{
  "id": "deepswe",
  "date": "2026-09-03",
  "generatedAt": "2026-09-03T22:24:37.984682+00:00",
  "retrievedAt": "2026-09-07T13:54:00Z",
  "page": "https://deepswe.datacurve.ai/",
  "pageSha256": "8fdbb59257d00cbb0772248bb602aafc1d20a51822388cd4eaf4625505182be7",
  "artifact": "https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json",
  "artifactSha256": "005cbedb49f988ba3f0d9636300862ad7ace93ce1992b37faf9945fe5b383415",
  "tasks": 113,
  "scope": "Every DeepSWE rollout across imported Pier jobs, grouped by configuration (harness + model + reasoning effort)",
  "unit": "pass@1 is attempt pass rate over scored rollout attempts. pass@4 is tasks with at least one passing rollout divided by tasks attempted. Context-window failures and agent timeouts are scored failures; provider/verifier/network errors are excluded. Efficiency aggregates are over every scored attempt.",
  "repriced": 19,
  "astraList": {
    "source": "https://developers.openai.com/api/docs/models/gpt-6-astra",
    "retrievedAt": "2026-09-07",
    "rates": {
      "uncached input": 10,
      "cache reads": 1,
      "cache writes": 12.5,
      "output": 50
    }
  },
  "configs": [
    {
      "config": "mini_swe_agent_gpt_6_astra_xhigh",
      "model": "gpt-6-astra",
      "effort": "xhigh",
      "pass": 0.7411504424778761,
      "ciHalf": 0.02865396174075141,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 6.52377356460177,
      "artifactCost": null,
      "outputTokens": 29557.327433628318,
      "inputTokens": 1456927.0929203539,
      "cacheTokens": 1326921.6836283186,
      "steps": 28.754424778761063,
      "peakContextTokens": null,
      "bill": {
        "basis": "Expected launch pricing at all context lengths: $12/M uncached input, $15/M cache writes, $1.20/M cache reads, $50/M output, $2/M compute units.",
        "rates": {
          "uncached input": 12,
          "cache writes": 15,
          "cache reads": 1.2,
          "output": 50,
          "compute units": 2
        },
        "reasoningTokens": 11255.66592920354,
        "uncachedInputTokens": 295.3871681415929,
        "cacheReadTokens": 1326921.6836283186,
        "cacheWriteTokens": 129710.02212389381,
        "computeUnits": 752203.0973451327
      }
    },
    {
      "config": "mini_swe_agent_gemini_3_8_flash_high",
      "model": "gemini-3-8-flash",
      "effort": "high",
      "pass": 0.738255033557047,
      "ciHalf": 0.014173132066358783,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.362349413758389,
      "artifactCost": null,
      "outputTokens": 143242.6644295302,
      "inputTokens": 21734449.25279642,
      "cacheTokens": 21456039.230425056,
      "steps": 166.3131991051454,
      "peakContextTokens": 215558,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_5_max",
      "model": "claude-opus-5",
      "effort": "max",
      "pass": 0.7364864864864865,
      "ciHalf": 0.03872310426371729,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 11.837583271396396,
      "artifactCost": null,
      "outputTokens": 117565.6936936937,
      "inputTokens": 15025834.39864865,
      "cacheTokens": 14784785.963963963,
      "steps": 99.0427927927928,
      "peakContextTokens": 215810,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_6_astra_high",
      "model": "gpt-6-astra",
      "effort": "high",
      "pass": 0.7323008849557522,
      "ciHalf": 0.03423496057873005,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 5.723721956194691,
      "artifactCost": null,
      "outputTokens": 26505.853982300883,
      "inputTokens": 1283270.8030973452,
      "cacheTokens": 1168811.0420353983,
      "steps": 27.424778761061948,
      "peakContextTokens": null,
      "bill": {
        "basis": "Expected launch pricing at all context lengths: $12/M uncached input, $15/M cache writes, $1.20/M cache reads, $50/M output, $2/M compute units.",
        "rates": {
          "uncached input": 12,
          "cache writes": 15,
          "cache reads": 1.2,
          "output": 50,
          "compute units": 2
        },
        "reasoningTokens": 9021.692477876106,
        "uncachedInputTokens": 450.7853982300885,
        "cacheReadTokens": 1168811.0420353983,
        "cacheWriteTokens": 114008.97566371682,
        "computeUnits": 640155.9734513274
      }
    },
    {
      "config": "mini_swe_agent_gpt_6_astra_max",
      "model": "gpt-6-astra",
      "effort": "max",
      "pass": 0.7323008849557522,
      "ciHalf": 0.008303197562056526,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 12.369032401327434,
      "artifactCost": null,
      "outputTokens": 61148.50663716814,
      "inputTokens": 2183033.681415929,
      "cacheTokens": 1986676.7079646017,
      "steps": 28.45353982300885,
      "peakContextTokens": null,
      "bill": {
