{
    "metadata": {
        "benchmark": "Vibe Code Bench v1.1",
        "slug": "vibe-code",
        "description": "Can models build web applications from scratch?",
        "benchmark_id": "vibe_code_bench",
        "family": "vibe_code_bench",
        "version": "1.1",
        "updated": "2026-11-09",
        "dataset_type": "private",
        "industry": "coding",
        "tasks": {
            "overall": "Overall"
        },
        "models": [
            "alibaba/qwen3-max",
            "alibaba/qwen3.5-plus-thinking",
            "alibaba/qwen3.6-27b",
            "alibaba/qwen3.6-plus",
            "alibaba/qwen3.7-max",
            "alibaba/qwen3.7-plus",
            "alibaba/qwen3.8-27b",
            "alibaba/qwen3.8-max",
            "alibaba/qwen3.8-max-internal",
            "ant/ling-3.0-flash-2607",
            "ant/ling-3.0-flash-af-rc3",
            "anthropic/claude-fable-5",
            "anthropic/claude-fable-5-1",
            "anthropic/claude-fable-5-2",
            "anthropic/claude-haiku-4-5-20251001-thinking",
            "anthropic/claude-haiku-5-5",
            "anthropic/claude-opus-4-5-20251101-thinking",
            "anthropic/claude-opus-4-6",
            "anthropic/claude-opus-4-6-thinking",
            "anthropic/claude-opus-4-7",
            "anthropic/claude-opus-4-8",
            "anthropic/claude-opus-4-8-claude-code",
            "anthropic/claude-opus-5",
            "anthropic/claude-opus-5-5",
            "anthropic/claude-sonnet-4-5-20250929-thinking",
            "anthropic/claude-sonnet-4-6",
            "anthropic/claude-sonnet-4-6-claude-code",
            "anthropic/claude-sonnet-5",
            "anthropic/claude-sonnet-5-5",
            "baseten/nemotron-3.5-super-vl-120b-a12b",
            "cursor/composer-2.5",
            "deepseek/deepseek-v4-flash-0731",
            "deepseek/deepseek-v4-pro",
            "deepseek/deepseek-v4-pro-0813",
            "deepseek/deepseek-v4.1-flash",
            "deepseek/deepseek-v4.1-flash-1017",
            "devin/swe-1-6-fast",
            "fireworks/deepseek-v3p2-thinking",
            "fireworks/ember-1",
            "fireworks/nemotron-lightning-3p5-30b-a3b",
            "google/gemini-2.5-pro",
            "google/gemini-3-flash-preview",
            "google/gemini-3-pro-preview",
            "google/gemini-3.1-flash-lite-preview",
            "google/gemini-3.1-pro-preview",
            "google/gemini-3.5-flash",
            "google/gemini-3.5-flash-lite",
            "google/gemini-3.6-flash",
            "google/gemini-3.7-flash",
            "google/gemini-3.8-flash",
            "google/gemini-4-argon",
            "google/gemini-4-carbon",
            "grok/grok-4-1-fast-reasoning",
            "grok/grok-4-fast-reasoning",
            "grok/grok-4.20-0309-reasoning",
            "grok/grok-4.3",
            "grok/grok-4.5",
            "grok/grok-4.6",
            "grok/grok-4.7",
            "grok/grok-build-0.1",
            "inception/mercury-2.5",
            "inception/mercury-3",
            "kimi/kimi-k2.5-thinking",
            "kimi/kimi-k2.6",
            "kimi/kimi-k2.7-code",
            "kimi/kimi-k3",
            "kimi/kimi-k3.1-pro",
            "meta/muse-ember",
            "meta/muse-spark-open",
            "meta/muse-wonder",
            "meta/muse-wonder-full",
            "meta/muse_spark",
            "meta/muse_spark_1_1",
            "meta/muse_spark_1_2",
            "meta/muse_spark_1_3",
            "meta/muse_spark_1_3_max",
            "minimax/MiniMax-M2.5",
            "minimax/MiniMax-M2.7",
            "minimax/MiniMax-M3",
            "minimax/MiniMax-M3.1-flash",
            "mistralai/mistral-large-4",
            "mistralai/mistral-large-4-oss",
            "mistralai/mistral-medium-3.5",
            "mistralai/mistral-small-2603",
            "nvidia/nemotron-3-ultra-550b-a55b",
            "openai/gpt-5-2025-08-07",
            "openai/gpt-5-mini-2025-08-07",
            "openai/gpt-5.1-2025-11-13",
            "openai/gpt-5.1-codex",
            "openai/gpt-5.1-codex-max",
            "openai/gpt-5.2-2025-12-11",
            "openai/gpt-5.2-codex",
            "openai/gpt-5.3-codex",
            "openai/gpt-5.4",
            "openai/gpt-5.4-2026-03-05",
            "openai/gpt-5.4-mini-2026-03-17",
            "openai/gpt-5.4-nano-2026-03-17",
            "openai/gpt-5.5",
            "openai/gpt-5.5-codex",
            "openai/gpt-5.5-factory",
            "openai/gpt-5.6-luna",
            "openai/gpt-5.6-sol",
            "openai/gpt-5.6-terra",
            "openai/gpt-6-astra",
            "openai/gpt-6-luna",
            "openai/gpt-6-sol",
            "openai/gpt-6.1-sol",
            "openai/gpt-6.1-terra",
            "poolside/laguna-m.1",
            "poolside/laguna-xs.2",
            "reflection/Beam-1.0",
            "stepfun/step-5-preview",
            "tencent/hy4",
            "tencent/hy4-preview",
            "thinkingmachines/inkling",
            "thinkingmachines/inkling-2-small",
            "thinkingmachines/inkling-small",
            "xiaomi/mimo-v2.5",
            "xiaomi/mimo-v2.5-pro",
            "xiaomi/mimo-v2.6-flash",
            "xiaomi/mimo-v2.6-pro",
            "zai/glm-4.6",
            "zai/glm-5-thinking",
            "zai/glm-5.1",
            "zai/glm-5.2",
            "zai/glm-5.3",
            "zai/glm-5.3-flash"
        ],
        "partners": [],
        "showBadge": false,
        "visible": true,
        "use_cost_per_test": true,
        "token_tasks_measured": 50,
        "runner": "external",
        "mode": "agentic",
        "archived": false,
        "partner": false,
        "total_models": 127
    },
    "tasks": {
        "overall": {
            "anthropic/claude-fable-5-2": {
                "accuracy": 93.771,
                "latency": 2437.279,
                "stderr": 1.152,
                "cost_per_test": 22.13226,
                "token_totals": {
                    "input_tokens": 1722388302,
                    "output_tokens": 12878299,
                    "reasoning_tokens": 3534023,
                    "cache_read_tokens": 1697180927,
                    "cache_write_tokens": 25192935
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 110.7,
                    "avg_query_seconds": 22.0,
                    "median_query_seconds": 9.4,
                    "avg_ttft_seconds": 14.4,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": "OpenHands",
                "run_date": "2026-11-08"
            },
            "anthropic/claude-sonnet-5-5": {
                "accuracy": 92.392,
                "latency": 3672.106,
                "stderr": 1.26,
                "cost_per_test": 19.729112,
                "token_totals": {
                    "input_tokens": 5822927217,
                    "output_tokens": 25491041,
                    "reasoning_tokens": 11893204,
                    "cache_read_tokens": 5760733058,
                    "cache_write_tokens": 62167153
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 219.9,
                    "avg_query_seconds": 16.7,
                    "median_query_seconds": 7.8,
                    "avg_ttft_seconds": 11.7,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands",
                "run_date": "2026-09-25"
            },
            "google/gemini-4-argon": {
                "accuracy": 91.906,
                "latency": 2247.675,
                "stderr": 1.899,
                "cost_per_test": 8.10797,
                "token_totals": {
                    "input_tokens": 451864686,
                    "output_tokens": 5436370,
                    "reasoning_tokens": 849287,
                    "cache_read_tokens": 397575696,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 72.8,
                    "avg_query_seconds": 30.9,
                    "median_query_seconds": 13.9,
                    "avg_ttft_seconds": 15.0,
                    "output_time_split": {
                        "reasoning_pct": 82.5,
                        "content_pct": 0.0,
                        "tool_call_pct": 17.5
                    }
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands",
                "run_date": "2026-09-24"
            },
            "anthropic/claude-haiku-5-5": {
                "accuracy": 90.444,
                "latency": 2075.723,
                "stderr": 1.725,
                "cost_per_test": 6.071856,
                "token_totals": {
                    "input_tokens": 4600663825,
                    "output_tokens": 23863970,
                    "reasoning_tokens": 13235182,
                    "cache_read_tokens": 4559642564,
                    "cache_write_tokens": 40996929
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 205.2,
                    "avg_query_seconds": 10.1,
                    "median_query_seconds": 4.6,
                    "avg_ttft_seconds": 7.1,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands",
                "run_date": "2026-10-07"
            },
            "anthropic/claude-fable-5": {
                "accuracy": 90.352,
                "latency": 3711.026,
