{
    "metadata": {
        "benchmark": "IOI v1",
        "slug": "ioi-v1",
        "description": "Based on the International Olympiad in Informatics",
        "benchmark_id": "ioi_v1",
        "family": "ioi",
        "version": "1",
        "updated": "2026-08-09",
        "dataset_type": "public",
        "industry": "coding",
        "tasks": {
            "overall": "Overall",
            "ioi2024": "IOI 2024",
            "ioi2025": "IOI 2025"
        },
        "models": [
            "alibaba/qwen3-max",
            "alibaba/qwen3-max-2026-01-23",
            "alibaba/qwen3-max-preview",
            "alibaba/qwen3.7-max",
            "alibaba/qwen3.8-max",
            "anthropic/claude-fable-5",
            "anthropic/claude-haiku-4-5-20251001-thinking",
            "anthropic/claude-opus-4-1-20250805",
            "anthropic/claude-opus-4-5-20251101",
            "anthropic/claude-opus-4-5-20251101-thinking",
            "anthropic/claude-opus-4-7",
            "anthropic/claude-opus-5",
            "anthropic/claude-sonnet-4-20250514",
            "anthropic/claude-sonnet-4-20250514-thinking",
            "anthropic/claude-sonnet-4-5-20250929-thinking",
            "deepseek/deepseek-v4-pro",
            "fireworks/deepseek-v3-0324",
            "fireworks/deepseek-v3p2",
            "fireworks/deepseek-v3p2-thinking",
            "fireworks/qwen3-235b-a22b",
            "google/gemini-2.5-flash",
            "google/gemini-2.5-pro",
            "google/gemini-3-flash-preview",
            "google/gemini-3-pro-preview",
            "google/gemini-3.5-flash-lite",
            "grok/grok-4-0709",
            "grok/grok-4-1-fast-non-reasoning",
            "grok/grok-4-1-fast-reasoning",
            "grok/grok-4-fast-non-reasoning",
            "grok/grok-4-fast-reasoning",
            "grok/grok-4.20-0309-reasoning",
            "grok/grok-4.3",
            "grok/grok-code-fast-1",
            "kimi/kimi-k2.5-thinking",
            "meta/muse_spark_1_2",
            "minimax/MiniMax-M2.1",
            "minimax/MiniMax-M2.5",
            "minimax/MiniMax-M2.7",
            "mistralai/devstral-2512",
            "mistralai/labs-devstral-small-2512",
            "mistralai/magistral-medium-2509",
            "mistralai/mistral-large-2512",
            "openai/gpt-5-2025-08-07",
            "openai/gpt-5-codex",
            "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-5.3-codex",
            "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-5.6-luna",
            "openai/gpt-5.6-sol",
            "openai/gpt-5.6-terra",
            "openai/o4-mini-2025-04-16",
            "together/moonshotai/Kimi-K2-Instruct",
            "zai/glm-4.5",
            "zai/glm-4.6",
            "zai/glm-4.7",
            "zai/glm-5-thinking"
        ],
        "partners": [],
        "showBadge": false,
        "visible": true,
        "use_cost_per_test": false,
        "runner": "custom",
        "mode": "agentic",
        "archived": true,
        "partner": false,
        "total_models": 62
    },
    "tasks": {
        "overall": {
            "anthropic/claude-opus-5": {
                "accuracy": 91.667,
                "latency": 1693.04,
                "stderr": 8.333,
                "cost_per_test": 5.541014,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.6-sol": {
                "accuracy": 86.667,
                "latency": 1310.679,
                "stderr": 1.667,
                "cost_per_test": 2.98545,
                "token_totals": {
                    "input_tokens": 8111299,
                    "output_tokens": 362342,
                    "reasoning_tokens": 307844,
                    "cache_read_tokens": 7447568,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 6,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "alibaba/qwen3.8-max": {
                "accuracy": 73.0,
                "latency": 3946.139,
                "stderr": 1.0,
                "cost_per_test": 2.392116,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "openai/gpt-5.6-luna": {
                "accuracy": 72.917,
                "latency": 1670.558,
                "stderr": 5.083,
                "cost_per_test": 0.262867,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-fable-5": {
                "accuracy": 72.25,
                "latency": 3318.969,
                "stderr": 9.357,
                "cost_per_test": 15.101678,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.4-2026-03-05": {
                "accuracy": 67.834,
                "latency": 2660.886,
                "stderr": 9.867,
                "cost_per_test": 3.471332,
                "avg_input_tokens": 3111734.8,
                "avg_output_tokens": 127091.0,
                "avg_reasoning_tokens": 91293.3,
                "avg_cache_read_tokens": 2761941.4,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.6-terra": {
                "accuracy": 65.25,
                "latency": 1330.749,
                "stderr": 0.917,
                "cost_per_test": 0.97448,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.2-2025-12-11": {
                "accuracy": 54.833,
                "latency": 6739.612,
                "stderr": 8.318,
                "cost_per_test": 3.871992,
                "avg_input_tokens": 2146870.9,
                "avg_output_tokens": 142786.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "meta/muse_spark_1_2": {
                "accuracy": 49.5,
                "latency": 4771.52,
                "stderr": 3.667,
                "cost_per_test": 6.100817,
                "token_totals": {
                    "input_tokens": 91784656,
                    "output_tokens": 2070730,
                    "reasoning_tokens": 1453110,
                    "cache_read_tokens": 79024104,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 6,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": null
            },
            "anthropic/claude-opus-4-7": {
                "accuracy": 47.084,
                "latency": 3081.905,
                "stderr": 8.704,
                "cost_per_test": 10.486954,
                "avg_input_tokens": 3958856.4,
                "avg_output_tokens": 227220.5,
                "avg_cache_read_tokens": 3467196.1,
                "avg_cache_write_tokens": 491632.8,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "alibaba/qwen3.7-max": {
                "accuracy": 46.75,
                "latency": 4380.294,
                "stderr": 10.263,
                "cost_per_test": 4.859648,
                "avg_input_tokens": 2893590.0,
                "avg_output_tokens": 287807.0,
                "avg_reasoning_tokens": 264261.0,
                "avg_cache_read_tokens": 2014613.3,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "openai/gpt-5.3-codex": {
                "accuracy": 43.834,
                "latency": 3574.257,
                "stderr": 7.81,
                "cost_per_test": 2.020025,
                "avg_input_tokens": 2128679.8,
                "avg_output_tokens": 96712.9,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "google/gemini-3-flash-preview": {
                "accuracy": 39.084,
                "latency": 1846.526,
                "stderr": 10.545,
                "cost_per_test": 0.375052,
                "avg_input_tokens": 1286051.5,
                "avg_output_tokens": 70681.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "google/gemini-3-pro-preview": {
                "accuracy": 38.834,
                "latency": 900.44,
                "stderr": 11.492,
                "cost_per_test": 0.331188,
                "avg_input_tokens": 104174.5,
                "avg_output_tokens": 10236.6,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65535,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "deepseek/deepseek-v4-pro": {
                "accuracy": 35.833,
                "latency": 5373.876,
                "stderr": 7.139,