        "basis": "Expected launch pricing at all context lengths: $12/M uncached input, $15/M cache writes, $1.20/M cache reads, $50/M output, $2/M compute units.",
        "rates": {
          "uncached input": 12,
          "cache writes": 15,
          "cache reads": 1.2,
          "output": 50,
          "compute units": 2
        },
        "reasoningTokens": 36555.72345132743,
        "uncachedInputTokens": 294.4845132743363,
        "cacheReadTokens": 1986676.7079646017,
        "cacheWriteTokens": 196062.4889380531,
        "computeUnits": 1991561.935840708
      }
    },
    {
      "config": "mini_swe_agent_claude_opus_5_xhigh",
      "model": "claude-opus-5",
      "effort": "xhigh",
      "pass": 0.7315436241610739,
      "ciHalf": 0.030609818216384643,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 9.07220232326622,
      "artifactCost": null,
      "outputTokens": 91672.01565995526,
      "inputTokens": 11292729.463087248,
      "cacheTokens": 11094990.232662192,
      "steps": 88.7248322147651,
      "peakContextTokens": 173749,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_5_high",
      "model": "claude-opus-5",
      "effort": "high",
      "pass": 0.7282850779510023,
      "ciHalf": 0.019454321571601495,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 6.076084489977728,
      "artifactCost": null,
      "outputTokens": 64207.43429844098,
      "inputTokens": 7233879.0824053455,
      "cacheTokens": 7085027.516703786,
      "steps": 72.92204899777283,
      "peakContextTokens": 126517,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_6_astra_medium",
      "model": "gpt-6-astra",
      "effort": "medium",
      "pass": 0.7278761061946902,
      "ciHalf": 0.025896490818318695,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 4.379527705752213,
      "artifactCost": null,
      "outputTokens": 20361.809734513274,
      "inputTokens": 1008238.2898230088,
      "cacheTokens": 916944.3473451327,
      "steps": 26.030973451327434,
      "peakContextTokens": null,
      "bill": {
        "basis": "Expected launch pricing at all context lengths: $12/M uncached input, $15/M cache writes, $1.20/M cache reads, $50/M output, $2/M compute units.",
        "rates": {
          "uncached input": 12,
          "cache writes": 15,
          "cache reads": 1.2,
          "output": 50,
          "compute units": 2
        },
        "reasoningTokens": 5510.918141592921,
        "uncachedInputTokens": 293.92699115044246,
        "cacheReadTokens": 916944.3473451327,
        "cacheWriteTokens": 91000.01548672566,
        "computeUnits": 446288.3230088496
      }
    },
    {
      "config": "mini_swe_agent_gpt_5_6_sol_max",
      "model": "gpt-5-6-sol",
      "effort": "max",
      "pass": 0.7266666666666667,
      "ciHalf": 0.02829822249837175,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 6.455954682467823,
      "artifactCost": 8.386436346666667,
      "outputTokens": 60013.64444444444,
      "inputTokens": 7907652.344444444,
      "cacheTokens": 7419435.235555556,
      "steps": 61.25333333333333,
      "peakContextTokens": 177470.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_8_flash_medium",
      "model": "gemini-3-8-flash",
      "effort": "medium",
      "pass": 0.7101769911504425,
      "ciHalf": 0.02280804572877925,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.9671024789823006,
      "artifactCost": null,
      "outputTokens": 124684.36283185841,
      "inputTokens": 16863939.814159293,
      "cacheTokens": 16519023.008849557,
      "steps": 147.30088495575222,
      "peakContextTokens": 189491.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_sol_xhigh",
      "model": "gpt-5-6-sol",
      "effort": "xhigh",
      "pass": 0.7073170731707317,
      "ciHalf": 0.008191117217343103,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.5986416572286237,
      "artifactCost": 4.703663860310422,
      "outputTokens": 40744.59201773836,
      "inputTokens": 4259318.379157428,
      "cacheTokens": 3967289.3303769403,
      "steps": 44,
      "peakContextTokens": 133054,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_fable_5_xhigh",
      "model": "claude-fable-5",
      "effort": "xhigh",
      "pass": 0.6991150442477876,
      "ciHalf": 0.03244917575471319,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 13.414521495535714,
      "artifactCost": null,
      "outputTokens": 80352.1703539823,
      "inputTokens": 7329160.601769911,
      "cacheTokens": 7159496.181415929,
      "steps": 68.40044247787611,
      "peakContextTokens": 141254.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_fable_5_max",
      "model": "claude-fable-5",
      "effort": "max",
      "pass": 0.6972477064220184,
      "ciHalf": 0.04033474250807936,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 21.634702092592594,