                "stderr": 2.097,
                "cost_per_test": 41.714694,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "anthropic/claude-opus-5-5": {
                "accuracy": 90.294,
                "latency": 5766.524,
                "stderr": 1.526,
                "cost_per_test": 35.774773,
                "token_totals": {
                    "input_tokens": 5596583425,
                    "output_tokens": 19722501,
                    "reasoning_tokens": 7457724,
                    "cache_read_tokens": 5539450465,
                    "cache_write_tokens": 57102136
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 231.0,
                    "avg_query_seconds": 25.0,
                    "median_query_seconds": 11.6,
                    "avg_ttft_seconds": 18.9,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands",
                "run_date": "2026-09-18"
            },
            "anthropic/claude-fable-5-1": {
                "accuracy": 90.263,
                "latency": 3459.994,
                "stderr": 1.566,
                "cost_per_test": 33.367507,
                "token_totals": {
                    "input_tokens": 2858376432,
                    "output_tokens": 11229337,
                    "reasoning_tokens": 2013796,
                    "cache_read_tokens": 2826345790,
                    "cache_write_tokens": 32006248
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 191.7,
                    "avg_query_seconds": 18.0,
                    "median_query_seconds": 10.4,
                    "avg_ttft_seconds": 10.8,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands",
                "run_date": "2026-08-29"
            },
            "openai/gpt-6-astra": {
                "accuracy": 89.594,
                "latency": 2344.127,
                "stderr": 2.174,
                "cost_per_test": 38.512323,
                "token_totals": {
                    "input_tokens": 813962842,
                    "output_tokens": 7672087,
                    "reasoning_tokens": 3013580,
                    "cache_read_tokens": 762745769,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 106.1,
                    "avg_query_seconds": 22.1,
                    "median_query_seconds": 9.7,
                    "avg_ttft_seconds": 11.5,
                    "output_time_split": {
                        "reasoning_pct": 8.0,
                        "content_pct": 0.7,
                        "tool_call_pct": 91.2
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands",
                "run_date": "2026-09-03"
            },
            "google/gemini-4-carbon": {
                "accuracy": 89.06,
                "latency": 2172.019,
                "stderr": 2.294,
                "cost_per_test": 8.254926,
                "token_totals": {
                    "input_tokens": 835863332,
                    "output_tokens": 7234900,
                    "reasoning_tokens": 1180038,
                    "cache_read_tokens": 809317116,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 96.5,
                    "avg_query_seconds": 22.5,
                    "median_query_seconds": 11.4,
                    "avg_ttft_seconds": 10.9,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 1048576,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands",
                "run_date": "2026-10-24"
            },
            "openai/gpt-6.1-sol": {
                "accuracy": 88.931,
                "latency": 4489.755,
                "stderr": 1.893,
                "cost_per_test": 6.234794,
                "token_totals": {
                    "input_tokens": 1073502468,
                    "output_tokens": 10186788,
                    "reasoning_tokens": 5383848,
                    "cache_read_tokens": 1056860976,
                    "cache_write_tokens": 16623336
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 121.0,
                    "avg_query_seconds": 37.1,
                    "median_query_seconds": 12.0,
                    "avg_ttft_seconds": 26.4,
                    "output_time_split": {
                        "reasoning_pct": 6.5,
                        "content_pct": 1.2,
                        "tool_call_pct": 92.3
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands",
                "run_date": "2026-09-29"
            },
            "anthropic/claude-opus-5": {
                "accuracy": 88.404,
                "latency": 5301.22,
                "stderr": 3.001,
                "cost_per_test": 33.876235,
                "token_totals": {
                    "input_tokens": 2523942367,
                    "output_tokens": 9766836,
                    "reasoning_tokens": 1672106,
                    "cache_read_tokens": 2491300194,
                    "cache_write_tokens": 32623919
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "openai/gpt-6-sol": {
                "accuracy": 87.824,
                "latency": 2336.393,
                "stderr": 2.526,
                "cost_per_test": 26.356012,
                "token_totals": {
                    "input_tokens": 3192235437,
                    "output_tokens": 6823472,
                    "reasoning_tokens": 2395580,
                    "cache_read_tokens": 3162891655,
                    "cache_write_tokens": 29258099
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 212.7,
                    "avg_query_seconds": 11.0,
                    "median_query_seconds": 7.4,
                    "avg_ttft_seconds": 5.8,
                    "output_time_split": {
                        "reasoning_pct": 18.1,
                        "content_pct": 0.0,
                        "tool_call_pct": 81.8
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands",
                "run_date": "2026-09-22"
            },
            "deepseek/deepseek-v4.1-flash-1017": {
                "accuracy": 87.73,
                "latency": 973.834,
                "stderr": 2.752,
                "cost_per_test": 0.579984,
                "token_totals": {
                    "input_tokens": 2173326299,
                    "output_tokens": 9246207,
                    "reasoning_tokens": 3107112,
                    "cache_read_tokens": 2156782720,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 170.2,
                    "avg_query_seconds": 5.7,
                    "median_query_seconds": 3.9,
                    "avg_ttft_seconds": 2.2,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 384000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": "OpenHands",
                "run_date": "2026-10-17"
            },
            "grok/grok-4.7": {
                "accuracy": 86.175,
                "latency": 2147.065,
                "stderr": 2.181,
                "cost_per_test": 15.82706,
                "token_totals": {
                    "input_tokens": 767137889,
                    "output_tokens": 7923865,
                    "reasoning_tokens": 3838088,
                    "cache_read_tokens": 713123456,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 86.4,
                    "avg_query_seconds": 24.8,
                    "median_query_seconds": 8.5,
                    "avg_ttft_seconds": 3.4,
                    "output_time_split": {
                        "reasoning_pct": 75.7,
                        "content_pct": 4.2,
                        "tool_call_pct": 20.2
                    }
                },
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands",
                "run_date": "2026-09-21"
            },
            "meta/muse-wonder-full": {
                "accuracy": 85.996,
                "latency": 648.336,
                "stderr": 1.933,
                "cost_per_test": 2.293448,
                "token_totals": {
                    "input_tokens": 222902077,
                    "output_tokens": 2071146,
                    "reasoning_tokens": 144351,
                    "cache_read_tokens": 215357588,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 60.5,
                    "avg_query_seconds": 10.7,
                    "median_query_seconds": 5.5,
                    "avg_ttft_seconds": 6.6,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands",
                "run_date": "2026-10-10"
            },
            "meta/muse_spark_1_3_max": {
                "accuracy": 85.856,
                "latency": 977.668,
                "stderr": 2.508,
                "cost_per_test": 2.543084,
                "token_totals": {
                    "input_tokens": 651739493,
                    "output_tokens": 3048548,
                    "reasoning_tokens": 422854,
                    "cache_read_tokens": 636796800,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 118.0,
                    "avg_query_seconds": 8.3,
                    "median_query_seconds": 4.8,
                    "avg_ttft_seconds": 7.3,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands",
                "run_date": "2026-09-05"
            },
            "xiaomi/mimo-v2.6-pro": {
                "accuracy": 85.223,
                "latency": 3646.574,
