,
   928,
   70,
   395,
   135,
   929,
   2746,
   540,
   270,
   232,
   172,
   1688,
   513,
   397,
   136,
   156,
   149,
   576,
   224,
   97,
   730,
   519,
   645,
   360,
   345,
   387,
   207,
   665,
   424,
   478,
   351,
   406,
   184,
   193,
   197,
   148,
   492,
   121,
   1023,
   1385,
   1012,
   337,
   640,
   578,
   497,
   82,
   262,
   1618,
   2423,
   102,
   363,
   314,
   764,
   387,
   676,
   339,
   57,
   208,
   542,
   409,
   1025,
   45,
   431,
   162,
   129,
   355,
   32,
   151,
   226,
   60,
   337,
   668,
   238,
   234,
   52,
   394,
   774,
   82,
   1252,
   725,
   332,
   443,
   113,
   339,
   1253,
   368,
   774,
   370,
   363,
   180,
   161,
   15,
   474,
   367,
   837,
   126,
   595,
   210,
   519,
   90,
   132,
   136,
   399,
   579,
   40,
   525,
   1226,
   77,
   568,
   140,
   36,
   138,
   201,
   137,
   734,
   70,
   935,
   1009,
   237,
   4201,
   265,
   1388,
   268,
   13085,
   287,
   567,
   1219,
   404,
   206,
   95,
   179,
   925,
   892,
   1614,
   332,
   314,
   232,
   154,
   175,
   950,
   1069,
   400,
   275,
   806,
   395,
   413,
   3203,
   685,
   391,
   74,
   4573,
   613,
   526,
   70,
   102,
   914,
   610,
   353,
   191,
   4099,
   412,
   69,
   1259,
   241,
   181,
   1036,
   1178,
   234,
   334,
   346,
   253,
   451,
   430,
   177,
   452,
   451,
   658,
   953,
   1210,
   416,
   697,
   397,
   425,
   350,
   1309,
   485,
   79,
   966,
   2405,
   1053,
   500,
   290,
   499,
   462,
   288,
   408,
   1328,
   1312,
   746,
   796,
   2875,
   387,
   326,
   229,
   4639,
   1418,
   718,
   2390,
   1164,
   475,
   50,
   287,
   446,
   793,
   382,
   264,
   567,
   880,
   409,
   267,
   449,
   352,
   885,
   15154,
   1431,
   392,
   763,
   220,
   371,
   1426,
   297,
   397,
   412,
   279,
   351,
   664,
   347,
   2114,
   520,
   605,
   370,
   511,
   241,
   1037,
   4283,
   766,
   1418,
   559,
   568,
   72,
   269,
   546,
   918,
   447,
   1183,
   572,
   274,
   323,
   463,
   253,
   350,
   204,
   251,
   1064,
   552,
   95,
   261,
   111,
   481,
   775,
   426,
   812,
   202,
   1149,
   479,
   583,
   538,
   197,
   640,
   558,
   431,
   297,
   470,
   83,
   213,
   436,
   692,
   237,
   77,
   433,
   314,
   397,
   3371,
   754,
   1206,
   690,
   1189,
   1430,
   210,
   336,
   208,
   431,
   242,
   309,
   509,
   476,
   1941,
   652,
   1333,
   353,
   1343,
   406,
   518,
   518,
   6874,
   262,
   813,
   911,
   441,
   515,
   925,
   188,
   472,
   190,
   423,
   516,
   1424,
   345,
   404,
   1123,
   1656,
   150
  ]
 },
 "SWE-rebench (2026-01..03, latest on HF)": {
  "benchmark": "SWE-rebench (2026-01..03, latest on HF)",
  "status": "ok",
  "stats": {
   "count": 215,
   "min": 50,
   "max": 15154,
   "mean": 863.391,
   "median": 452.0,
   "p25": 293.5,
   "p75": 888.5,
   "p95": 2545.999999999992,
   "p99": 6561.099999999967,
   "pct_under_1024": 79.53,
   "pct_under_2048": 93.49,
   "pct_under_4096": 96.28,
   "pct_under_8192": 99.07,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   1009,
   237,
   4201,
   265,
   1388,
   268,
   13085,
   287,
   567,
   1219,
   404,
   206,
   95,
   179,
   925,
   892,
   1614,
   332,
   314,
   232,
   154,
   175,
   950,
   1069,
   400,
   275,
   806,
   395,
   413,
   3203,
   685,
   391,
   74,
   4573,
   613,
   526,
   70,