      "artifactCost": null,
      "outputTokens": 118592.77293577982,
      "inputTokens": 12638832.12614679,
      "cacheTokens": 12388674.334862385,
      "steps": 88.4288990825688,
      "peakContextTokens": 201598,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_terra_max",
      "model": "gpt-5-6-terra",
      "effort": "max",
      "pass": 0.6962305986696231,
      "ciHalf": 0.025569389504458404,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.956677811086475,
      "artifactCost": 4.945847263858093,
      "outputTokens": 71938.62527716186,
      "inputTokens": 9230560.541019956,
      "cacheTokens": 8652201.720620843,
      "steps": 75.9290465631929,
      "peakContextTokens": 177398,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_sol_high",
      "model": "gpt-5-6-sol",
      "effort": "high",
      "pass": 0.6940133037694013,
      "ciHalf": 0.014321452203772355,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.661832088842267,
      "artifactCost": 3.4698331108647453,
      "outputTokens": 28450.31929046563,
      "inputTokens": 2713572.2505543237,
      "cacheTokens": 2435251.370288248,
      "steps": 36.889135254988915,
      "peakContextTokens": 98355,
      "bill": null
    },
    {
      "config": "mini_swe_agent_glm_5_3_max",
      "model": "glm-5-3",
      "effort": "max",
      "pass": 0.6895787139689579,
      "ciHalf": 0.030186512715587,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.9933584893126386,
      "artifactCost": null,
      "outputTokens": 80435.60975609756,
      "inputTokens": 13272344.266075388,
      "cacheTokens": 13106008.833702883,
      "steps": 124.47228381374723,
      "peakContextTokens": 144729,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_5_medium",
      "model": "claude-opus-5",
      "effort": "medium",
      "pass": 0.6890380313199105,
      "ciHalf": 0.011725586658930944,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.28978764541387,
      "artifactCost": null,
      "outputTokens": 36981.530201342284,
      "inputTokens": 3579815.3601789707,
      "cacheTokens": 3479530.087248322,
      "steps": 52.29530201342282,
      "peakContextTokens": 78690,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_fable_5_high",
      "model": "claude-fable-5",
      "effort": "high",
      "pass": 0.686046511627907,
      "ciHalf": 0.011208427174303877,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 9.177638214788733,
      "artifactCost": null,
      "outputTokens": 57287.06976744186,
      "inputTokens": 4833178.365116279,
      "cacheTokens": 4711714.3162790695,
      "steps": 58.73720930232558,
      "peakContextTokens": 99524,
      "bill": null
    },
    {
      "config": "mini_swe_agent_kimi_k3_max",
      "model": "kimi-k3",
      "effort": "max",
      "pass": 0.6851441241685144,
      "ciHalf": 0.045370140792823206,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 4.654682129933482,
      "artifactCost": null,
      "outputTokens": 81499.84257206209,
      "inputTokens": 9695436.246119734,
      "cacheTokens": 9501527.498891352,
      "steps": 97.58758314855876,
      "peakContextTokens": 130945,
      "bill": null
    },
    {
      "config": "mini_swe_agent_grok_4_6_medium",
      "model": "grok-4-6",
      "effort": "medium",
      "pass": 0.6747787610619469,
      "ciHalf": 0.0228080457287792,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.4489837522123894,
      "artifactCost": null,
      "outputTokens": 49763.99778761062,
      "inputTokens": 5725195.139380531,
      "cacheTokens": 5533327.0088495575,
      "steps": 70.28982300884955,
      "peakContextTokens": 116622,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_luna_max",
      "model": "gpt-5-6-luna",
      "effort": "max",
      "pass": 0.671875,
      "ciHalf": 0.03992001235671055,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.6056233620535714,
      "artifactCost": 3.028116810267857,
      "outputTokens": 73399.70758928571,
      "inputTokens": 15443718.330357144,
      "cacheTokens": 14666893.714285715,
      "steps": 101.68080357142857,
      "peakContextTokens": 201647,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_6_astra_low",
      "model": "gpt-6-astra",
      "effort": "low",
      "pass": 0.6703539823008849,
      "ciHalf": 0.013008610516858731,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.188762706637168,
      "artifactCost": null,
      "outputTokens": 10579.53982300885,
      "inputTokens": 494506.91150442476,
      "cacheTokens": 444727.3495575221,
      "steps": 19.537610619469028,
      "peakContextTokens": null,
      "bill": {
        "basis": "Expected launch pricing at all context lengths: $12/M uncached input, $15/M cache writes, $1.20/M cache reads, $50/M output, $2/M compute units.",
        "rates": {