                "cost_per_test": 0.568564,
                "avg_input_tokens": 6758593.9,
                "avg_output_tokens": 189617.6,
                "avg_reasoning_tokens": 134333.0,
                "avg_cache_read_tokens": 6542402.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "grok/grok-4.20-0309-reasoning": {
                "accuracy": 30.166,
                "latency": 896.93,
                "stderr": 7.489,
                "cost_per_test": 0.709499,
                "avg_input_tokens": 610400.0,
                "avg_output_tokens": 75423.9,
                "avg_reasoning_tokens": 70471.4,
                "avg_cache_read_tokens": 556835.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "google/gemini-3.5-flash-lite": {
                "accuracy": 26.167,
                "latency": 882.37,
                "stderr": 1.167,
                "cost_per_test": 0.636385,
                "token_totals": {
                    "input_tokens": 24147621,
                    "output_tokens": 423418,
                    "reasoning_tokens": 222934,
                    "cache_read_tokens": 16609343,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 6,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "grok/grok-4-0709": {
                "accuracy": 26.167,
                "latency": 4265.882,
                "stderr": 6.763,
                "cost_per_test": 2.693986,
                "avg_input_tokens": 630057.2,
                "avg_output_tokens": 86144.8,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101": {
                "accuracy": 23.584,
                "latency": 7682.383,
                "stderr": 7.547,
                "cost_per_test": 3.048735,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "zai/glm-5-thinking": {
                "accuracy": 22.0,
                "latency": 6806.938,
                "stderr": 7.832,
                "cost_per_test": 3.273674,
                "avg_input_tokens": 4847320.8,
                "avg_output_tokens": 112527.6,
                "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": null
            },
            "openai/gpt-5.1-2025-11-13": {
                "accuracy": 21.5,
                "latency": 1750.069,
                "stderr": 7.336,
                "cost_per_test": 0.368193,
                "avg_input_tokens": 183697.8,
                "avg_output_tokens": 13857.1,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.1-codex-max": {
                "accuracy": 21.416,
                "latency": 956.692,
                "stderr": 6.995,
                "cost_per_test": 0.422645,
                "avg_input_tokens": 256701.2,
                "avg_output_tokens": 10176.8,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101-thinking": {
                "accuracy": 20.25,
                "latency": 8211.492,
                "stderr": 5.157,
                "cost_per_test": 3.9235,
                "avg_input_tokens": 370.1,
                "avg_output_tokens": 156866.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5-2025-08-07": {
                "accuracy": 20.0,
                "latency": 2608.252,
                "stderr": 4.581,
                "cost_per_test": 1.629264,
                "avg_input_tokens": 275834.5,
                "avg_output_tokens": 128447.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": "medium",
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-sonnet-4-5-20250929-thinking": {
                "accuracy": 18.334,
                "latency": 3315.166,
                "stderr": 5.918,
                "cost_per_test": 3.07299,
                "avg_input_tokens": 802193.2,
                "avg_output_tokens": 44427.3,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "kimi/kimi-k2.5-thinking": {
                "accuracy": 17.667,
                "latency": 3828.386,
                "stderr": 6.084,
                "cost_per_test": 0.677261,
                "avg_input_tokens": 2229026.1,
                "avg_output_tokens": 134792.8,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": null
            },
            "google/gemini-2.5-pro": {
                "accuracy": 17.084,
                "latency": 2964.799,
                "stderr": 6.17,
                "cost_per_test": 0.615461,
                "avg_input_tokens": 279613.5,
                "avg_output_tokens": 26594.4,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "alibaba/qwen3-max": {
                "accuracy": 15.666,
                "latency": 2045.247,
                "stderr": 6.352,
                "cost_per_test": 0.824523,
                "avg_input_tokens": 520216.8,
                "avg_output_tokens": 33377.1,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "grok/grok-4.3": {
                "accuracy": 15.334,
                "latency": 628.816,
                "stderr": 6.313,
                "cost_per_test": 0.351754,
                "avg_input_tokens": 564315.1,
                "avg_output_tokens": 64106.7,
                "avg_reasoning_tokens": 57861.0,
                "avg_cache_read_tokens": 489434.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "openai/gpt-5.4-nano-2026-03-17": {
                "accuracy": 15.25,
                "latency": 1170.492,
                "stderr": 6.438,
                "cost_per_test": 0.042833,
                "avg_input_tokens": 877443.2,
                "avg_output_tokens": 86687.1,
                "avg_reasoning_tokens": 73259.4,
                "avg_cache_read_tokens": 793642.6,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "fireworks/deepseek-v3p2": {
                "accuracy": 14.416,
                "latency": 2384.516,
                "stderr": 4.496,
                "cost_per_test": 0.05196,
                "avg_input_tokens": 4249.6,
                "avg_output_tokens": 29512.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "none",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "alibaba/qwen3-max-2026-01-23": {
                "accuracy": 13.75,
                "latency": 2953.233,
                "stderr": 3.547,
                "cost_per_test": 1.901446,
                "avg_input_tokens": 510043.0,
                "avg_output_tokens": 93580.4,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "anthropic/claude-opus-4-1-20250805": {
                "accuracy": 12.516,
                "latency": 6124.896,
                "stderr": 4.913,
                "cost_per_test": 17.585952,
                "avg_input_tokens": 997542.3,
                "avg_output_tokens": 34970.9,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 32000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "grok/grok-4-fast-reasoning": {
                "accuracy": 11.5,
                "latency": 1408.454,
                "stderr": 4.388,
                "cost_per_test": 0.97412,
                "avg_input_tokens": 1335858.5,
                "avg_output_tokens": 1413897.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "fireworks/deepseek-v3p2-thinking": {
                "accuracy": 10.667,
                "latency": 1558.619,
                "stderr": 3.089,
                "cost_per_test": 0.058713,
                "avg_input_tokens": 50676.9,
                "avg_output_tokens": 18055.8,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "openai/gpt-5-codex": {
                "accuracy": 9.75,
                "latency": 1542.894,
                "stderr": 7.717,
                "cost_per_test": 2.669955,
                "avg_input_tokens": 1435225.2,
                "avg_output_tokens": 87592.4,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "alibaba/qwen3-max-preview": {
                "accuracy": 7.75,
                "latency": 3372.048,
                "stderr": 3.165,
                "cost_per_test": 1.399136,
                "avg_input_tokens": 1277152.2,
                "avg_output_tokens": 37429.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "grok/grok-4-1-fast-non-reasoning": {