   102,
   914,
   610,
   353,
   191,
   4099,
   412,
   69,
   1259,
   241,
   181,
   1036,
   1178,
   234,
   334,
   346,
   253,
   451,
   430,
   177,
   452,
   451,
   658,
   953,
   1210,
   416,
   697,
   397,
   425,
   350,
   1309,
   485,
   79,
   966,
   2405,
   1053,
   500,
   290,
   499,
   462,
   288,
   408,
   1328,
   1312,
   746,
   796,
   2875,
   387,
   326,
   229,
   4639,
   1418,
   718,
   2390,
   1164,
   475,
   50,
   287,
   446,
   793,
   382,
   264,
   567,
   880,
   409,
   267,
   449,
   352,
   885,
   15154,
   1431,
   392,
   763,
   220,
   371,
   1426,
   297,
   397,
   412,
   279,
   351,
   664,
   347,
   2114,
   520,
   605,
   370,
   511,
   241,
   1037,
   4283,
   766,
   1418,
   559,
   568,
   72,
   269,
   546,
   918,
   447,
   1183,
   572,
   274,
   323,
   463,
   253,
   350,
   204,
   251,
   1064,
   552,
   95,
   261,
   111,
   481,
   775,
   426,
   812,
   202,
   1149,
   479,
   583,
   538,
   197,
   640,
   558,
   431,
   297,
   470,
   83,
   213,
   436,
   692,
   237,
   77,
   433,
   314,
   397,
   3371,
   754,
   1206,
   690,
   1189,
   1430,
   210,
   336,
   208,
   431,
   242,
   309,
   509,
   476,
   1941,
   652,
   1333,
   353,
   1343,
   406,
   518,
   518,
   6874,
   262,
   813,
   911,
   441,
   515,
   925,
   188,
   472,
   190,
   423,
   516,
   1424,
   345,
   404,
   1123,
   1656,
   150
  ]
 },
 "SWE-Lancer Diamond (IC SWE)": {
  "benchmark": "SWE-Lancer Diamond (IC SWE)",
  "status": "ok",
  "stats": {
   "count": 198,
   "min": 229,
   "max": 1653,
   "mean": 656.025,
   "median": 653.0,
   "p25": 589.0,
   "p75": 716.0,
   "p95": 877.7499999999999,
   "p99": 1018.6300000000001,
   "pct_under_1024": 98.99,
   "pct_under_2048": 100.0,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   736,
   1653,
   765,
   723,
   653,
   688,
   369,
   651,
   543,
   677,
   657,
   643,
   576,
   525,
   589,
   405,
   844,
   618,
   596,
   708,
   643,
   720,
   548,
   656,
   691,
   655,
   718,
   537,
   531,
   292,
   682,
   539,
   710,
   655,
   723,
   760,
   565,
   630,
   557,
   586,
   612,
   623,
   599,
   522,
   694,
   675,
   671,
   644,
   649,
   797,
   721,
   686,
   680,
   735,
   412,
   564,
   600,
   636,
   630,
   649,
   522,
   556,
   633,
   677,
   653,
   665,
   634,
   598,
   877,
   556,
   739,
   297,
   768,
   583,
   505,
   781,
   713,
   561,
   644,
   650,
   945,
   590,
   607,
   559,
   654,
   677,
   641,
   580,
   535,
   787,
   683,
   634,
   651,
   704,
   1004,
   589,
   860,
   785,
   571,
   640,
   619,
   770,
   826,
   705,
   572,
   622,
   882,
   672,
   667,
   394,
   434,
   752,
   702,
   823,
   774,
   385,
   597,
   576,
   701,
   658,
   229,
   531,
   1015,
   460,
   712,
   788,
   387,
   996,
   703,
   589,
   838,
   618,
   667,
   910,
   667,
   842,
   560,
   725,
   709,
   723,
   726,
   657,
   707,
   758,
   802,
   640,
   666,
   555,
   726,
   619,
   771,
   308,
   641,
   654,
   662,
   616,
   994,
   653,
   620,
   607,
   667,
   674,
   580,
   624,
   696,
   735,
   669,
   781,
   668,
   551,
   584,
   607,
   656,
   614,
   657,
   272,
   717,
   1136,
   750,
   747,
   601,
   622,
   648,
   589,
   852,
   763,
   651,
   589,
   371,
   661,
   659,
   676,
   244,
   519,
   640,
   629,
   598,
   890
  ]
 },