          "uncached input": 12,
          "cache writes": 15,
          "cache reads": 1.2,
          "output": 50,
          "compute units": 2
        },
        "reasoningTokens": 1414.641592920354,
        "uncachedInputTokens": 290.17035398230087,
        "cacheReadTokens": 444727.3495575221,
        "cacheWriteTokens": 49489.39159292035,
        "computeUnits": 190144.9889380531
      }
    },
    {
      "config": "mini_swe_agent_gpt_5_5_xhigh",
      "model": "gpt-5-5",
      "effort": "xhigh",
      "pass": 0.6703539823008849,
      "ciHalf": 0.06465646340908864,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 7.226236674778761,
      "artifactCost": null,
      "outputTokens": 46294.72345132743,
      "inputTokens": 8372927.630530974,
      "cacheTokens": 8032415.716814159,
      "steps": 82.01548672566372,
      "peakContextTokens": 141957.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_grok_4_6_xhigh",
      "model": "grok-4-6",
      "effort": "xhigh",
      "pass": 0.6674057649667405,
      "ciHalf": 0.02175684224405049,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 5.497668745011087,
      "artifactCost": null,
      "outputTokens": 71403.54323725056,
      "inputTokens": 9344022.093126386,
      "cacheTokens": 9079197.80044346,
      "steps": 87.21951219512195,
      "peakContextTokens": 156581,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_7_flash_medium",
      "model": "gemini-3-7-flash",
      "effort": "medium",
      "pass": 0.6548672566371682,
      "ciHalf": 0.030865322764155222,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.0251351826880533,
      "artifactCost": null,
      "outputTokens": 93990.8517699115,
      "inputTokens": 15332065.907079646,
      "cacheTokens": 14557599.913716814,
      "steps": 117.36946902654867,
      "peakContextTokens": 195705.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_fable_5_medium",
      "model": "claude-fable-5",
      "effort": "medium",
      "pass": 0.6536697247706422,
      "ciHalf": 0.044219288792381656,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 6.088186528935186,
      "artifactCost": null,
      "outputTokens": 40201.35321100918,
      "inputTokens": 2942251.607798165,
      "cacheTokens": 2848228.9174311925,
      "steps": 48.36697247706422,
      "peakContextTokens": 71989.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_7_flash_high",
      "model": "gemini-3-7-flash",
      "effort": "high",
      "pass": 0.6526548672566371,
      "ciHalf": 0.017878625067843174,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.1762860351216813,
      "artifactCost": null,
      "outputTokens": 107248.30309734514,
      "inputTokens": 16999853.159292035,
      "cacheTokens": 16260422.17920354,
      "steps": 124.51548672566372,
      "peakContextTokens": 221180.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_grok_4_6_high",
      "model": "grok-4-6",
      "effort": "high",
      "pass": 0.6518847006651884,
      "ciHalf": 0.015336008186572951,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 4.3848732239467845,
      "artifactCost": null,
      "outputTokens": 61160.94456762749,
      "inputTokens": 7348488.252771619,
      "cacheTokens": 7119379.299334812,
      "steps": 78.960088691796,
      "peakContextTokens": 136248,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_5_high",
      "model": "gpt-5-5",
      "effort": "high",
      "pass": 0.6438053097345132,
      "ciHalf": 0.031168426495054677,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 5.100437004424779,
      "artifactCost": null,
      "outputTokens": 31159.49778761062,
      "inputTokens": 4617781.876106195,
      "cacheTokens": 4205870.442477876,
      "steps": 61.924778761061944,
      "peakContextTokens": 107945.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_glm_5_3_flash_max",
      "model": "glm-5-3-flash",
      "effort": "max",
      "pass": 0.6339285714285714,
      "ciHalf": 0.04377970751693644,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.24098185622767856,
      "artifactCost": 0.48196371245535713,
      "outputTokens": 72829.77008928571,
      "inputTokens": 12387025.401785715,
      "cacheTokens": 11770874.857142856,
      "steps": 122.890625,
      "peakContextTokens": 136183.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_deepseek_v4_pro_max",
      "model": "deepseek-v4-pro",
      "effort": "max",
      "pass": 0.6283185840707964,
      "ciHalf": 0.06333430597228876,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.6660232187256647,
      "artifactCost": 0.24138687892256638,
      "outputTokens": 105998.91814159292,
      "inputTokens": 24191606.099557523,
      "cacheTokens": 24049100.743362833,
      "steps": 154.71238938053096,