                "accuracy": 7.667,
                "latency": 7675.292,
                "stderr": 3.198,
                "cost_per_test": 0.06955,
                "avg_input_tokens": 270945.7,
                "avg_output_tokens": 30719.8,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "zai/glm-4.7": {
                "accuracy": 7.584,
                "latency": 5316.876,
                "stderr": 3.404,
                "cost_per_test": 0.443515,
                "avg_input_tokens": 1552932.6,
                "avg_output_tokens": 48322.6,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "openai/gpt-5-mini-2025-08-07": {
                "accuracy": 6.75,
                "latency": 390.378,
                "stderr": 3.316,
                "cost_per_test": 0.039168,
                "avg_input_tokens": 69879.0,
                "avg_output_tokens": 10848.9,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": "high",
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "minimax/MiniMax-M2.5": {
                "accuracy": 6.666,
                "latency": 22887.998,
                "stderr": 2.641,
                "cost_per_test": 1.501416,
                "avg_input_tokens": 4332998.5,
                "avg_output_tokens": 86408.9,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514": {
                "accuracy": 6.5,
                "latency": 3253.12,
                "stderr": 2.096,
                "cost_per_test": 2.388928,
                "avg_input_tokens": 679864.8,
                "avg_output_tokens": 23289.0,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.4-mini-2026-03-17": {
                "accuracy": 6.417,
                "latency": 1896.804,
                "stderr": 3.607,
                "cost_per_test": 0.35057,
                "avg_input_tokens": 1265346.0,
                "avg_output_tokens": 132676.8,
                "avg_reasoning_tokens": 121166.0,
                "avg_cache_read_tokens": 1027200.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-haiku-4-5-20251001-thinking": {
                "accuracy": 6.166,
                "latency": 7415.352,
                "stderr": 2.515,
                "cost_per_test": 2.133406,
                "avg_input_tokens": 1786445.0,
                "avg_output_tokens": 69392.2,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "minimax/MiniMax-M2.7": {
                "accuracy": 4.916,
                "latency": 3242.758,
                "stderr": 2.379,
                "cost_per_test": 1.154876,
                "avg_input_tokens": 3424865.0,
                "avg_output_tokens": 109783.1,
                "avg_cache_read_tokens": 16980.4,
                "avg_cache_write_tokens": 3490.8,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "openai/o4-mini-2025-04-16": {
                "accuracy": 4.834,
                "latency": 480.192,
                "stderr": 2.355,
                "cost_per_test": 0.156077,
                "avg_input_tokens": 44475.2,
                "avg_output_tokens": 24353.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 100000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514-thinking": {
                "accuracy": 4.584,
                "latency": 2216.287,
                "stderr": 1.139,
                "cost_per_test": 1.329832,
                "avg_input_tokens": 361606.8,
                "avg_output_tokens": 16334.1,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "zai/glm-4.6": {
                "accuracy": 4.334,
                "latency": 7105.854,
                "stderr": 2.485,
                "cost_per_test": 1.516537,
                "avg_input_tokens": 2707515.0,
                "avg_output_tokens": 65549.0,
                "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": null
            },
            "grok/grok-code-fast-1": {
                "accuracy": 4.333,
                "latency": 1083.862,
                "stderr": 1.157,
                "cost_per_test": 1.61801,
                "avg_input_tokens": 873912.0,
                "avg_output_tokens": 962152.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 40000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "mistralai/mistral-large-2512": {
                "accuracy": 4.0,
                "latency": 6788.576,
                "stderr": 1.46,
                "cost_per_test": 3.073948,
                "avg_input_tokens": 5730229.8,
                "avg_output_tokens": 139221.8,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.065,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "grok/grok-4-fast-non-reasoning": {
                "accuracy": 3.834,
                "latency": 577.632,
                "stderr": 2.848,
                "cost_per_test": 0.12675,
                "avg_input_tokens": 172617.8,
                "avg_output_tokens": 184453.6,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "openai/gpt-5.1-codex": {
                "accuracy": 3.666,
                "latency": 2227.442,
                "stderr": 3.347,
                "cost_per_test": 0.176857,
                "avg_input_tokens": 44275.2,
                "avg_output_tokens": 12151.2,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "grok/grok-4-1-fast-reasoning": {
                "accuracy": 3.084,
                "latency": 1533.288,
                "stderr": 1.749,
                "cost_per_test": 0.02997,
                "avg_input_tokens": 124370.1,
                "avg_output_tokens": 10190.6,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "zai/glm-4.5": {
                "accuracy": 2.917,
                "latency": 2336.43,
                "stderr": 0.987,
                "cost_per_test": 0.942275,
                "avg_input_tokens": 1292285.2,
                "avg_output_tokens": 75865.2,
                "temperature": 0.6,
                "top_p": 1.0,
                "max_output_tokens": 81920,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "google/gemini-2.5-flash": {
                "accuracy": 2.611,
                "latency": 350.186,
                "stderr": 1.03,
                "cost_per_test": 0.036998,
                "avg_input_tokens": 58583.2,
                "avg_output_tokens": 7769.1,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "mistralai/labs-devstral-small-2512": {
                "accuracy": 2.5,
                "latency": 7466.603,
                "stderr": 1.781,
                "cost_per_test": 0.50569,
                "avg_input_tokens": 4792353.6,
                "avg_output_tokens": 88182.0,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.2,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "minimax/MiniMax-M2.1": {
                "accuracy": 2.334,
                "latency": 5210.402,
                "stderr": 1.3,
                "cost_per_test": 0.319345,
                "avg_input_tokens": 1611250.4,
                "avg_output_tokens": 82905.4,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "fireworks/deepseek-v3-0324": {
                "accuracy": 1.667,
                "latency": 171.479,
                "stderr": 0.9,
                "cost_per_test": 0.606484,
                "avg_input_tokens": 665967.5,
                "avg_output_tokens": 7903.6,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "together/moonshotai/Kimi-K2-Instruct": {
                "accuracy": 1.25,
                "latency": 1551.101,
                "stderr": 0.632,
                "cost_per_test": 2.367573,
                "avg_input_tokens": 2257202.1,
                "avg_output_tokens": 36790.4,
                "avg_reasoning_tokens": 0.0,
                "temperature": 0.6,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Together AI",
                "harness": null
            },
            "mistralai/magistral-medium-2509": {
                "accuracy": 0.666,
                "latency": 2211.783,
                "stderr": 0.444,
                "cost_per_test": 6.344222,