 "SWE-Lancer Diamond (SWE Manager)": {
  "benchmark": "SWE-Lancer Diamond (SWE Manager)",
  "status": "ok",
  "stats": {
   "count": 265,
   "min": 642,
   "max": 7610,
   "mean": 2296.698,
   "median": 2128.0,
   "p25": 1686.0,
   "p75": 2770.0,
   "p95": 3889.9999999999986,
   "p99": 5296.840000000015,
   "pct_under_1024": 2.26,
   "pct_under_2048": 47.17,
   "pct_under_4096": 96.23,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   3087,
   3228,
   2748,
   3134,
   2957,
   5981,
   1535,
   1881,
   2978,
   1919,
   1623,
   2493,
   1453,
   3569,
   3346,
   1935,
   1678,
   2236,
   1939,
   3539,
   1710,
   2150,
   1270,
   2367,
   2030,
   1168,
   2286,
   2796,
   4412,
   1979,
   1757,
   1498,
   1191,
   1724,
   2189,
   2131,
   1613,
   1256,
   1327,
   747,
   1587,
   3822,
   1452,
   1416,
   1295,
   1313,
   2566,
   2495,
   1447,
   1452,
   2667,
   2672,
   3510,
   2372,
   3070,
   3364,
   3003,
   1215,
   1988,
   3693,
   2399,
   1277,
   1802,
   3116,
   2183,
   1846,
   2404,
   2082,
   1825,
   2831,
   1248,
   2868,
   2687,
   3928,
   1431,
   1363,
   1809,
   1515,
   1756,
   2448,
   2361,
   1217,
   2028,
   1998,
   1741,
   2095,
   1973,
   1972,
   3656,
   4912,
   2109,
   1884,
   2870,
   2525,
   1390,
   3016,
   1850,
   2128,
   2936,
   3132,
   2542,
   2303,
   1820,
   2440,
   2208,
   3677,
   2197,
   2827,
   1804,
   1925,
   2018,
   1875,
   1649,
   2201,
   1775,
   3320,
   2859,
   1523,
   943,
   3024,
   1803,
   1686,
   1659,
   1856,
   3955,
   1312,
   2352,
   3181,
   1301,
   1121,
   2736,
   3659,
   6033,
   3929,
   1631,
   1729,
   1731,
   2770,
   2048,
   2515,
   1311,
   1961,
   2733,
   1709,
   2381,
   1740,
   1939,
   1980,
   1261,
   2005,
   1512,
   3324,
   1507,
   2176,
   2295,
   3232,
   1743,
   2299,
   4097,
   1805,
   1604,
   1980,
   1538,
   1689,
   7610,
   1933,
   1490,
   1942,
   1779,
   2610,
   2528,
   3394,
   2320,
   1785,
   2805,
   1057,
   2453,
   3041,
   2115,
   2009,
   1566,
   3144,
   1593,
   2728,
   3291,
   3726,
   1783,
   1696,
   2969,
   2819,
   2327,
   1527,
   1911,
   2701,
   2016,
   1807,
   2558,
   3907,
   2219,
   1595,
   1284,
   2071,
   1912,
   2377,
   1343,
   2727,
   2680,
   4286,
   3813,
   2196,
   2028,
   1689,
   2956,
   2184,
   4368,
   3202,
   1210,
   3480,
   3004,
   1170,
   2421,
   3107,
   2291,
   1360,
   1018,
   1635,
   3163,
   1463,
   1486,
   2660,
   2512,
   1853,
   1223,
   2975,
   1226,
   1260,
   3229,
   4364,
   2172,
   2273,
   983,
   2325,
   4195,
   1530,
   2494,
   3313,
   2164,
   1686,
   2373,
   2818,
   2538,
   1286,
   2380,
   2636,
   2266,
   2526,
   2485,
   976,
   2106,
   642,
   1634,
   2846,
   1942,
   2531,
   1897
  ]
 },
 "Terminal-Bench 2.0": {
  "benchmark": "Terminal-Bench 2.0",
  "status": "ok",
  "stats": {
   "count": 89,
   "min": 34,
   "max": 1148,
   "mean": 231.067,
   "median": 167.0,
   "p25": 116.0,
   "p75": 303.0,
   "p95": 575.1999999999998,
   "p99": 906.8800000000012,
   "pct_under_1024": 98.88,
   "pct_under_2048": 100.0,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   562,
   311,
   117,
   394,
   135,
   142,
   132,
   122,
   70,
   262,
   319,
   70,
   72,
   117,
   584,
   103,
   34,
   262,
   179,
   286,
   446,
   254,
   156,
   70,
   126,
   146,
   123,
   250,
   874,
   34,
   99,
   57,
   113,
   237,
   122,
   151,