      "peakContextTokens": 232374.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_sol_medium",
      "model": "gpt-5-6-sol",
      "effort": "medium",
      "pass": 0.6106194690265486,
      "ciHalf": 0.01583357649307215,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.4157802656590275,
      "artifactCost": 1.8620318075221238,
      "outputTokens": 18425.216814159292,
      "inputTokens": 1505793.9557522123,
      "cacheTokens": 1382962.9734513275,
      "steps": 30.913716814159294,
      "peakContextTokens": 65185,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_terra_xhigh",
      "model": "gpt-5-6-terra",
      "effort": "xhigh",
      "pass": 0.6017699115044248,
      "ciHalf": 0.021242972019271257,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.7017533805309735,
      "artifactCost": 2.127191725663717,
      "outputTokens": 39616.53982300885,
      "inputTokens": 3246355.4668141594,
      "cacheTokens": 2926653.1681415928,
      "steps": 43.06637168141593,
      "peakContextTokens": 108741,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_fable_5_low",
      "model": "claude-fable-5",
      "effort": "low",
      "pass": 0.5958429561200924,
      "ciHalf": 0.027940054451297294,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.757873125874126,
      "artifactCost": null,
      "outputTokens": 25242.833718244805,
      "inputTokens": 1691250.452655889,
      "cacheTokens": 1624197.8868360277,
      "steps": 37.79907621247113,
      "peakContextTokens": 48670,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_4_8_max",
      "model": "claude-opus-4-8",
      "effort": "max",
      "pass": 0.5897435897435898,
      "ciHalf": 0.01764815347429254,
      "runs": 4,
      "tasksAttempted": 111,
      "cost": 13.222583593240094,
      "artifactCost": null,
      "outputTokens": 135031.67132867133,
      "inputTokens": 17047938.554778554,
      "cacheTokens": 16817766.494172495,
      "steps": 120,
      "peakContextTokens": 225741,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_5_low",
      "model": "claude-opus-5",
      "effort": "low",
      "pass": 0.5812917594654788,
      "ciHalf": 0.023306879466842723,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.6626223919821828,
      "artifactCost": null,
      "outputTokens": 19884.3140311804,
      "inputTokens": 1564287.6570155902,
      "cacheTokens": 1497598.9933184856,
      "steps": 35.641425389755014,
      "peakContextTokens": 46865,
      "bill": null
    },
    {
      "config": "mini_swe_agent_qwen3_8_max_xhigh",
      "model": "qwen3-8-max",
      "effort": "xhigh",
      "pass": 0.5746102449888641,
      "ciHalf": 0.026627926725075454,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.7290646500445437,
      "artifactCost": null,
      "outputTokens": 95075.18262806236,
      "inputTokens": 12996066.461024499,
      "cacheTokens": 12477251.240534522,
      "steps": 111.33853006681514,
      "peakContextTokens": 160572,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_luna_xhigh",
      "model": "gpt-5-6-luna",
      "effort": "xhigh",
      "pass": 0.5685840707964602,
      "ciHalf": 0.021681017528097975,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.30712385371681417,
      "artifactCost": 1.5356192685840708,
      "outputTokens": 44677.900442477876,
      "inputTokens": 7610577.53539823,
      "cacheTokens": 7096152.3539823005,
      "steps": 71.09955752212389,
      "peakContextTokens": 138126.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_muse_spark_1_2_xhigh",
      "model": "muse-spark-1-2",
      "effort": "xhigh",
      "pass": 0.5486725663716814,
      "ciHalf": 0.02124297201927127,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.6955048180309733,
      "artifactCost": null,
      "outputTokens": 99226.38053097345,
      "inputTokens": 13693824.435840707,
      "cacheTokens": 12584988.949115044,
      "steps": 100.75884955752213,
      "peakContextTokens": 189481,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_4_8_xhigh",
      "model": "claude-opus-4-8",
      "effort": "xhigh",
      "pass": 0.5436241610738255,
      "ciHalf": 0.03713430628094476,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 8.006355704138702,
      "artifactCost": null,
      "outputTokens": 86088.7874720358,
      "inputTokens": 9854652.170022372,
      "cacheTokens": 9693014.304250559,
      "steps": 94.64429530201342,
      "peakContextTokens": 153870,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_5_medium",
      "model": "gpt-5-5",
      "effort": "medium",
      "pass": 0.5398230088495575,
      "ciHalf": 0.02553087495290979,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.749342734513274,
      "artifactCost": null,
      "outputTokens": 19625.433628318584,
      "inputTokens": 2438539.053097345,
      "cacheTokens": 2229359.0088495575,