                "avg_input_tokens": 2965557.2,
                "avg_output_tokens": 82621.5,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 1.0,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "mistralai/devstral-2512": {
                "accuracy": 0.666,
                "latency": 8044.645,
                "stderr": 0.608,
                "cost_per_test": 1.753753,
                "avg_input_tokens": 4070057.1,
                "avg_output_tokens": 62865.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.2,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "fireworks/qwen3-235b-a22b": {
                "accuracy": 0.0,
                "latency": 352.565,
                "stderr": 0.0,
                "cost_per_test": 0.109574,
                "avg_input_tokens": 375794.5,
                "avg_output_tokens": 30567.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 16384,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            }
        },
        "ioi2024": {
            "anthropic/claude-opus-5": {
                "accuracy": 100.0,
                "latency": 1737.255,
                "stderr": 0.0,
                "cost_per_test": 6.45987,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "anthropic/claude-fable-5": {
                "accuracy": 100.0,
                "latency": 2540.44,
                "stderr": 0.0,
                "cost_per_test": 15.68634,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.6-sol": {
                "accuracy": 85.0,
                "latency": 1314.969,
                "stderr": 13.693,
                "cost_per_test": 3.002041,
                "token_totals": {
                    "input_tokens": 10317678,
                    "output_tokens": 349355,
                    "reasoning_tokens": 282948,
                    "cache_read_tokens": 9790399,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 6,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.6-luna": {
                "accuracy": 78.0,
                "latency": 1730.527,
                "stderr": 13.904,
                "cost_per_test": 0.260799,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "alibaba/qwen3.8-max": {
                "accuracy": 72.0,
                "latency": 3819.907,
                "stderr": 13.392,
                "cost_per_test": 1.999003,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "openai/gpt-5.4-2026-03-05": {
                "accuracy": 67.167,
                "latency": 2241.026,
                "stderr": 14.878,
                "cost_per_test": 3.371664,
                "avg_input_tokens": 3085697.7,
                "avg_output_tokens": 124750.7,
                "avg_reasoning_tokens": 91532.3,
                "avg_cache_read_tokens": 2761706.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.6-terra": {
                "accuracy": 66.167,
                "latency": 678.342,
                "stderr": 14.997,
                "cost_per_test": 0.818561,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.3-codex": {
                "accuracy": 58.167,
                "latency": 2631.97,
                "stderr": 14.481,
                "cost_per_test": 1.818037,
                "avg_input_tokens": 2060938.7,
                "avg_output_tokens": 89108.8,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-opus-4-7": {
                "accuracy": 53.167,
                "latency": 2569.514,
                "stderr": 14.854,
                "cost_per_test": 9.010059,
                "avg_input_tokens": 2313633.7,
                "avg_output_tokens": 196826.8,
                "avg_cache_read_tokens": 1803617.0,
                "avg_cache_write_tokens": 509996.8,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "meta/muse_spark_1_2": {
                "accuracy": 45.833,
                "latency": 5252.146,
                "stderr": 15.842,
                "cost_per_test": 7.024904,
                "token_totals": {
                    "input_tokens": 83449414,
                    "output_tokens": 2270344,
                    "reasoning_tokens": 1692829,
                    "cache_read_tokens": 65283007,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 6,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": null
            },
            "openai/gpt-5.2-2025-12-11": {
                "accuracy": 43.833,
                "latency": 7378.658,
                "stderr": 12.379,
                "cost_per_test": 4.02342,
                "avg_input_tokens": 2379847.3,
                "avg_output_tokens": 145795.8,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "google/gemini-3-flash-preview": {
                "accuracy": 41.0,
                "latency": 2307.779,
                "stderr": 17.098,
                "cost_per_test": 0.401804,
                "avg_input_tokens": 1552270.2,
                "avg_output_tokens": 72440.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "alibaba/qwen3.7-max": {
                "accuracy": 40.5,
                "latency": 4033.028,
                "stderr": 17.613,
                "cost_per_test": 4.69984,
                "avg_input_tokens": 2365448.3,
                "avg_output_tokens": 279020.2,
                "avg_reasoning_tokens": 261596.7,
                "avg_cache_read_tokens": 1469525.3,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "google/gemini-3-pro-preview": {
                "accuracy": 38.5,
                "latency": 1079.286,
                "stderr": 17.904,
                "cost_per_test": 0.328592,
                "avg_input_tokens": 105008.8,
                "avg_output_tokens": 9881.2,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65535,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "deepseek/deepseek-v4-pro": {
                "accuracy": 31.333,
                "latency": 5262.744,
                "stderr": 10.426,
                "cost_per_test": 0.580726,
                "avg_input_tokens": 7402429.6,
                "avg_output_tokens": 188545.0,
                "avg_reasoning_tokens": 131255.6,
                "avg_cache_read_tokens": 7183257.6,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "google/gemini-3.5-flash-lite": {
                "accuracy": 25.0,
                "latency": 1087.865,
                "stderr": 14.652,
                "cost_per_test": 0.708425,
                "token_totals": {
                    "input_tokens": 27132786,
                    "output_tokens": 473906,
                    "reasoning_tokens": 240717,
                    "cache_read_tokens": 18792784,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 6,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "zai/glm-5-thinking": {
                "accuracy": 23.667,
                "latency": 7231.432,
                "stderr": 11.716,
                "cost_per_test": 2.864289,
                "avg_input_tokens": 4774476.5,
                "avg_output_tokens": 103191.8,
                "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": null
            },
            "grok/grok-4-0709": {
                "accuracy": 23.167,
                "latency": 4824.866,
                "stderr": 11.985,
                "cost_per_test": 1.953434,
                "avg_input_tokens": 548064.2,
                "avg_output_tokens": 85730.5,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "grok/grok-4.20-0309-reasoning": {
                "accuracy": 22.5,
                "latency": 622.262,
                "stderr": 12.057,
                "cost_per_test": 0.654763,
                "avg_input_tokens": 428960.3,
                "avg_output_tokens": 75398.0,
                "avg_reasoning_tokens": 71344.3,
                "avg_cache_read_tokens": 364192.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "alibaba/qwen3-max": {
                "accuracy": 21.5,
                "latency": 1069.464,
                "stderr": 12.27,
                "cost_per_test": 0.415113,