                "stderr": 3.392,
                "cost_per_test": 1.043846,
                "token_totals": {
                    "input_tokens": 1076595168,
                    "output_tokens": 7478091,
                    "reasoning_tokens": 2852217,
                    "cache_read_tokens": 979676672,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 111.4,
                    "avg_query_seconds": 32.7,
                    "median_query_seconds": 18.1,
                    "avg_ttft_seconds": 13.8,
                    "output_time_split": {
                        "reasoning_pct": 36.4,
                        "content_pct": 0.7,
                        "tool_call_pct": 62.9
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": "OpenHands",
                "run_date": "2026-09-21"
            },
            "kimi/kimi-k3": {
                "accuracy": 84.968,
                "latency": 999.021,
                "stderr": 2.746,
                "cost_per_test": 10.007576,
                "token_totals": {
                    "input_tokens": 1261633418,
                    "output_tokens": 5010801,
                    "reasoning_tokens": 1248736,
                    "cache_read_tokens": 1244327217,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 139.6,
                    "avg_query_seconds": 7.2,
                    "median_query_seconds": 6.2,
                    "avg_ttft_seconds": 4.4,
                    "output_time_split": {
                        "reasoning_pct": 33.5,
                        "content_pct": 2.5,
                        "tool_call_pct": 64.1
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": "OpenHands",
                "run_date": "2026-10-01"
            },
            "kimi/kimi-k3.1-pro": {
                "accuracy": 84.894,
                "latency": 3028.937,
                "stderr": 2.949,
                "cost_per_test": 7.485151,
                "token_totals": {
                    "input_tokens": 1401107533,
                    "output_tokens": 5806937,
                    "reasoning_tokens": 1661626,
                    "cache_read_tokens": 1381126038,
                    "cache_write_tokens": 19409526
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 131.4,
                    "avg_query_seconds": 23.1,
                    "median_query_seconds": 14.0,
                    "avg_ttft_seconds": 10.5,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": "OpenHands",
                "run_date": "2026-10-23"
            },
            "deepseek/deepseek-v4.1-flash": {
                "accuracy": 84.739,
                "latency": 928.101,
                "stderr": 2.891,
                "cost_per_test": 0.407445,
                "token_totals": {
                    "input_tokens": 1429431621,
                    "output_tokens": 7186472,
                    "reasoning_tokens": 1913924,
                    "cache_read_tokens": 1418642812,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 149.4,
                    "avg_query_seconds": 6.2,
                    "median_query_seconds": 4.9,
                    "avg_ttft_seconds": 3.1,
                    "output_time_split": {
                        "reasoning_pct": 36.8,
                        "content_pct": 0.4,
                        "tool_call_pct": 62.8
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 384000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": "OpenHands",
                "run_date": "2026-09-10"
            },
            "openai/gpt-6.1-terra": {
                "accuracy": 83.997,
                "latency": 2250.002,
                "stderr": 2.865,
                "cost_per_test": 5.996953,
                "token_totals": {
                    "input_tokens": 2454324986,
                    "output_tokens": 5928692,
                    "reasoning_tokens": 1847456,
                    "cache_read_tokens": 2424165406,
                    "cache_write_tokens": 30133951
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 170.9,
                    "avg_query_seconds": 13.2,
                    "median_query_seconds": 9.4,
                    "avg_ttft_seconds": 7.0,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands",
                "run_date": "2026-10-26"
            },
            "fireworks/ember-1": {
                "accuracy": 83.869,
                "latency": 2357.968,
                "stderr": 3.151,
                "cost_per_test": 8.559507,
                "token_totals": {
                    "input_tokens": 981791343,
                    "output_tokens": 4071290,
                    "reasoning_tokens": 774425,
                    "cache_read_tokens": 954988156,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 132.4,
                    "avg_query_seconds": 17.8,
                    "median_query_seconds": 10.4,
                    "avg_ttft_seconds": 6.6,
                    "output_time_split": {
                        "reasoning_pct": 19.6,
                        "content_pct": 1.9,
                        "tool_call_pct": 78.5
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": "OpenHands",
                "run_date": "2026-09-28"
            },
            "meta/muse-ember": {
                "accuracy": 83.703,
                "latency": 167.856,
                "stderr": 2.756,
                "cost_per_test": 0.054457,
                "token_totals": {
                    "input_tokens": 267895132,
                    "output_tokens": 1887915,
                    "reasoning_tokens": 206822,
                    "cache_read_tokens": 260527092,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 70.5,
                    "avg_query_seconds": 2.4,
                    "median_query_seconds": 1.9,
                    "avg_ttft_seconds": 1.8,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 524288,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands",
                "run_date": "2026-11-03"
            },
            "meta/muse-wonder": {
                "accuracy": 83.089,
                "latency": 350.076,
                "stderr": 2.49,
                "cost_per_test": 1.802723,
                "token_totals": {
                    "input_tokens": 144518172,
                    "output_tokens": 1830347,
                    "reasoning_tokens": 114242,
                    "cache_read_tokens": 138037760,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 52.3,
                    "avg_query_seconds": 6.7,
                    "median_query_seconds": 3.6,
                    "avg_ttft_seconds": 4.3,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands",
                "run_date": "2026-10-10"
            },
            "meta/muse_spark_1_3": {
                "accuracy": 82.859,
                "latency": 773.797,
                "stderr": 2.901,
                "cost_per_test": 2.101762,
                "token_totals": {
                    "input_tokens": 401837405,
                    "output_tokens": 2713902,
                    "reasoning_tokens": 370079,
                    "cache_read_tokens": 371584301,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 95.9,
                    "avg_query_seconds": 8.1,
                    "median_query_seconds": 5.4,
                    "avg_ttft_seconds": 6.7,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands",
                "run_date": "2026-09-03"
            },
            "anthropic/claude-opus-4-8": {
                "accuracy": 82.725,
                "latency": 4549.256,
                "stderr": 3.081,
                "cost_per_test": 26.879989,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "deepseek/deepseek-v4-pro-0813": {
                "accuracy": 82.297,
                "latency": 3982.6,
                "stderr": 3.148,
                "cost_per_test": 0.356023,
                "token_totals": {
                    "input_tokens": 1830028483,
                    "output_tokens": 7746431,
                    "reasoning_tokens": 2336919,
                    "cache_read_tokens": 1820296320,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 384000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": "OpenHands"
            },
            "openai/gpt-6-luna": {
                "accuracy": 81.649,
                "latency": 2219.515,
                "stderr": 3.377,
                "cost_per_test": 1.345703,
                "token_totals": {
                    "input_tokens": 3186713261,
                    "output_tokens": 9004550,
                    "reasoning_tokens": 3632878,
                    "cache_read_tokens": 3158117507,
                    "cache_write_tokens": 28566327
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 196.2,
                    "avg_query_seconds": 11.3,
                    "median_query_seconds": 7.6,
                    "avg_ttft_seconds": 5.5,
                    "output_time_split": {
                        "reasoning_pct": 28.4,
                        "content_pct": 0.0,
                        "tool_call_pct": 71.6
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands",
                "run_date": "2026-09-22"