   305,
   209,
   274,
   304,
   167,
   1148,
   343,
   221,
   116,
   105,
   351,
   341,
   142,
   290,
   80,
   100,
   446,
   421,
   303,
   73,
   134,
   121,
   190,
   128,
   147,
   201,
   619,
   127,
   196,
   113,
   313,
   77,
   81,
   121,
   155,
   516,
   230,
   291,
   433,
   593,
   173,
   284,
   281,
   73,
   50,
   395,
   276,
   64,
   145,
   315,
   89,
   276,
   88
  ]
 },
 "Terminal-Bench 4.0": {
  "benchmark": "Terminal-Bench 4.0",
  "status": "ok",
  "stats": {
   "count": 66,
   "min": 89,
   "max": 1972,
   "mean": 455.682,
   "median": 393.5,
   "p25": 228.5,
   "p75": 583.5,
   "p95": 945.0,
   "p99": 1493.5999999999958,
   "pct_under_1024": 96.97,
   "pct_under_2048": 100.0,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   957,
   826,
   1236,
   552,
   89,
   496,
   254,
   296,
   122,
   251,
   602,
   184,
   909,
   324,
   337,
   755,
   349,
   181,
   665,
   367,
   513,
   610,
   141,
   819,
   201,
   457,
   363,
   420,
   990,
   254,
   338,
   570,
   588,
   140,
   224,
   432,
   237,
   304,
   218,
   203,
   226,
   838,
   112,
   496,
   443,
   654,
   236,
   730,
   563,
   476,
   471,
   501,
   542,
   217,
   201,
   181,
   435,
   318,
   420,
   316,
   243,
   609,
   119,
   213,
   769,
   1972
  ]
 },
 "DeepSWE": {
  "benchmark": "DeepSWE",
  "status": "ok",
  "stats": {
   "count": 113,
   "min": 117,
   "max": 1302,
   "mean": 485.168,
   "median": 439.0,
   "p25": 299.0,
   "p75": 619.0,
   "p95": 917.3999999999997,
   "p99": 1119.3199999999997,
   "pct_under_1024": 96.46,
   "pct_under_2048": 100.0,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   520,
   781,
   444,
   219,
   384,
   169,
   381,
   1302,
   439,
   416,
   381,
   286,
   561,
   831,
   288,
   619,
   261,
   383,
   592,
   316,
   746,
   486,
   243,
   273,
   469,
   278,
   1124,
   321,
   740,
   362,
   814,
   161,
   412,
   351,
   424,
   420,
   294,
   143,
   319,
   563,
   233,
   724,
   466,
   573,
   299,
   220,
   885,
   167,
   546,
   766,
   533,
   907,
   991,
   309,
   201,
   526,
   192,
   177,
   630,
   389,
   117,
   296,
   700,
   603,
   509,
   225,
   393,
   575,
   490,
   778,
   565,
   672,
   190,
   662,
   141,
   699,
   568,
   237,
   381,
   299,
   593,
   807,
   362,
   513,
   290,
   637,
   408,
   193,
   777,
   386,
   640,
   563,
   933,
   576,
   230,
   214,
   387,
   512,
   450,
   374,
   333,
   425,
   529,
   615,
   1060,
   309,
   1085,
   503,
   775,
   708,
   302,
   343,
   642
  ]
 },
 "LiveCodeBench (release_v6)": {
  "benchmark": "LiveCodeBench (release_v6)",
  "status": "ok",
  "stats": {
   "count": 1055,
   "min": 114,
   "max": 1521,
   "mean": 447.891,
   "median": 416.0,
   "p25": 298.5,
   "p75": 553.5,
   "p95": 825.1999999999998,
   "p99": 1092.1200000000008,
   "pct_under_1024": 98.67,
   "pct_under_2048": 100.0,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   404,
   290,
   507,
   695,
   688,
   231,
   703,
   435,
   692,
   287,
   295,
   253,
   262,
   292,
   249,
   275,
   619,
   508,
   446,
   417,
   268,
   520,
   386,
   243,
   360,
   358,
   407,
   199,
   287,
   332,
   375,
   124,
   242,
   508,
   512,
   334,
   580,
   313,
   433,
   555,
   317,
   661,
   378,
   357,
   383,
   204,
   469,
   313,
   525,
   484,
   217,
   279,
   436,
   224,
   342,
   465,
   334,
   333,
   233,