      "steps": 45.982300884955755,
      "peakContextTokens": 75466,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_sonnet_5_max",
      "model": "claude-sonnet-5",
      "effort": "max",
      "pass": 0.5384615384615384,
      "ciHalf": 0.04236916470174386,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 26.399858950791852,
      "artifactCost": null,
      "outputTokens": 214117.54977375566,
      "inputTokens": 72415756.48642534,
      "cacheTokens": 71991474.90950227,
      "steps": 268.4547511312217,
      "peakContextTokens": 409978.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_terra_high",
      "model": "gpt-5-6-terra",
      "effort": "high",
      "pass": 0.5376106194690266,
      "ciHalf": 0.04328970467213552,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.9075010212389382,
      "artifactCost": 1.1343762765486725,
      "outputTokens": 21517.03982300885,
      "inputTokens": 1557052.774336283,
      "cacheTokens": 1369338.3362831858,
      "steps": 33.51327433628319,
      "peakContextTokens": 68750,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_7_flash_low",
      "model": "gemini-3-7-flash",
      "effort": "low",
      "pass": 0.5376106194690266,
      "ciHalf": 0.02589649081831869,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.8322645629424779,
      "artifactCost": null,
      "outputTokens": 73364.9557522124,
      "inputTokens": 15056565.075221239,
      "cacheTokens": 14422633.818584071,
      "steps": 130.37610619469027,
      "peakContextTokens": 168146,
      "bill": null
    },
    {
      "config": "mini_swe_agent_grok_4_5_high",
      "model": "grok-4-5",
      "effort": "high",
      "pass": 0.5376106194690266,
      "ciHalf": 0.0228080457287792,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.4157481725663716,
      "artifactCost": null,
      "outputTokens": 35525.33185840708,
      "inputTokens": 4059182.975663717,
      "cacheTokens": 3943846.5132743362,
      "steps": 61.33185840707964,
      "peakContextTokens": 94044,
      "bill": null
    },
    {
      "config": "mini_swe_agent_deepseek_v4_flash_max",
      "model": "deepseek-v4-flash",
      "effort": "max",
      "pass": 0.5331858407079646,
      "ciHalf": 0.035669502150324287,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.46407388012739975,
      "artifactCost": 0.10023560370265487,
      "outputTokens": 107687.02212389381,
      "inputTokens": 19829931.451327432,
      "cacheTokens": 19719518.867256638,
      "steps": 152.87610619469027,
      "peakContextTokens": 201636.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_muse_spark_1_1_xhigh",
      "model": "muse-spark-1-1",
      "effort": "xhigh",
      "pass": 0.5331858407079646,
      "ciHalf": 0.030353424539337114,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.361142644469026,
      "artifactCost": null,
      "outputTokens": 74008.4203539823,
      "inputTokens": 12005399.261061948,
      "cacheTokens": 11781947.471238937,
      "steps": 95.82522123893806,
      "peakContextTokens": 154817.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_4_8_high",
      "model": "claude-opus-4-8",
      "effort": "high",
      "pass": 0.5176991150442478,
      "ciHalf": 0.04561609145755843,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 4.281940017699115,
      "artifactCost": null,
      "outputTokens": 50063.52654867257,
      "inputTokens": 4908687.0265486725,
      "cacheTokens": 4807501.1283185845,
      "steps": 72.5,
      "peakContextTokens": 94158.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_4_xhigh",
      "model": "gpt-5-4",
      "effort": "xhigh",
      "pass": 0.5176991150442478,
      "ciHalf": 0.015021049567382833,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 5.6524577245575225,
      "artifactCost": null,
      "outputTokens": 71408.87389380531,
      "inputTokens": 9418920.763274336,
      "cacheTokens": 8613618.407079646,
      "steps": 70.47123893805309,
      "peakContextTokens": 172734.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_sonnet_5_xhigh",
      "model": "claude-sonnet-5",
      "effort": "xhigh",
      "pass": 0.49667405764966743,
      "ciHalf": 0.034545489916778645,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 11.890634540022173,
      "artifactCost": null,
      "outputTokens": 120698.59201773835,
      "inputTokens": 30695627.87804878,
      "cacheTokens": 30442947.99556541,
      "steps": 185.53215077605321,
      "peakContextTokens": 240780,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_4_8_medium",
      "model": "claude-opus-4-8",
      "effort": "medium",
      "pass": 0.48672566371681414,
      "ciHalf": 0.02239205861737452,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.4438571028761062,
      "artifactCost": null,