            },
            "mistralai/mistral-large-4-oss": {
                "accuracy": 81.555,
                "latency": 3012.646,
                "stderr": 3.289,
                "cost_per_test": 11.723179,
                "token_totals": {
                    "input_tokens": 1215599434,
                    "output_tokens": 6354662,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 441437184,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 131.9,
                    "avg_query_seconds": 22.8,
                    "median_query_seconds": 20.7,
                    "avg_ttft_seconds": 14.6,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": "OpenHands",
                "run_date": "2026-10-26"
            },
            "thinkingmachines/inkling-2-small": {
                "accuracy": 81.546,
                "latency": 1537.412,
                "stderr": 3.454,
                "cost_per_test": 1.901278,
                "token_totals": {
                    "input_tokens": 2544521097,
                    "output_tokens": 9443332,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 2510132352,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 173.8,
                    "avg_query_seconds": 8.8,
                    "median_query_seconds": 6.3,
                    "avg_ttft_seconds": 5.3,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 1024000,
                "reasoning": null,
                "reasoning_effort": "0.99",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Thinkingmachines",
                "harness": "OpenHands",
                "run_date": "2026-11-03"
            },
            "anthropic/claude-sonnet-5": {
                "accuracy": 81.325,
                "latency": 4001.424,
                "stderr": 3.046,
                "cost_per_test": 25.38542,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "tencent/hy4": {
                "accuracy": 81.008,
                "latency": 2281.498,
                "stderr": 3.548,
                "cost_per_test": 2.394585,
                "token_totals": {
                    "input_tokens": 1730119557,
                    "output_tokens": 7711952,
                    "reasoning_tokens": 3236621,
                    "cache_read_tokens": 1695048064,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 165.4,
                    "avg_query_seconds": 13.8,
                    "median_query_seconds": 9.8,
                    "avg_ttft_seconds": 6.3,
                    "output_time_split": null
                },
                "temperature": 0.9,
                "top_p": 1.0,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Tencent",
                "harness": "OpenHands",
                "run_date": "2026-11-04"
            },
            "openai/gpt-5.6-sol": {
                "accuracy": 80.495,
                "latency": 2033.047,
                "stderr": 3.716,
                "cost_per_test": 33.403634,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "meta/muse_spark_1_2": {
                "accuracy": 79.1,
                "latency": 1195.221,
                "stderr": 3.305,
                "cost_per_test": 1.529642,
                "token_totals": {
                    "input_tokens": 342866386,
                    "output_tokens": 2351182,
                    "reasoning_tokens": 239369,
                    "cache_read_tokens": 329175836,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands"
            },
            "xiaomi/mimo-v2.6-flash": {
                "accuracy": 78.96,
                "latency": 3013.012,
                "stderr": 4.045,
                "cost_per_test": 0.563041,
                "token_totals": {
                    "input_tokens": 1311689878,
                    "output_tokens": 7947370,
                    "reasoning_tokens": 3093850,
                    "cache_read_tokens": 1157695808,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 48,
                "turn_metrics": {
                    "tasks_measured": 48,
                    "avg_turns": 122.0,
                    "avg_query_seconds": 24.7,
                    "median_query_seconds": 14.8,
                    "avg_ttft_seconds": 13.5,
                    "output_time_split": {
                        "reasoning_pct": 32.7,
                        "content_pct": 0.6,
                        "tool_call_pct": 66.7
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": "OpenHands",
                "run_date": "2026-09-21"
            },
            "google/gemini-3.8-flash": {
                "accuracy": 78.651,
                "latency": 519.104,
                "stderr": 3.884,
                "cost_per_test": 6.865141,
                "token_totals": {
                    "input_tokens": 1149521706,
                    "output_tokens": 6144190,
                    "reasoning_tokens": 1439332,
                    "cache_read_tokens": 1057116240,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 146.1,
                    "avg_query_seconds": 3.6,
                    "median_query_seconds": 2.8,
                    "avg_ttft_seconds": 2.6,
                    "output_time_split": {
                        "reasoning_pct": 96.1,
                        "content_pct": 0.0,
                        "tool_call_pct": 3.9
                    }
                },
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands",
                "run_date": "2026-08-27"
            },
            "mistralai/mistral-large-4": {
                "accuracy": 78.403,
                "latency": 10395.145,
                "stderr": 3.55,
                "cost_per_test": 20.281954,
                "token_totals": {
                    "input_tokens": 1823486517,
                    "output_tokens": 8065079,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 443300864,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 183.4,
                    "avg_query_seconds": 56.7,
                    "median_query_seconds": 45.1,
                    "avg_ttft_seconds": 29.9,
                    "output_time_split": {
                        "reasoning_pct": 66.5,
                        "content_pct": 33.4,
                        "tool_call_pct": 0.1
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": "OpenHands",
                "run_date": "2026-10-04"
            },
            "zai/glm-5.3": {
                "accuracy": 78.125,
                "latency": 3847.197,
                "stderr": 3.94,
                "cost_per_test": 12.450185,
                "token_totals": {
                    "input_tokens": 1971471587,
                    "output_tokens": 8173329,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 1906590911,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 194.4,
                    "avg_query_seconds": 19.8,
                    "median_query_seconds": 8.0,
                    "avg_ttft_seconds": 11.9,
                    "output_time_split": {
                        "reasoning_pct": 42.9,
                        "content_pct": 1.1,
                        "tool_call_pct": 56.0
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": "OpenHands",
                "run_date": "2026-08-28"
            },
            "anthropic/claude-opus-4-8-claude-code": {
                "accuracy": 77.485,
                "latency": 1142.14,
                "stderr": 3.737,
                "cost_per_test": 6.8557,
                "token_totals": {
                    "input_tokens": 405940950,
                    "output_tokens": 4014200,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": "Claude Code"
            },
            "tencent/hy4-preview": {
                "accuracy": 77.478,
                "latency": 2493.104,
                "stderr": 4.035,
                "cost_per_test": 2.181516,
                "token_totals": {
                    "input_tokens": 1648623995,
                    "output_tokens": 6263219,
                    "reasoning_tokens": 1671679,
                    "cache_read_tokens": 1618107200,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 178.5,
                    "avg_query_seconds": 14.0,
                    "median_query_seconds": 8.9,
                    "avg_ttft_seconds": 5.2,
                    "output_time_split": {
                        "reasoning_pct": 31.8,
                        "content_pct": 0.8,
                        "tool_call_pct": 67.4
                    }
                },
                "temperature": 0.9,
                "top_p": 1.0,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Tencent",
                "harness": "OpenHands",
                "run_date": "2026-09-15"
            },
            "alibaba/qwen3.8-max-internal": {
                "accuracy": 77.141,
                "latency": 5079.378,
                "stderr": 3.721,
                "cost_per_test": 11.668329,
                "token_totals": {
                    "input_tokens": 1895650724,
                    "output_tokens": 8327720,
                    "reasoning_tokens": 2363284,
                    "cache_read_tokens": 1861629312,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 171.6,