                "avg_input_tokens": 210142.2,
                "avg_output_tokens": 27157.0,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101": {
                "accuracy": 20.667,
                "latency": 11576.195,
                "stderr": 11.43,
                "cost_per_test": 2.959818,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-2.5-pro": {
                "accuracy": 19.0,
                "latency": 2159.535,
                "stderr": 10.263,
                "cost_per_test": 0.842034,
                "avg_input_tokens": 413361.8,
                "avg_output_tokens": 32533.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-sonnet-4-5-20250929-thinking": {
                "accuracy": 19.0,
                "latency": 2583.917,
                "stderr": 10.263,
                "cost_per_test": 2.711026,
                "avg_input_tokens": 710801.0,
                "avg_output_tokens": 38574.8,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "anthropic/claude-opus-4-1-20250805": {
                "accuracy": 18.667,
                "latency": 5926.555,
                "stderr": 9.657,
                "cost_per_test": 15.554335,
                "avg_input_tokens": 857014.0,
                "avg_output_tokens": 35988.3,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 32000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101-thinking": {
                "accuracy": 18.0,
                "latency": 4779.544,
                "stderr": 5.452,
                "cost_per_test": 3.923563,
                "avg_input_tokens": 331.0,
                "avg_output_tokens": 156876.3,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.1-codex-max": {
                "accuracy": 14.5,
                "latency": 975.205,
                "stderr": 9.757,
                "cost_per_test": 0.49262,
                "avg_input_tokens": 282354.3,
                "avg_output_tokens": 13967.7,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.4-nano-2026-03-17": {
                "accuracy": 14.167,
                "latency": 967.635,
                "stderr": 6.269,
                "cost_per_test": 0.035235,
                "avg_input_tokens": 461999.8,
                "avg_output_tokens": 78731.0,
                "avg_reasoning_tokens": 70120.7,
                "avg_cache_read_tokens": 430165.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "fireworks/deepseek-v3p2": {
                "accuracy": 14.0,
                "latency": 1615.658,
                "stderr": 6.364,
                "cost_per_test": 0.052688,
                "avg_input_tokens": 4429.5,
                "avg_output_tokens": 29885.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "none",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "grok/grok-4.3": {
                "accuracy": 13.0,
                "latency": 555.026,
                "stderr": 6.272,
                "cost_per_test": 0.32626,
                "avg_input_tokens": 505701.7,
                "avg_output_tokens": 60952.2,
                "avg_reasoning_tokens": 55836.3,
                "avg_cache_read_tokens": 436426.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "alibaba/qwen3-max-2026-01-23": {
                "accuracy": 12.333,
                "latency": 3278.996,
                "stderr": 5.124,
                "cost_per_test": 1.949747,
                "avg_input_tokens": 540495.8,
                "avg_output_tokens": 95207.8,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "kimi/kimi-k2.5-thinking": {
                "accuracy": 12.167,
                "latency": 3195.697,
                "stderr": 5.041,
                "cost_per_test": 0.561257,
                "avg_input_tokens": 1353032.2,
                "avg_output_tokens": 127550.8,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": null
            },
            "openai/gpt-5.1-2025-11-13": {
                "accuracy": 11.833,
                "latency": 1702.974,
                "stderr": 6.126,
                "cost_per_test": 0.363369,
                "avg_input_tokens": 168091.0,
                "avg_output_tokens": 15325.5,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "alibaba/qwen3-max-preview": {
                "accuracy": 11.667,
                "latency": 1362.606,
                "stderr": 5.728,
                "cost_per_test": 2.276975,
                "avg_input_tokens": 2025083.6,
                "avg_output_tokens": 50378.2,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "fireworks/deepseek-v3p2-thinking": {
                "accuracy": 11.167,
                "latency": 1374.876,
                "stderr": 5.32,
                "cost_per_test": 0.050024,
                "avg_input_tokens": 43612.3,
                "avg_output_tokens": 15238.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "openai/gpt-5-2025-08-07": {
                "accuracy": 11.0,
                "latency": 2627.572,
                "stderr": 4.967,
                "cost_per_test": 1.870345,
                "avg_input_tokens": 412865.0,
                "avg_output_tokens": 135426.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": "medium",
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "zai/glm-4.7": {
                "accuracy": 10.5,
                "latency": 3615.545,
                "stderr": 5.882,
                "cost_per_test": 0.384617,
                "avg_input_tokens": 1258372.3,
                "avg_output_tokens": 47854.5,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514": {
                "accuracy": 9.667,
                "latency": 2018.192,
                "stderr": 3.949,
                "cost_per_test": 2.080064,
                "avg_input_tokens": 567886.2,
                "avg_output_tokens": 25093.7,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "grok/grok-4-fast-reasoning": {
                "accuracy": 9.333,
                "latency": 1370.235,
                "stderr": 4.305,
                "cost_per_test": 1.353118,
                "avg_input_tokens": 1872571.3,
                "avg_output_tokens": 1957208.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "openai/o4-mini-2025-04-16": {
                "accuracy": 7.667,
                "latency": 376.345,
                "stderr": 4.647,
                "cost_per_test": 0.114606,
                "avg_input_tokens": 31078.8,
                "avg_output_tokens": 18277.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 100000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "grok/grok-4-1-fast-non-reasoning": {
                "accuracy": 7.667,
                "latency": 4647.63,
                "stderr": 5.13,
                "cost_per_test": 0.047983,
                "avg_input_tokens": 175099.7,
                "avg_output_tokens": 25925.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "minimax/MiniMax-M2.5": {
                "accuracy": 7.5,
                "latency": 17357.397,
                "stderr": 4.458,
                "cost_per_test": 1.508215,
                "avg_input_tokens": 4326244.0,
                "avg_output_tokens": 90341.0,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "openai/gpt-5.4-mini-2026-03-17": {
                "accuracy": 6.667,
                "latency": 1876.864,
                "stderr": 4.513,
                "cost_per_test": 0.384694,
                "avg_input_tokens": 1638391.3,
                "avg_output_tokens": 137586.5,
                "avg_reasoning_tokens": 124562.8,
                "avg_cache_read_tokens": 1333674.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5-mini-2025-08-07": {
                "accuracy": 6.5,
                "latency": 272.805,
                "stderr": 4.37,
                "cost_per_test": 0.033967,
                "avg_input_tokens": 58767.2,
                "avg_output_tokens": 9637.5,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": "high",