   294,
   353,
   286,
   498,
   381,
   283,
   342,
   328,
   354,
   327,
   637,
   377,
   564,
   355,
   228,
   603,
   508,
   573,
   462,
   438,
   295,
   427,
   312,
   465,
   277,
   351,
   398,
   205,
   239,
   361,
   393,
   395,
   284,
   361,
   481,
   525,
   533,
   390,
   239,
   325,
   235,
   311,
   591,
   201,
   404,
   546,
   473,
   326,
   330,
   305,
   349,
   504,
   385,
   416,
   573,
   454,
   335,
   351,
   478,
   478,
   276,
   450,
   315,
   382,
   474,
   495,
   373,
   621,
   395,
   427,
   235,
   294,
   353,
   258,
   299,
   883,
   312,
   260,
   412,
   498,
   375,
   304,
   220,
   529,
   549,
   272,
   264,
   965,
   422,
   311,
   328,
   514,
   630,
   292,
   445,
   708,
   408,
   653,
   275,
   379,
   517,
   188,
   477,
   789,
   418,
   388,
   385,
   300,
   466,
   589,
   461,
   390,
   405,
   270,
   441,
   304,
   458,
   811,
   456,
   277,
   345,
   253,
   471,
   372,
   366,
   504,
   287,
   224,
   393,
   356,
   510,
   312,
   466,
   361,
   347,
   730,
   330,
   186,
   963,
   337,
   523,
   607,
   700,
   404,
   558,
   811,
   557,
   563,
   423,
   392,
   530,
   753,
   758,
   295,
   295,
   602,
   822,
   757,
   190,
   439,
   457,
   884,
   649,
   402,
   421,
   1062,
   311,
   311,
   299,
   391,
   392,
   601,
   467,
   421,
   189,
   557,
   618,
   689,
   500,
   319,
   1000,
   439,
   460,
   822,
   516,
   278,
   429,
   607,
   700,
   646,
   186,
   770,
   343,
   285,
   697,
   525,
   259,
   607,
   365,
   283,
   712,
   610,
   653,
   1369,
   1214,
   189,
   458,
   448,
   512,
   625,
   557,
   286,
   397,
   501,
   538,
   319,
   389,
   927,
   621,
   815,
   160,
   184,
   634,
   513,
   783,
   381,
   645,
   314,
   562,
   650,
   275,
   364,
   447,
   1104,
   572,
   249,
   423,
   700,
   491,
   580,
   268,
   254,
   740,
   512,
   490,
   759,
   253,
   454,
   545,
   511,
   630,
   596,
   218,
   196,
   372,
   631,
   555,
   223,
   189,
   929,
   538,
   451,
   275,
   437,
   644,
   346,
   816,
   174,
   265,
   288,
   633,
   359,
   563,
   324,
   340,
   185,
   520,
   597,
   371,
   230,
   583,
   739,
   714,
   523,
   504,
   693,
   1195,
   115,
   286,
   209,
   534,
   1022,
   197,
   424,
   491,
   440,
   671,
   203,
   547,
   448,
   603,
   167,
   233,
   228,
   485,
   395,
   467,
   667,
   700,
   960,
   232,
   230,
   683,
   852,
   352,
   628,
   200,
   457,
   326,
   575,
   232,
   403,
   556,
   533,
   417,
   138,
   658,
   894,
   292,
   702,
   910,
   169,
   466,
   492,
   299,
   1521,
   226,
   527,
   300,
   733,
   1082,
   556,
   175,
   445,
   306,
   634,
   460,
   349,
   445,
   327,
   747,
   254,
   306,
   393,
   298,
   539,
   167,
   408,
   441,
   192,
   787,
   524,
   309,
   514,
   268,
   810,
   642,
   289,
   634,
   485,
   456,
   450,
   602,
   634,
   680,
   347,
   828,
   673,
   683,
   337,
   622,
   492,
   553,
   318,
   674,
   292,
   325,
   378,
   632,
   400,
   447,
   495,
   432,
   907,
   353,
   435,
   265,
   287,
   255,
   464,
   351,
   493,
   184,
   154,
   339,
   872,
   130,
   259,
   520,
   686,
   165,
   157,
   390,
   302,
   331,
   308,
   274,
   184,
   352,
   577,
   182,
   569,
   440,
   512,
   229,
   633,
   359,
   236,
   634,
   147,
   275,
   169,