                    "avg_query_seconds": 29.6,
                    "median_query_seconds": 18.6,
                    "avg_ttft_seconds": 17.6,
                    "output_time_split": {
                        "reasoning_pct": 33.2,
                        "content_pct": 0.3,
                        "tool_call_pct": 66.5
                    }
                },
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands",
                "run_date": "2026-10-12"
            },
            "openai/gpt-5.6-luna": {
                "accuracy": 77.055,
                "latency": 1551.831,
                "stderr": 3.069,
                "cost_per_test": 0.726426,
                "token_totals": {
                    "input_tokens": 54304210,
                    "output_tokens": 3660213,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "grok/grok-4.6": {
                "accuracy": 76.239,
                "latency": 1530.145,
                "stderr": 3.824,
                "cost_per_test": 4.875513,
                "token_totals": {
                    "input_tokens": 395097143,
                    "output_tokens": 3804849,
                    "reasoning_tokens": 775807,
                    "cache_read_tokens": 379498496,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "meta/muse-spark-open": {
                "accuracy": 76.187,
                "latency": 1869.172,
                "stderr": 3.317,
                "cost_per_test": 1.655609,
                "token_totals": {
                    "input_tokens": 225685852,
                    "output_tokens": 2085879,
                    "reasoning_tokens": 952456,
                    "cache_read_tokens": 189265312,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 70.3,
                    "avg_query_seconds": 26.6,
                    "median_query_seconds": 6.8,
                    "avg_ttft_seconds": 6.7,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Together AI",
                "harness": "OpenHands",
                "run_date": "2026-10-15"
            },
            "deepseek/deepseek-v4-flash-0731": {
                "accuracy": 74.736,
                "latency": 2241.572,
                "stderr": 3.442,
                "cost_per_test": 0.905592,
                "token_totals": {
                    "input_tokens": 2153389585,
                    "output_tokens": 7751888,
                    "reasoning_tokens": 2696365,
                    "cache_read_tokens": 2141888000,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 384000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": "OpenHands"
            },
            "openai/gpt-5.6-terra": {
                "accuracy": 74.594,
                "latency": 1152.433,
                "stderr": 4.203,
                "cost_per_test": 7.887015,
                "token_totals": {
                    "input_tokens": 1192383214,
                    "output_tokens": 4865371,
                    "reasoning_tokens": 1379403,
                    "cache_read_tokens": 1138222288,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 127.4,
                    "avg_query_seconds": 9.0,
                    "median_query_seconds": 5.4,
                    "avg_ttft_seconds": 4.1,
                    "output_time_split": {
                        "reasoning_pct": 23.9,
                        "content_pct": 0.0,
                        "tool_call_pct": 76.1
                    }
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands",
                "run_date": "2026-08-14"
            },
            "minimax/MiniMax-M3.1-flash": {
                "accuracy": 73.944,
                "latency": 1263.916,
                "stderr": 4.249,
                "cost_per_test": 1.146649,
                "token_totals": {
                    "input_tokens": 3334725307,
                    "output_tokens": 8488142,
                    "reasoning_tokens": 2462335,
                    "cache_read_tokens": 3318290676,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 231.6,
                    "avg_query_seconds": 5.5,
                    "median_query_seconds": 4.5,
                    "avg_ttft_seconds": 3.0,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "MiniMax",
                "harness": "OpenHands",
                "run_date": "2026-10-16"
            },
            "meta/muse_spark_1_1": {
                "accuracy": 72.158,
                "latency": 615.428,
                "stderr": 3.327,
                "cost_per_test": 0.923283,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands"
            },
            "anthropic/claude-opus-4-7": {
                "accuracy": 71.003,
                "latency": 2141.902,
                "stderr": 4.506,
                "cost_per_test": 21.407199,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "stepfun/step-5-preview": {
                "accuracy": 70.399,
                "latency": 5466.358,
                "stderr": 4.267,
                "cost_per_test": 5.856257,
                "token_totals": {
                    "input_tokens": 2504815838,
                    "output_tokens": 8182685,
                    "reasoning_tokens": 0,
                    "cache_read_tokens": 2351680256,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 231.7,
                    "avg_query_seconds": 23.6,
                    "median_query_seconds": 18.0,
                    "avg_ttft_seconds": 14.0,
                    "output_time_split": {
                        "reasoning_pct": 38.8,
                        "content_pct": 2.1,
                        "tool_call_pct": 59.1
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 1024000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Stepfun",
                "harness": "OpenHands",
                "run_date": "2026-10-02"
            },
            "google/gemini-3.7-flash": {
                "accuracy": 70.395,
                "latency": 1423.494,
                "stderr": 4.837,
                "cost_per_test": 4.827643,
                "token_totals": {
                    "input_tokens": 911735026,
                    "output_tokens": 5880420,
                    "reasoning_tokens": 1013076,
                    "cache_read_tokens": 866906330,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "openai/gpt-5.5": {
                "accuracy": 69.847,
                "latency": 1911.567,
                "stderr": 4.535,
                "cost_per_test": 16.661911,
                "token_totals": {
                    "input_tokens": 92633221,
                    "output_tokens": 3089898,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "grok/grok-4.5": {
                "accuracy": 69.002,
                "latency": 830.057,
                "stderr": 4.48,
                "cost_per_test": 4.102194,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "openai/gpt-5.4-2026-03-05": {
                "accuracy": 67.421,
                "latency": 5174.848,
                "stderr": 4.843,
                "cost_per_test": 10.686976,
                "token_totals": {
                    "input_tokens": 90113056,
                    "output_tokens": 5822598,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "openai/gpt-5.5-factory": {
                "accuracy": 67.391,
                "latency": 1177.43,
                "stderr": 4.75,
                "cost_per_test": 5.9268,
                "token_totals": {
                    "input_tokens": 341996100,
                    "output_tokens": 2443400,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "Factory"
            },
            "reflection/Beam-1.0": {
                "accuracy": 66.436,
                "latency": 145.263,
                "stderr": 4.062,
                "cost_per_test": null,
                "token_totals": {
                    "input_tokens": 430528251,
                    "output_tokens": 2004844,
                    "reasoning_tokens": 550281,
                    "cache_read_tokens": 419321600,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 129.5,
                    "avg_query_seconds": 1.1,
                    "median_query_seconds": 0.6,
                    "avg_ttft_seconds": 0.5,
                    "output_time_split": null
                },
                "temperature": 0.7,
                "top_p": 0.99,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Reflection",
                "harness": "OpenHands",
                "run_date": "2026-10-16"
            },
            "alibaba/qwen3.8-27b": {
                "accuracy": 64.85,
                "latency": 2619.407,
                "stderr": 4.825,
                "cost_per_test": 23.456372,
                "token_totals": {
                    "input_tokens": 2292687899,
                    "output_tokens": 8824879,
                    "reasoning_tokens": 3211356,
                    "cache_read_tokens": 0,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 203.2,
                    "avg_query_seconds": 12.9,
                    "median_query_seconds": 10.3,
                    "avg_ttft_seconds": 7.2,
                    "output_time_split": {