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-haiku-4-5-20251001-thinking": {
                "accuracy": 6.5,
                "latency": 4391.967,
                "stderr": 4.383,
                "cost_per_test": 2.10517,
                "avg_input_tokens": 1763331.0,
                "avg_output_tokens": 68367.8,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "mistralai/mistral-large-2512": {
                "accuracy": 6.5,
                "latency": 7790.385,
                "stderr": 2.786,
                "cost_per_test": 3.946165,
                "avg_input_tokens": 7374782.3,
                "avg_output_tokens": 172515.8,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.065,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "grok/grok-4-fast-non-reasoning": {
                "accuracy": 6.167,
                "latency": 307.059,
                "stderr": 5.629,
                "cost_per_test": 0.173256,
                "avg_input_tokens": 235702.7,
                "avg_output_tokens": 252230.0,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "google/gemini-2.5-flash": {
                "accuracy": 5.222,
                "latency": 623.818,
                "stderr": 2.059,
                "cost_per_test": 0.07068,
                "avg_input_tokens": 106115.4,
                "avg_output_tokens": 15538.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514-thinking": {
                "accuracy": 5.167,
                "latency": 1431.232,
                "stderr": 1.892,
                "cost_per_test": 1.023628,
                "avg_input_tokens": 260701.8,
                "avg_output_tokens": 16101.5,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "mistralai/labs-devstral-small-2512": {
                "accuracy": 3.667,
                "latency": 858.154,
                "stderr": 3.347,
                "cost_per_test": 0.513867,
                "avg_input_tokens": 4863815.8,
                "avg_output_tokens": 91619.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.2,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "grok/grok-code-fast-1": {
                "accuracy": 3.333,
                "latency": 867.087,
                "stderr": 1.925,
                "cost_per_test": 2.032726,
                "avg_input_tokens": 1110286.8,
                "avg_output_tokens": 1207112.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 40000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "zai/glm-4.5": {
                "accuracy": 3.167,
                "latency": 2172.987,
                "stderr": 1.535,
                "cost_per_test": 1.093628,
                "avg_input_tokens": 1532796.2,
                "avg_output_tokens": 79068.2,
                "temperature": 0.6,
                "top_p": 1.0,
                "max_output_tokens": 81920,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "openai/gpt-5-codex": {
                "accuracy": 2.833,
                "latency": 1650.37,
                "stderr": 2.586,
                "cost_per_test": 2.583712,
                "avg_input_tokens": 1338925.5,
                "avg_output_tokens": 91005.5,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "fireworks/deepseek-v3-0324": {
                "accuracy": 1.667,
                "latency": 144.646,
                "stderr": 1.521,
                "cost_per_test": 0.106655,
                "avg_input_tokens": 113991.2,
                "avg_output_tokens": 4514.8,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "zai/glm-4.6": {
                "accuracy": 1.0,
                "latency": 6110.323,
                "stderr": 0.577,
                "cost_per_test": 2.024354,
                "avg_input_tokens": 3101403.2,
                "avg_output_tokens": 74323.7,
                "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": null
            },
            "grok/grok-4-1-fast-reasoning": {
                "accuracy": 0.5,
                "latency": 1364.023,
                "stderr": 0.456,
                "cost_per_test": 0.01707,
                "avg_input_tokens": 70433.2,
                "avg_output_tokens": 5965.8,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "together/moonshotai/Kimi-K2-Instruct": {
                "accuracy": 0.5,
                "latency": 1542.884,
                "stderr": 0.456,
                "cost_per_test": 2.42593,
                "avg_input_tokens": 2309624.7,
                "avg_output_tokens": 38768.5,
                "avg_reasoning_tokens": 0.0,
                "temperature": 0.6,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Together AI",
                "harness": null
            },
            "mistralai/magistral-medium-2509": {
                "accuracy": 0.5,
                "latency": 2735.47,
                "stderr": 0.456,
                "cost_per_test": 8.012136,
                "avg_input_tokens": 3750936.2,
                "avg_output_tokens": 102052.7,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 1.0,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "minimax/MiniMax-M2.7": {
                "accuracy": 0.5,
                "latency": 3472.218,
                "stderr": 0.456,
                "cost_per_test": 1.262533,
                "avg_input_tokens": 3754837.0,
                "avg_output_tokens": 116984.5,
                "avg_cache_read_tokens": 17174.5,
                "avg_cache_write_tokens": 4495.5,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "fireworks/qwen3-235b-a22b": {
                "accuracy": 0.0,
                "latency": 303.027,
                "stderr": 0.0,
                "cost_per_test": 0.066363,
                "avg_input_tokens": 194145.8,
                "avg_output_tokens": 26875.5,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 16384,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "mistralai/devstral-2512": {
                "accuracy": 0.0,
                "latency": 683.82,
                "stderr": 0.0,
                "cost_per_test": 1.817543,
                "avg_input_tokens": 4179678.7,
                "avg_output_tokens": 72836.0,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.2,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "openai/gpt-5.1-codex": {
                "accuracy": 0.0,
                "latency": 2326.487,
                "stderr": 0.0,
                "cost_per_test": 0.201958,
                "avg_input_tokens": 45114.0,
                "avg_output_tokens": 14556.5,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "minimax/MiniMax-M2.1": {
                "accuracy": 0.0,
                "latency": 4937.493,
                "stderr": 0.0,
                "cost_per_test": 0.233531,
                "avg_input_tokens": 824445.5,
                "avg_output_tokens": 86656.2,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            }
        },
        "ioi2025": {
            "openai/gpt-5.6-sol": {
                "accuracy": 88.333,
                "latency": 1306.389,
                "stderr": 10.65,
                "cost_per_test": 2.96886,
                "token_totals": {
                    "input_tokens": 5904920,
                    "output_tokens": 375329,
                    "reasoning_tokens": 332739,
                    "cache_read_tokens": 5104736,
                    "cache_write_tokens": null
                },
                "token_tasks_measured": 6,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-opus-5": {
                "accuracy": 83.333,
                "latency": 1648.826,
                "stderr": 16.667,
                "cost_per_test": 4.438387,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "alibaba/qwen3.8-max": {
                "accuracy": 74.0,
                "latency": 4072.372,
                "stderr": 15.882,
                "cost_per_test": 2.785229,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "openai/gpt-5.4-2026-03-05": {
                "accuracy": 68.5,
                "latency": 3080.746,