   452,
   229,
   332,
   157,
   644,
   293,
   354,
   481,
   354,
   285,
   187,
   239,
   548,
   245,
   283,
   388,
   260,
   411,
   181,
   309,
   313,
   551,
   430,
   794,
   363,
   380,
   416,
   247,
   235,
   438,
   477,
   476,
   675,
   477,
   199,
   609,
   312,
   640,
   314,
   435,
   432,
   342,
   400,
   254,
   591,
   486,
   418,
   286,
   172,
   319,
   401,
   757,
   404,
   432,
   281,
   247,
   356,
   274,
   432,
   374,
   169,
   789,
   882,
   547,
   544,
   535,
   434,
   274,
   222,
   312,
   466,
   424,
   491,
   428,
   263,
   309,
   448,
   336,
   262,
   213,
   245,
   467,
   432,
   201,
   528,
   229,
   266,
   446,
   224,
   140,
   192,
   371,
   189,
   515,
   214,
   329,
   262,
   334,
   224,
   203,
   316,
   386,
   437,
   479,
   329,
   307,
   155,
   600,
   201,
   144,
   283,
   501,
   190,
   543,
   205,
   224,
   254,
   369,
   340,
   242,
   471,
   469,
   457,
   353,
   1074,
   281,
   592,
   642,
   484,
   624,
   344,
   687,
   224,
   659,
   661,
   643,
   319,
   295,
   347,
   512,
   361,
   806,
   569,
   784,
   441,
   320,
   515,
   948,
   291,
   256,
   638,
   893,
   509,
   424,
   671,
   437,
   485,
   857,
   817,
   1401,
   309,
   336,
   859,
   519,
   421,
   677,
   685,
   160,
   318,
   318,
   408,
   669,
   294,
   611,
   656,
   854,
   566,
   641,
   743,
   524,
   1104,
   439,
   528,
   446,
   565,
   845,
   354,
   238,
   310,
   187,
   336,
   268,
   207,
   427,
   206,
   612,
   248,
   303,
   206,
   684,
   346,
   321,
   329,
   366,
   339,
   367,
   275,
   551,
   409,
   239,
   356,
   201,
   613,
   203,
   236,
   245,
   185,
   410,
   192,
   242,
   388,
   281,
   477,
   590,
   428,
   945,
   460,
   173,
   649,
   500,
   534,
   824,
   244,
   258,
   641,
   651,
   807,
   429,
   650,
   491,
   691,
   642,
   473,
   680,
   527,
   184,
   445,
   689,
   526,
   376,
   413,
   567,
   438,
   371,
   390,
   254,
   454,
   313,
   284,
   467,
   585,
   413,
   638,
   247,
   367,
   676,
   579,
   499,
   217,
   596,
   300,
   401,
   600,
   305,
   447,
   460,
   536,
   446,
   488,
   1276,
   627,
   651,
   465,
   545,
   796,
   597,
   114,
   738,
   549,
   583,
   249,
   896,
   324,
   850,
   480,
   226,
   337,
   774,
   472,
   1009,
   634,
   328,
   554,
   385,
   290,
   359,
   339,
   505,
   605,
   387,
   584,
   487,
   601,
   612,
   904,
   395,
   364,
   952,
   524,
   980,
   509,
   899,
   568,
   522,
   1023,
   656,
   512,
   481,
   543,
   324,
   179,
   233,
   509,
   221,
   385,
   507,
   199,
   397,
   271,
   284,
   238,
   345,
   693,
   371,
   308,
   402,
   449,
   425,
   539,
   449,
   304,
   201,
   383,
   162,
   252,
   164,
   716,
   404,
   711,
   127,
   311,
   520,
   394,
   246,
   326,
   479,
   296,
   285,
   370,
   742,
   219,
   231,
   331,
   217,
   266,
   216,
   590,
   391,
   167,
   684,
   470,
   384,
   338,
   398,
   297,
   442,
   216,
   334,
   436,
   284,
   322,
   145,
   221,
   518,
   361,
   942,
   518,
   182,
   464,
   467,
   249,
   178,
   181,
   495,
   832,
   303,
   532,
   378,
   292,
   294,
   661,
   510,
   600,
   678,
   854,
   196,
   518,
   412,
   505,
   239,
   319,
   375,
   467,
   401,
   387,
   342,
   572,
   474,
   410,
   237,
   488,
   242,
   490,
   176,