                        "reasoning_pct": 45.6,
                        "content_pct": 1.9,
                        "tool_call_pct": 52.5
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands",
                "run_date": "2026-08-17"
            },
            "alibaba/qwen3.8-max": {
                "accuracy": 64.696,
                "latency": 10135.139,
                "stderr": 5.362,
                "cost_per_test": 8.238852,
                "token_totals": {
                    "input_tokens": 966988648,
                    "output_tokens": 5955904,
                    "reasoning_tokens": 1971427,
                    "cache_read_tokens": 890154368,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "google/gemini-3.6-flash": {
                "accuracy": 64.005,
                "latency": 1523.201,
                "stderr": 4.29,
                "cost_per_test": 3.041993,
                "token_totals": {
                    "input_tokens": 419948837,
                    "output_tokens": 4065006,
                    "reasoning_tokens": 715555,
                    "cache_read_tokens": 376526772,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "zai/glm-5.2": {
                "accuracy": 63.961,
                "latency": 3748.167,
                "stderr": 4.795,
                "cost_per_test": 8.488514,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": "OpenHands"
            },
            "openai/gpt-5.3-codex": {
                "accuracy": 61.767,
                "latency": 4548.115,
                "stderr": 4.714,
                "cost_per_test": 11.914536,
                "token_totals": {
                    "input_tokens": 192538209,
                    "output_tokens": 4009383,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "inception/mercury-3": {
                "accuracy": 60.927,
                "latency": 566.58,
                "stderr": 5.379,
                "cost_per_test": 0.627191,
                "token_totals": {
                    "input_tokens": 1422007111,
                    "output_tokens": 6493005,
                    "reasoning_tokens": 5135055,
                    "cache_read_tokens": 1256819130,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 171.6,
                    "avg_query_seconds": 3.3,
                    "median_query_seconds": 2.2,
                    "avg_ttft_seconds": 2.5,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Inception",
                "harness": "OpenHands",
                "run_date": "2026-10-19"
            },
            "openai/gpt-5.5-codex": {
                "accuracy": 58.194,
                "latency": 708.51,
                "stderr": 4.933,
                "cost_per_test": 3.6264,
                "token_totals": {
                    "input_tokens": 167963850,
                    "output_tokens": 2018400,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "Codex"
            },
            "anthropic/claude-opus-4-6": {
                "accuracy": 57.573,
                "latency": 1278.658,
                "stderr": 4.371,
                "cost_per_test": 8.687436,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": false,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "anthropic/claude-sonnet-4-6-claude-code": {
                "accuracy": 55.774,
                "latency": 2982.342,
                "stderr": 4.682,
                "cost_per_test": 7.354471,
                "token_totals": {
                    "input_tokens": 896566178,
                    "output_tokens": 362124,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 869510565,
                    "cache_write_tokens": 27028887
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": "Claude Code"
            },
            "openai/gpt-5.2-2025-12-11": {
                "accuracy": 53.499,
                "latency": 4971.341,
                "stderr": 5.067,
                "cost_per_test": 17.745182,
                "token_totals": {
                    "input_tokens": 302477783,
                    "output_tokens": 4406663,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "anthropic/claude-opus-4-6-thinking": {
                "accuracy": 53.498,
                "latency": 1386.056,
                "stderr": 4.678,
                "cost_per_test": 8.279062,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": true,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "anthropic/claude-sonnet-4-6": {
                "accuracy": 51.476,
                "latency": 1572.118,
                "stderr": 4.645,
                "cost_per_test": 5.907892,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": true,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "deepseek/deepseek-v4-pro": {
                "accuracy": 49.931,
                "latency": 3418.92,
                "stderr": 4.767,
                "cost_per_test": 2.205991,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": "OpenHands"
            },
            "cursor/composer-2.5": {
                "accuracy": 49.614,
                "latency": 592.9,
                "stderr": 4.972,
                "cost_per_test": 0.502233,
                "token_totals": {
                    "input_tokens": 94458506,
                    "output_tokens": 2029275,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 200000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Cursor",
                "harness": "Cursor CLI"
            },
            "google/gemini-3.5-flash": {
                "accuracy": 48.683,
                "latency": 893.074,
                "stderr": 4.727,
                "cost_per_test": 2.540385,
                "token_totals": {
                    "input_tokens": 64968703,
                    "output_tokens": 3285132,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "openai/gpt-5.4": {
                "accuracy": 48.474,
                "latency": 1075.396,
                "stderr": 5.07,
                "cost_per_test": 7.50518,
                "token_totals": {
                    "input_tokens": 428145333,
                    "output_tokens": 3610264,
                    "reasoning_tokens": 934026,
                    "cache_read_tokens": 410377472,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "Codex"
            },
            "openai/gpt-5.4-mini-2026-03-17": {
                "accuracy": 47.969,
                "latency": 2055.117,
                "stderr": 5.606,
                "cost_per_test": 1.191299,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "alibaba/qwen3.7-max": {
                "accuracy": 47.671,
                "latency": 4689.627,
                "stderr": 4.63,
                "cost_per_test": 11.400322,
                "token_totals": {
                    "input_tokens": 197229291,
                    "output_tokens": 2354762,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "minimax/MiniMax-M3": {
                "accuracy": 47.566,
                "latency": 5073.23,
                "stderr": 5.442,
                "cost_per_test": 6.453899,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 512000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": "OpenHands"
            },
            "kimi/kimi-k2.7-code": {
                "accuracy": 47.211,
                "latency": 10318.246,
                "stderr": 5.191,
                "cost_per_test": 3.835806,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": "OpenHands"
            },
            "alibaba/qwen3.7-plus": {
                "accuracy": 46.391,
                "latency": 2231.75,
                "stderr": 4.614,
                "cost_per_test": 1.082348,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "xiaomi/mimo-v2.5": {
                "accuracy": 42.174,
                "latency": 1580.348,
                "stderr": 4.568,
                "cost_per_test": 0.068395,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": "OpenHands"
            },
            "openai/gpt-5.2-codex": {
                "accuracy": 37.912,
                "latency": 1934.792,
                "stderr": 4.576,
                "cost_per_test": 4.152495,
                "token_totals": {
                    "input_tokens": 40226294,
                    "output_tokens": 2658691,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "kimi/kimi-k2.6": {
                "accuracy": 37.891,
                "latency": 2967.768,
                "stderr": 4.912,
                "cost_per_test": 1.925351,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": "OpenHands"
            },
            "google/gemini-3.5-flash-lite": {
                "accuracy": 37.161,
                "latency": 501.522,
                "stderr": 4.627,
                "cost_per_test": 0.833111,
                "token_totals": {
                    "input_tokens": 387765124,
                    "output_tokens": 3360015,
                    "reasoning_tokens": 658865,
                    "cache_read_tokens": 307681641,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "xiaomi/mimo-v2.5-pro": {
                "accuracy": 34.113,
                "latency": 2403.764,