                "stderr": 12.965,
                "cost_per_test": 3.571001,
                "avg_input_tokens": 3137771.8,
                "avg_output_tokens": 129431.2,
                "avg_reasoning_tokens": 91054.3,
                "avg_cache_read_tokens": 2762176.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.6-luna": {
                "accuracy": 67.833,
                "latency": 1610.589,
                "stderr": 15.511,
                "cost_per_test": 0.264936,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.2-2025-12-11": {
                "accuracy": 65.833,
                "latency": 6100.567,
                "stderr": 11.114,
                "cost_per_test": 3.720564,
                "avg_input_tokens": 1913894.5,
                "avg_output_tokens": 139776.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.6-terra": {
                "accuracy": 64.333,
                "latency": 1983.157,
                "stderr": 12.199,
                "cost_per_test": 1.130399,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "meta/muse_spark_1_2": {
                "accuracy": 53.167,
                "latency": 4290.894,
                "stderr": 14.321,
                "cost_per_test": 5.176731,
                "token_totals": {
                    "input_tokens": 100119897,
                    "output_tokens": 1871115,
                    "reasoning_tokens": 1213390,
                    "cache_read_tokens": 92765202,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 6,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": null
            },
            "alibaba/qwen3.7-max": {
                "accuracy": 53.0,
                "latency": 4727.561,
                "stderr": 10.541,
                "cost_per_test": 5.019455,
                "avg_input_tokens": 3421731.8,
                "avg_output_tokens": 296593.8,
                "avg_reasoning_tokens": 266925.3,
                "avg_cache_read_tokens": 2559701.3,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "anthropic/claude-fable-5": {
                "accuracy": 44.5,
                "latency": 4097.498,
                "stderr": 18.714,
                "cost_per_test": 14.517016,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "anthropic/claude-opus-4-7": {
                "accuracy": 41.0,
                "latency": 3594.296,
                "stderr": 9.077,
                "cost_per_test": 11.963848,
                "avg_input_tokens": 5604079.2,
                "avg_output_tokens": 257614.2,
                "avg_cache_read_tokens": 5130775.2,
                "avg_cache_write_tokens": 473268.8,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "deepseek/deepseek-v4-pro": {
                "accuracy": 40.333,
                "latency": 5485.007,
                "stderr": 9.754,
                "cost_per_test": 0.556402,
                "avg_input_tokens": 6114758.2,
                "avg_output_tokens": 190690.3,
                "avg_reasoning_tokens": 137410.3,
                "avg_cache_read_tokens": 5901546.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "google/gemini-3-pro-preview": {
                "accuracy": 39.167,
                "latency": 721.594,
                "stderr": 14.411,
                "cost_per_test": 0.333784,
                "avg_input_tokens": 103340.2,
                "avg_output_tokens": 10592.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65535,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "grok/grok-4.20-0309-reasoning": {
                "accuracy": 37.833,
                "latency": 1171.599,
                "stderr": 8.886,
                "cost_per_test": 0.764235,
                "avg_input_tokens": 791839.6,
                "avg_output_tokens": 75449.8,
                "avg_reasoning_tokens": 69598.4,
                "avg_cache_read_tokens": 749478.4,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "google/gemini-3-flash-preview": {
                "accuracy": 37.167,
                "latency": 1385.274,
                "stderr": 12.346,
                "cost_per_test": 0.3483,
                "avg_input_tokens": 1019832.8,
                "avg_output_tokens": 68922.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "openai/gpt-5.1-2025-11-13": {
                "accuracy": 31.167,
                "latency": 1797.164,
                "stderr": 13.332,
                "cost_per_test": 0.373017,
                "avg_input_tokens": 199304.5,
                "avg_output_tokens": 12388.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.3-codex": {
                "accuracy": 29.5,
                "latency": 4516.544,
                "stderr": 5.854,
                "cost_per_test": 2.222013,
                "avg_input_tokens": 2196421.0,
                "avg_output_tokens": 104317.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "grok/grok-4-0709": {
                "accuracy": 29.167,
                "latency": 3706.897,
                "stderr": 6.269,
                "cost_per_test": 3.434538,
                "avg_input_tokens": 712050.2,
                "avg_output_tokens": 86559.2,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "openai/gpt-5-2025-08-07": {
                "accuracy": 29.0,
                "latency": 2588.931,
                "stderr": 7.699,
                "cost_per_test": 1.388182,
                "avg_input_tokens": 138804.0,
                "avg_output_tokens": 121467.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": "medium",
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.1-codex-max": {
                "accuracy": 28.333,
                "latency": 938.178,
                "stderr": 10.027,
                "cost_per_test": 0.35267,
                "avg_input_tokens": 231048.2,
                "avg_output_tokens": 6386.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "google/gemini-3.5-flash-lite": {
                "accuracy": 27.333,
                "latency": 676.876,
                "stderr": 10.257,
                "cost_per_test": 0.564344,
                "token_totals": {
                    "input_tokens": 21162456,
                    "output_tokens": 372929,
                    "reasoning_tokens": 205150,
                    "cache_read_tokens": 14425902,
                    "cache_write_tokens": 0
                },
                "token_tasks_measured": 6,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101": {
                "accuracy": 26.5,
                "latency": 3788.571,
                "stderr": 9.857,
                "cost_per_test": 3.137652,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "kimi/kimi-k2.5-thinking": {
                "accuracy": 23.167,
                "latency": 4461.074,
                "stderr": 11.074,
                "cost_per_test": 0.793265,
                "avg_input_tokens": 3105020.0,
                "avg_output_tokens": 142034.7,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101-thinking": {
                "accuracy": 22.5,
                "latency": 11643.441,
                "stderr": 8.755,
                "cost_per_test": 3.923438,
                "avg_input_tokens": 409.2,
                "avg_output_tokens": 156855.7,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "zai/glm-5-thinking": {
                "accuracy": 20.333,
                "latency": 6382.444,
                "stderr": 10.397,
                "cost_per_test": 3.68306,
                "avg_input_tokens": 4920165.0,
                "avg_output_tokens": 121863.3,
                "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": null
            },
            "grok/grok-4.3": {
                "accuracy": 17.667,
                "latency": 702.606,
                "stderr": 10.959,
                "cost_per_test": 0.377249,
                "avg_input_tokens": 622928.5,
                "avg_output_tokens": 67261.2,
                "avg_reasoning_tokens": 59885.8,