   1282,
   482,
   699,
   326,
   666,
   623,
   329,
   821,
   549,
   396,
   429,
   568,
   726,
   692,
   399,
   261,
   445,
   460,
   422,
   414,
   318,
   310,
   159,
   318,
   688,
   128,
   327,
   560,
   400,
   663,
   258,
   340,
   339,
   611,
   239,
   1171,
   172,
   250,
   359,
   897,
   1350,
   778,
   765,
   586,
   435,
   356,
   461,
   627,
   529,
   778,
   713,
   938,
   828,
   755,
   403,
   640,
   519,
   381,
   697,
   524,
   780,
   526,
   366,
   884,
   566,
   330,
   855,
   280,
   517,
   553,
   433,
   303,
   355,
   598,
   299,
   339,
   690,
   271,
   235,
   462,
   260,
   342,
   427,
   278,
   463,
   248,
   455,
   284,
   595,
   368,
   326,
   447,
   577,
   324,
   262,
   403,
   483,
   389,
   423,
   289,
   381,
   755,
   156,
   228,
   325,
   522,
   518,
   424,
   271,
   474,
   226,
   504,
   157,
   442,
   372,
   239,
   437,
   463,
   228,
   381,
   266,
   284,
   385,
   419,
   421,
   288,
   467,
   258,
   458,
   570
  ]
 },
 "LiveCodeBench (release_v1, control)": {
  "benchmark": "LiveCodeBench (release_v1, control)",
  "status": "ok",
  "stats": {
   "count": 400,
   "min": 115,
   "max": 1521,
   "mean": 456.51,
   "median": 421.0,
   "p25": 304.75,
   "p75": 557.0,
   "p95": 822.0,
   "p99": 1104.9099999999992,
   "pct_under_1024": 98.25,
   "pct_under_2048": 100.0,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   404,
   290,
   507,
   695,
   688,
   231,
   703,
   435,
   692,
   287,
   295,
   253,
   262,
   292,
   249,
   275,
   619,
   508,
   446,
   417,
   268,
   520,
   386,
   243,
   360,
   358,
   407,
   199,
   287,
   332,
   375,
   124,
   242,
   508,
   512,
   334,
   580,
   313,
   433,
   555,
   317,
   661,
   378,
   357,
   383,
   204,
   469,
   313,
   525,
   484,
   217,
   279,
   436,
   224,
   342,
   465,
   334,
   333,
   233,
   294,
   353,
   286,
   498,
   381,
   283,
   342,
   328,
   354,
   327,
   637,
   377,
   564,
   355,
   228,
   603,
   508,
   573,
   462,
   438,
   295,
   427,
   312,
   465,
   277,
   351,
   398,
   205,
   239,
   361,
   393,
   395,
   284,
   361,
   481,
   525,
   533,
   390,
   239,
   325,
   235,
   311,
   591,
   201,
   404,
   546,
   473,
   326,
   330,
   305,
   349,
   504,
   385,
   416,
   573,
   454,
   335,
   351,
   478,
   478,
   276,
   450,
   315,
   382,
   474,
   495,
   373,
   621,
   395,
   427,
   235,
   294,
   353,
   258,
   299,
   883,
   312,
   260,
   412,
   498,
   375,
   304,
   220,
   529,
   549,
   272,
   264,
   965,
   422,
   311,
   328,
   514,
   630,
   292,
   445,
   708,
   408,
   653,
   275,
   379,
   517,
   188,
   477,
   789,
   418,
   388,
   385,
   300,
   466,
   589,
   461,
   390,
   405,
   270,
   441,
   304,
   458,
   811,
   456,
   277,
   345,
   253,
   471,
   372,
   366,
   504,
   287,
   224,
   393,
   356,
   510,
   312,
   466,
   361,
   347,
   730,
   330,
   186,
   963,
   337,
   523,
   607,
   700,
   404,
   558,
   811,
   557,
   563,
   423,
   392,
   530,
   753,
   758,
   295,
   295,
   602,
   822,
   757,
   190,
   439,
   457,
   884,
   649,
   402,
   421,
   1062,
   311,
   311,
   299,
   391,
   392,
   601,
   467,
   421,
   189,
   557,
   618,
   689,
   500,
   319,
   1000,
   439,
   460,
   822,
   516,
   278,
   429,
   607,
   700,
   646,
   186,
   770,
   343,