                "stderr": 4.529,
                "cost_per_test": 0.166747,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": "OpenHands"
            },
            "google/gemini-3.1-pro-preview": {
                "accuracy": 32.034,
                "latency": 1211.906,
                "stderr": 4.342,
                "cost_per_test": 3.825202,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "zai/glm-5.1": {
                "accuracy": 31.456,
                "latency": 2014.732,
                "stderr": 4.553,
                "cost_per_test": 2.894911,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": "OpenHands"
            },
            "zai/glm-5.3-flash": {
                "accuracy": 30.759,
                "latency": 5027.281,
                "stderr": 5.277,
                "cost_per_test": 4.69761,
                "token_totals": {
                    "input_tokens": 7308851703,
                    "output_tokens": 11916569,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 7228379520,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 556.0,
                    "avg_query_seconds": 9.0,
                    "median_query_seconds": 5.5,
                    "avg_ttft_seconds": 3.1,
                    "output_time_split": {
                        "reasoning_pct": 37.2,
                        "content_pct": 1.7,
                        "tool_call_pct": 61.1
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": "OpenHands",
                "run_date": "2026-08-28"
            },
            "openai/gpt-5.4-nano-2026-03-17": {
                "accuracy": 26.097,
                "latency": 3276.224,
                "stderr": 5.075,
                "cost_per_test": 1.277298,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "alibaba/qwen3.6-plus": {
                "accuracy": 25.565,
                "latency": 2289.977,
                "stderr": 3.906,
                "cost_per_test": 5.447636,
                "token_totals": {
                    "input_tokens": 479493282,
                    "output_tokens": 2653745,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "openai/gpt-5.1-2025-11-13": {
                "accuracy": 24.606,
                "latency": 1836.188,
                "stderr": 4.254,
                "cost_per_test": 2.574926,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "zai/glm-5-thinking": {
                "accuracy": 23.359,
                "latency": 13455.794,
                "stderr": 4.034,
                "cost_per_test": 40.270258,
                "token_totals": {
                    "input_tokens": 1954171739,
                    "output_tokens": 2870967,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": "OpenHands"
            },
            "anthropic/claude-sonnet-4-5-20250929-thinking": {
                "accuracy": 22.621,
                "latency": 2962.133,
                "stderr": 3.728,
                "cost_per_test": 6.656984,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "openai/gpt-5.1-codex-max": {
                "accuracy": 22.168,
                "latency": 31182.938,
                "stderr": 3.84,
                "cost_per_test": 7.324105,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "anthropic/claude-opus-4-5-20251101-thinking": {
                "accuracy": 20.63,
                "latency": 2283.142,
                "stderr": 3.159,
                "cost_per_test": 32.873283,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "google/gemini-3-flash-preview": {
                "accuracy": 20.204,
                "latency": 806.66,
                "stderr": 3.946,
                "cost_per_test": 0.942067,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "openai/gpt-5-2025-08-07": {
                "accuracy": 20.088,
                "latency": 1852.149,
                "stderr": 3.409,
                "cost_per_test": 1.525167,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "meta/muse_spark": {
                "accuracy": 19.674,
                "latency": 981.298,
                "stderr": 3.966,
                "cost_per_test": 0.579705,
                "token_totals": {
                    "input_tokens": 184911334,
                    "output_tokens": 2080918,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": "OpenHands"
            },
            "grok/grok-4.3": {
                "accuracy": 19.403,
                "latency": 589.407,
                "stderr": 4.243,
                "cost_per_test": 1.28472,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "thinkingmachines/inkling": {
                "accuracy": 19.214,
                "latency": 1105.492,
                "stderr": 3.659,
                "cost_per_test": 1.605949,
                "token_totals": {
                    "input_tokens": 391977485,
                    "output_tokens": 2288277,
                    "reasoning_tokens": 0,
                    "cache_read_tokens": 386683776,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "0.99",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Thinkingmachines",
                "harness": "OpenHands"
            },
            "thinkingmachines/inkling-small": {
                "accuracy": 19.052,
                "latency": 2949.469,
                "stderr": 3.403,
                "cost_per_test": 0.432264,
                "token_totals": {
                    "input_tokens": 294407624,
                    "output_tokens": 2135670,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 289327616,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 262000,
                "reasoning": null,
                "reasoning_effort": "0.99",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Thinkingmachines",
                "harness": "OpenHands"
            },
            "kimi/kimi-k2.5-thinking": {
                "accuracy": 17.536,
                "latency": 2570.381,
                "stderr": 3.258,
                "cost_per_test": 0.879292,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": "OpenHands"
            },
            "alibaba/qwen3.5-plus-thinking": {
                "accuracy": 15.738,
                "latency": 3015.618,
                "stderr": 3.179,
                "cost_per_test": 3.803761,
                "token_totals": {
                    "input_tokens": 459410090,
                    "output_tokens": 2440928,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 0.6,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "minimax/MiniMax-M2.5": {
                "accuracy": 14.853,
                "latency": 3065.622,
                "stderr": 2.953,
                "cost_per_test": 2.197729,
                "token_totals": {
                    "input_tokens": 348550236,
                    "output_tokens": 2628151,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": "OpenHands"
            },
            "google/gemini-3-pro-preview": {
                "accuracy": 14.3,
                "latency": 10398.545,
                "stderr": 3.061,
                "cost_per_test": 6.417592,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "openai/gpt-5-mini-2025-08-07": {
                "accuracy": 14.171,
                "latency": 698.246,
                "stderr": 3.539,
                "cost_per_test": 0.248587,
                "token_totals": {
                    "input_tokens": 26079914,
                    "output_tokens": 1087208,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "grok/grok-build-0.1": {
                "accuracy": 13.349,
                "latency": 394.638,
                "stderr": 3.819,
                "cost_per_test": null,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "Grok Build"
            },
            "openai/gpt-5.1-codex": {
                "accuracy": 13.115,
                "latency": 3026.069,
                "stderr": 3.161,
                "cost_per_test": 3.797914,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": "OpenHands"
            },
            "alibaba/qwen3.6-27b": {
                "accuracy": 11.941,
                "latency": 9762.856,
                "stderr": 3.414,
                "cost_per_test": 4.655127,
                "token_totals": {
                    "input_tokens": 363862398,
                    "output_tokens": 2524854,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 0,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 49,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "minimax/MiniMax-M2.7": {
                "accuracy": 11.926,
                "latency": 1377.326,
                "stderr": 2.857,
                "cost_per_test": 2.819109,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": "OpenHands"
            },
            "anthropic/claude-haiku-4-5-20251001-thinking": {
                "accuracy": 11.393,
                "latency": 775.882,
                "stderr": 3.129,
                "cost_per_test": 1.306474,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": "OpenHands"
            },
            "poolside/laguna-m.1": {
                "accuracy": 11.038,
                "latency": 2381.926,
                "stderr": 2.822,