      "outputTokens": 41313.45132743363,
      "inputTokens": 3843602.6681415928,
      "cacheTokens": 3757520.9115044246,
      "steps": 65.57300884955752,
      "peakContextTokens": 79616,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_sonnet_5_high",
      "model": "claude-sonnet-5",
      "effort": "high",
      "pass": 0.4823008849557522,
      "ciHalf": 0.045063148702148406,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 7.425560161197339,
      "artifactCost": null,
      "outputTokens": 87294.75609756098,
      "inputTokens": 18254491.34368071,
      "cacheTokens": 18068889.902439024,
      "steps": 146.57649667405764,
      "peakContextTokens": 174563,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_6_flash_high",
      "model": "gemini-3-6-flash",
      "effort": "high",
      "pass": 0.4668141592920354,
      "ciHalf": 0.037048538992472776,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.209506638666667,
      "artifactCost": 4.419013277333334,
      "outputTokens": 95844.86222222222,
      "inputTokens": 12595957.344444444,
      "cacheTokens": 11254636.448888889,
      "steps": 116.73333333333333,
      "peakContextTokens": 151398.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_sol_low",
      "model": "gpt-5-6-sol",
      "effort": "low",
      "pass": 0.45353982300884954,
      "ciHalf": 0.0238819467145892,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.8170052734939612,
      "artifactCost": 1.0742664646017699,
      "outputTokens": 10579.141592920354,
      "inputTokens": 690833.657079646,
      "cacheTokens": 599908.814159292,
      "steps": 23.358407079646017,
      "peakContextTokens": 39823,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_luna_high",
      "model": "gpt-5-6-luna",
      "effort": "high",
      "pass": 0.4424778761061947,
      "ciHalf": 0.029195672479165317,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.15558014999999997,
      "artifactCost": 0.7779007499999999,
      "outputTokens": 25778.274336283186,
      "inputTokens": 3372477.7876106193,
      "cacheTokens": 3055611.469026549,
      "steps": 49.02212389380531,
      "peakContextTokens": 90166.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_glm_5_2_max",
      "model": "glm-5-2",
      "effort": "max",
      "pass": 0.43777777777777777,
      "ciHalf": 0.01725629620580811,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.9199075743111114,
      "artifactCost": null,
      "outputTokens": 78175.30666666667,
      "inputTokens": 12606560.215555556,
      "cacheTokens": 12344954.453333333,
      "steps": 129.12666666666667,
      "peakContextTokens": 142129,
      "bill": null
    },
    {
      "config": "mini_swe_agent_grok_4_6_low",
      "model": "grok-4-6",
      "effort": "low",
      "pass": 0.41648106904231624,
      "ciHalf": 0.023186517644299014,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.0423604231625836,
      "artifactCost": null,
      "outputTokens": 16458.3429844098,
      "inputTokens": 1646919.8017817372,
      "cacheTokens": 1566819.4922048997,
      "steps": 44.18708240534521,
      "peakContextTokens": 45300,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_opus_4_8_low",
      "model": "claude-opus-4-8",
      "effort": "low",
      "pass": 0.4079822616407982,
      "ciHalf": 0.014635847585691517,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.293369216740577,
      "artifactCost": null,
      "outputTokens": 28922.736141906873,
      "inputTokens": 2417987.955654102,
      "cacheTokens": 2354415.691796009,
      "steps": 53.97782705099778,
      "peakContextTokens": 57903,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_sonnet_5_medium",
      "model": "claude-sonnet-5",
      "effort": "medium",
      "pass": 0.3977777777777778,
      "ciHalf": 0.03127576206329727,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 4.079036229,
      "artifactCost": null,
      "outputTokens": 56816.753333333334,
      "inputTokens": 9286962.313333333,
      "cacheTokens": 9158953.993333334,
      "steps": 107.61111111111111,
      "peakContextTokens": 118790,
      "bill": null
    },
    {
      "config": "mini_swe_agent_glm_5_2_high",
      "model": "glm-5-2",
      "effort": "high",
      "pass": 0.36283185840707965,
      "ciHalf": 0.047500729479216554,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.8355164725663715,
      "artifactCost": null,
      "outputTokens": 54245.50442477876,
      "inputTokens": 9070605.707964601,
      "cacheTokens": 8861413.805309735,
      "steps": 121.88274336283186,
      "peakContextTokens": 102096,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_5_flash_high",
      "model": "gemini-3-5-flash",
      "effort": "high",
      "pass": 0.3606194690265487,