   285,
   697,
   525,
   259,
   607,
   365,
   283,
   712,
   610,
   653,
   1369,
   1214,
   189,
   458,
   448,
   512,
   625,
   557,
   286,
   397,
   501,
   538,
   319,
   389,
   927,
   621,
   815,
   160,
   184,
   634,
   513,
   783,
   381,
   645,
   314,
   562,
   650,
   275,
   364,
   447,
   1104,
   572,
   249,
   423,
   700,
   491,
   580,
   268,
   254,
   740,
   512,
   490,
   759,
   253,
   454,
   545,
   511,
   630,
   596,
   218,
   196,
   372,
   631,
   555,
   223,
   189,
   929,
   538,
   451,
   275,
   437,
   644,
   346,
   816,
   174,
   265,
   288,
   633,
   359,
   563,
   324,
   340,
   185,
   520,
   597,
   371,
   230,
   583,
   739,
   714,
   523,
   504,
   693,
   1195,
   115,
   286,
   209,
   534,
   1022,
   197,
   424,
   491,
   440,
   671,
   203,
   547,
   448,
   603,
   167,
   233,
   228,
   485,
   395,
   467,
   667,
   700,
   960,
   232,
   230,
   683,
   852,
   352,
   628,
   200,
   457,
   326,
   575,
   232,
   403,
   556,
   533,
   417,
   138,
   658,
   894,
   292,
   702,
   910,
   169,
   466,
   492,
   299,
   1521,
   226,
   527,
   300,
   733,
   1082
  ]
 },
 "Aider Polyglot": {
  "benchmark": "Aider Polyglot",
  "status": "ok",
  "stats": {
   "count": 225,
   "min": 38,
   "max": 3270,
   "mean": 483.444,
   "median": 434.0,
   "p25": 268.0,
   "p75": 598.0,
   "p95": 915.9999999999995,
   "p99": 2853.319999999989,
   "pct_under_1024": 96.44,
   "pct_under_2048": 98.67,
   "pct_under_4096": 100.0,
   "pct_under_8192": 100.0,
   "pct_under_16384": 100.0,
   "pct_under_32768": 100.0
  },
  "per_problem_tokens": [
   380,
   436,
   403,
   434,
   466,
   38,
   505,
   516,
   310,
   697,
   462,
   268,
   452,
   311,
   672,
   642,
   520,
   442,
   303,
   297,
   132,
   589,
   269,
   586,
   662,
   466,
   429,
   3270,
   665,
   393,
   548,
   283,
   199,
   516,
   697,
   517,
   569,
   598,
   211,
   89,
   452,
   139,
   149,
   312,
   347,
   88,
   406,
   625,
   134,
   715,
   465,
   135,
   876,
   331,
   921,
   223,
   586,
   215,
   277,
   236,
   896,
   365,
   143,
   276,
   598,
   874,
   380,
   179,
   666,
   572,
   393,
   548,
   171,
   466,
   283,
   57,
   255,
   598,
   211,
   282,
   552,
   731,
   452,
   139,
   760,
   398,
   406,
   303,
   626,
   51,
   930,
   462,
   139,
   297,
   837,
   135,
   580,
   510,
   223,
   129,
   873,
   223,
   529,
   215,
   277,
   706,
   542,
   365,
   143,
   276,
   466,
   346,
   831,
   179,
   3143,
   282,
   644,
   393,
   548,
   505,
   283,
   598,
   211,
   632,
   268,
   686,
   731,
   1240,
   139,
   343,
   711,
   398,
   406,
   1077,
   303,
   626,
   51,
   477,
   510,
   837,
   135,
   175,
   580,
   640,
   132,
   318,
   921,
   223,
   589,
   529,
   383,
   485,
   215,
   222,
   706,
   652,
   365,
   143,
   276,
   604,
   346,
   1058,
   3143,
   572,
   393,
   809,
   283,
   255,
   707,
   598,
   672,
   518,
   336,
   292,
   444,
   301,
   88,
   797,
   626,
   51,
   632,
   318,
   135,
   510,
   132,
   921,
   1200,
   1936,
   215,
   476,
   766,
   604,
   832,
   466,
   346,
   209,
   122,
   179,
   572,
   548,
   368,
   443,
   727,
   215,
   261,
   513,
   268,
   655,
   125,
   554,
   217,
   398,
   286,
   625,
   51,
   135,
   205,
   496,
   490,
   770,
   542,
   365,
   413,
   305,
   887
  ]
 }
}