                "cost_per_test": 2.059401,
                "token_totals": {
                    "input_tokens": 90126692,
                    "output_tokens": 3112565,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Poolside",
                "harness": "OpenHands"
            },
            "nvidia/nemotron-3-ultra-550b-a55b": {
                "accuracy": 7.636,
                "latency": 2217.462,
                "stderr": 2.783,
                "cost_per_test": null,
                "token_totals": {
                    "input_tokens": 1965727676,
                    "output_tokens": 5440855,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Nvidia",
                "harness": "OpenHands"
            },
            "devin/swe-1-6-fast": {
                "accuracy": 7.22,
                "latency": 189.132,
                "stderr": 2.635,
                "cost_per_test": null,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 0,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Devin",
                "harness": "Devin CLI"
            },
            "poolside/laguna-xs.2": {
                "accuracy": 5.212,
                "latency": 2199.244,
                "stderr": 2.18,
                "cost_per_test": 0.981155,
                "token_totals": {
                    "input_tokens": 312422657,
                    "output_tokens": 2581908,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Poolside",
                "harness": "OpenHands"
            },
            "fireworks/deepseek-v3p2-thinking": {
                "accuracy": 5.108,
                "latency": 3365.726,
                "stderr": 2.127,
                "cost_per_test": 2.469325,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": "OpenHands"
            },
            "grok/grok-4.20-0309-reasoning": {
                "accuracy": 4.063,
                "latency": 301.651,
                "stderr": 2.058,
                "cost_per_test": 0.771885,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "baseten/nemotron-3.5-super-vl-120b-a12b": {
                "accuracy": 3.71,
                "latency": 262.905,
                "stderr": 1.926,
                "cost_per_test": 0.539233,
                "token_totals": {
                    "input_tokens": 419784036,
                    "output_tokens": 2901901,
                    "reasoning_tokens": 402890,
                    "cache_read_tokens": 365288192,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 116.8,
                    "avg_query_seconds": 2.3,
                    "median_query_seconds": 1.3,
                    "avg_ttft_seconds": 1.5,
                    "output_time_split": null
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Baseten",
                "harness": "OpenHands",
                "run_date": "2026-10-28"
            },
            "inception/mercury-2.5": {
                "accuracy": 3.683,
                "latency": 193.041,
                "stderr": 1.407,
                "cost_per_test": 0.378016,
                "token_totals": {
                    "input_tokens": 198612247,
                    "output_tokens": 1426011,
                    "reasoning_tokens": 1298893,
                    "cache_read_tokens": 121617600,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 85.0,
                    "avg_query_seconds": 2.3,
                    "median_query_seconds": 1.6,
                    "avg_ttft_seconds": 1.8,
                    "output_time_split": null
                },
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Inception",
                "harness": "OpenHands",
                "run_date": "2026-09-10"
            },
            "alibaba/qwen3-max": {
                "accuracy": 3.506,
                "latency": 3465.17,
                "stderr": 1.292,
                "cost_per_test": 6.023105,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": "OpenHands"
            },
            "ant/ling-3.0-flash-af-rc3": {
                "accuracy": 3.4,
                "latency": 1451.032,
                "stderr": 1.291,
                "cost_per_test": 0.233022,
                "token_totals": {
                    "input_tokens": 666603077,
                    "output_tokens": 7351064,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 618088896,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 114.0,
                    "avg_query_seconds": 12.7,
                    "median_query_seconds": 5.0,
                    "avg_ttft_seconds": 2.3,
                    "output_time_split": {
                        "reasoning_pct": 7.1,
                        "content_pct": 53.9,
                        "tool_call_pct": 38.9
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Ant",
                "harness": "OpenHands",
                "run_date": "2026-09-17"
            },
            "zai/glm-4.6": {
                "accuracy": 3.09,
                "latency": 10002.446,
                "stderr": 1.162,
                "cost_per_test": 10.845475,
                "temperature": 0.6,
                "top_p": 1.0,
                "max_output_tokens": 122880,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": "OpenHands"
            },
            "ant/ling-3.0-flash-2607": {
                "accuracy": 2.914,
                "latency": 1005.598,
                "stderr": 2.072,
                "cost_per_test": 0.292199,
                "token_totals": {
                    "input_tokens": 779810749,
                    "output_tokens": 3806141,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 745220087,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 0.6,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Ant",
                "harness": "OpenHands"
            },
            "mistralai/mistral-medium-3.5": {
                "accuracy": 2.888,
                "latency": 2470.533,
                "stderr": 1.713,
                "cost_per_test": 16.735503,
                "token_totals": {
                    "input_tokens": 538194513,
                    "output_tokens": 3931115,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 80000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": "OpenHands"
            },
            "grok/grok-4-1-fast-reasoning": {
                "accuracy": 1.2,
                "latency": 527.562,
                "stderr": 1.2,
                "cost_per_test": 0.209444,
                "token_totals": {
                    "input_tokens": 16252556,
                    "output_tokens": 831827,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "google/gemini-2.5-pro": {
                "accuracy": 0.4,
                "latency": 2097.144,
                "stderr": 0.4,
                "cost_per_test": 1.223831,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "google/gemini-3.1-flash-lite-preview": {
                "accuracy": 0.0,
                "latency": 572.711,
                "stderr": 0.0,
                "cost_per_test": 0.51,
                "token_totals": {
                    "input_tokens": 53939702,
                    "output_tokens": 1042512,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 50,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": "OpenHands"
            },
            "fireworks/nemotron-lightning-3p5-30b-a3b": {
                "accuracy": 0.0,
                "latency": 959.662,
                "stderr": 0.0,
                "cost_per_test": 0.128799,
                "token_totals": {
                    "input_tokens": 535193452,
                    "output_tokens": 3346611,
                    "reasoning_tokens": null,
                    "cache_read_tokens": 524725810,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "turn_metrics": {
                    "tasks_measured": 50,
                    "avg_turns": 144.2,
                    "avg_query_seconds": 6.7,
                    "median_query_seconds": 1.5,
                    "avg_ttft_seconds": 3.1,
                    "output_time_split": {
                        "reasoning_pct": 33.5,
                        "content_pct": 33.6,
                        "tool_call_pct": 32.8
                    }
                },
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": "OpenHands",
                "run_date": "2026-08-11"
            },
            "grok/grok-4-fast-reasoning": {
                "accuracy": 0.0,
                "latency": 1448.855,
                "stderr": 0.0,
                "cost_per_test": 0.133206,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": "OpenHands"
            },
            "mistralai/mistral-small-2603": {
                "accuracy": 0.0,
                "latency": 1814.681,
                "stderr": 0.0,
                "cost_per_test": 6.473001,
                "token_totals": {
                    "input_tokens": 2145609935,
                    "output_tokens": 3014270,
                    "reasoning_tokens": null,
                    "cache_read_tokens": null,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 50,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": "OpenHands"
            }
        }
    }
}