      "ciHalf": 0.03966303010520439,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 3.4467114588691796,
      "artifactCost": null,
      "outputTokens": 75730.19290465632,
      "inputTokens": 7629071.858093127,
      "cacheTokens": 6428494.862527716,
      "steps": 105.30376940133037,
      "peakContextTokens": 113979,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_terra_medium",
      "model": "gpt-5-6-terra",
      "effort": "medium",
      "pass": 0.3511111111111111,
      "ciHalf": 0.03381964303406632,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.46659949511111115,
      "artifactCost": 0.5832493688888889,
      "outputTokens": 11746.56,
      "inputTokens": 725100.8355555555,
      "cacheTokens": 624756.0533333333,
      "steps": 25.14666666666667,
      "peakContextTokens": 44178,
      "bill": null
    },
    {
      "config": "mini_swe_agent_kimi_k2_7_code_default",
      "model": "kimi-k2-7-code",
      "effort": null,
      "pass": 0.3053097345132743,
      "ciHalf": 0.005007016522460913,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.815536243274336,
      "artifactCost": null,
      "outputTokens": 59297.24778761062,
      "inputTokens": 13008041.482300885,
      "cacheTokens": 12857596.451327434,
      "steps": 149.1150442477876,
      "peakContextTokens": 122628.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_sonnet_5_low",
      "model": "claude-sonnet-5",
      "effort": "low",
      "pass": 0.3051224944320713,
      "ciHalf": 0.011260175414427497,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.1865550832962137,
      "artifactCost": null,
      "outputTokens": 35595.08240534521,
      "inputTokens": 4534475.699331849,
      "cacheTokens": 4449592.527839644,
      "steps": 76.88864142538975,
      "peakContextTokens": 76944,
      "bill": null
    },
    {
      "config": "mini_swe_agent_claude_sonnet_4_6_high",
      "model": "claude-sonnet-4-6",
      "effort": "high",
      "pass": 0.29933481152993346,
      "ciHalf": 0.04092141269189136,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 5.5223517987804875,
      "artifactCost": null,
      "outputTokens": 76160.31263858093,
      "inputTokens": 12870627.738359202,
      "cacheTokens": 12719994.494456762,
      "steps": 133.65853658536585,
      "peakContextTokens": 146430,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_5_low",
      "model": "gpt-5-5",
      "effort": "low",
      "pass": 0.26991150442477874,
      "ciHalf": 0.02294503222007181,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 1.2002025442477877,
      "artifactCost": null,
      "outputTokens": 9442.774336283186,
      "inputTokens": 776751.5840707965,
      "cacheTokens": 658930.407079646,
      "steps": 28.06637168141593,
      "peakContextTokens": 39278,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_terra_low",
      "model": "gpt-5-6-terra",
      "effort": "low",
      "pass": 0.24053452115812918,
      "ciHalf": 0.007767613669447833,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.3421962084632517,
      "artifactCost": 0.4277452605790646,
      "outputTokens": 8572.26280623608,
      "inputTokens": 480565.34521158127,
      "cacheTokens": 401000.90868596884,
      "steps": 21.456570155902003,
      "peakContextTokens": 33373,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gemini_3_1_pro_preview_high",
      "model": "gemini-3-1-pro-preview",
      "effort": "high",
      "pass": 0.1172566371681416,
      "ciHalf": 0.01481095461108845,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 2.1434045568888886,
      "artifactCost": null,
      "outputTokens": 28368.884444444444,
      "inputTokens": 2403677.331111111,
      "cacheTokens": 1678992.7311111111,
      "steps": 75.56444444444445,
      "peakContextTokens": 49745.5,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_luna_medium",
      "model": "gpt-5-6-luna",
      "effort": "medium",
      "pass": 0.11283185840707964,
      "ciHalf": 0.008303197562056514,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.04326195796460178,
      "artifactCost": 0.21630978982300886,
      "outputTokens": 8179.570796460177,
      "inputTokens": 617827.4800884955,
      "cacheTokens": 500661.2389380531,
      "steps": 23.67699115044248,
      "peakContextTokens": 35812,
      "bill": null
    },
    {
      "config": "mini_swe_agent_gpt_5_6_luna_low",
      "model": "gpt-5-6-luna",
      "effort": "low",
      "pass": 0.015486725663716814,
      "ciHalf": 0.008303197562056514,
      "runs": 4,
      "tasksAttempted": 113,
      "cost": 0.014481247876106192,
      "artifactCost": 0.07240623938053097,
      "outputTokens": 3127.754424778761,
      "inputTokens": 150031.52876106196,
      "cacheTokens": 107102.01769911505,
      "steps": 12.464601769911505,
      "peakContextTokens": 17490.5,
      "bill": null
    }
  ]
}