                "avg_cache_read_tokens": 542442.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "anthropic/claude-sonnet-4-5-20250929-thinking": {
                "accuracy": 17.667,
                "latency": 4046.414,
                "stderr": 5.896,
                "cost_per_test": 3.434954,
                "avg_input_tokens": 893585.5,
                "avg_output_tokens": 50279.8,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5-codex": {
                "accuracy": 16.667,
                "latency": 1435.417,
                "stderr": 15.215,
                "cost_per_test": 2.756198,
                "avg_input_tokens": 1531525.0,
                "avg_output_tokens": 84179.2,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5.4-nano-2026-03-17": {
                "accuracy": 16.333,
                "latency": 1373.348,
                "stderr": 11.246,
                "cost_per_test": 0.050431,
                "avg_input_tokens": 1292886.7,
                "avg_output_tokens": 94643.2,
                "avg_reasoning_tokens": 76398.2,
                "avg_cache_read_tokens": 1157120.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "alibaba/qwen3-max-2026-01-23": {
                "accuracy": 15.167,
                "latency": 2627.47,
                "stderr": 4.907,
                "cost_per_test": 1.853145,
                "avg_input_tokens": 479590.2,
                "avg_output_tokens": 91953.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "google/gemini-2.5-pro": {
                "accuracy": 15.167,
                "latency": 3770.063,
                "stderr": 6.853,
                "cost_per_test": 0.388888,
                "avg_input_tokens": 145865.2,
                "avg_output_tokens": 20655.7,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "fireworks/deepseek-v3p2": {
                "accuracy": 14.833,
                "latency": 3153.373,
                "stderr": 6.353,
                "cost_per_test": 0.051233,
                "avg_input_tokens": 4069.8,
                "avg_output_tokens": 29139.3,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "none",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "grok/grok-4-fast-reasoning": {
                "accuracy": 13.667,
                "latency": 1446.674,
                "stderr": 7.647,
                "cost_per_test": 0.595122,
                "avg_input_tokens": 799145.7,
                "avg_output_tokens": 870586.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "fireworks/deepseek-v3p2-thinking": {
                "accuracy": 10.167,
                "latency": 1742.362,
                "stderr": 3.14,
                "cost_per_test": 0.067402,
                "avg_input_tokens": 57741.5,
                "avg_output_tokens": 20873.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 20480,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "alibaba/qwen3-max": {
                "accuracy": 9.833,
                "latency": 3021.03,
                "stderr": 3.295,
                "cost_per_test": 1.233933,
                "avg_input_tokens": 830291.3,
                "avg_output_tokens": 39597.2,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "minimax/MiniMax-M2.7": {
                "accuracy": 9.333,
                "latency": 3013.297,
                "stderr": 4.736,
                "cost_per_test": 1.04722,
                "avg_input_tokens": 3094893.0,
                "avg_output_tokens": 102581.7,
                "avg_cache_read_tokens": 16786.3,
                "avg_cache_write_tokens": 2486.0,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "zai/glm-4.6": {
                "accuracy": 7.667,
                "latency": 8101.384,
                "stderr": 4.937,
                "cost_per_test": 1.00872,
                "avg_input_tokens": 2313626.8,
                "avg_output_tokens": 56774.2,
                "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": null
            },
            "grok/grok-4-1-fast-non-reasoning": {
                "accuracy": 7.667,
                "latency": 10702.953,
                "stderr": 3.82,
                "cost_per_test": 0.091116,
                "avg_input_tokens": 366791.7,
                "avg_output_tokens": 35514.3,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "openai/gpt-5.1-codex": {
                "accuracy": 7.333,
                "latency": 2128.396,
                "stderr": 6.694,
                "cost_per_test": 0.151756,
                "avg_input_tokens": 43436.5,
                "avg_output_tokens": 9746.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5-mini-2025-08-07": {
                "accuracy": 7.0,
                "latency": 507.95,
                "stderr": 4.989,
                "cost_per_test": 0.044368,
                "avg_input_tokens": 80990.7,
                "avg_output_tokens": 12060.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": "high",
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-opus-4-1-20250805": {
                "accuracy": 6.364,
                "latency": 6323.238,
                "stderr": 1.819,
                "cost_per_test": 19.617569,
                "avg_input_tokens": 1138070.6,
                "avg_output_tokens": 33953.5,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 32000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.4-mini-2026-03-17": {
                "accuracy": 6.167,
                "latency": 1916.743,
                "stderr": 5.629,
                "cost_per_test": 0.316446,
                "avg_input_tokens": 892300.8,
                "avg_output_tokens": 127767.2,
                "avg_reasoning_tokens": 117769.3,
                "avg_cache_read_tokens": 720725.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-haiku-4-5-20251001-thinking": {
                "accuracy": 5.833,
                "latency": 10438.736,
                "stderr": 2.466,
                "cost_per_test": 2.161642,
                "avg_input_tokens": 1809559.0,
                "avg_output_tokens": 70416.7,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "minimax/MiniMax-M2.5": {
                "accuracy": 5.833,
                "latency": 28418.598,
                "stderr": 2.833,
                "cost_per_test": 1.494618,
                "avg_input_tokens": 4339753.0,
                "avg_output_tokens": 82476.8,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 196608,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "grok/grok-4-1-fast-reasoning": {
                "accuracy": 5.667,
                "latency": 1702.552,
                "stderr": 3.469,
                "cost_per_test": 0.042869,
                "avg_input_tokens": 178307.0,
                "avg_output_tokens": 14415.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "grok/grok-code-fast-1": {
                "accuracy": 5.333,
                "latency": 1300.636,
                "stderr": 1.284,
                "cost_per_test": 1.203294,
                "avg_input_tokens": 637537.2,
                "avg_output_tokens": 717191.3,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 40000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "minimax/MiniMax-M2.1": {
                "accuracy": 4.667,
                "latency": 5483.31,
                "stderr": 2.6,
                "cost_per_test": 0.405159,
                "avg_input_tokens": 2398055.3,
                "avg_output_tokens": 79154.7,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "zai/glm-4.7": {
                "accuracy": 4.667,
                "latency": 7018.207,
                "stderr": 3.429,
                "cost_per_test": 0.502413,
                "avg_input_tokens": 1847492.8,
                "avg_output_tokens": 48790.8,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514-thinking": {
                "accuracy": 4.0,
                "latency": 3001.342,
                "stderr": 1.269,
                "cost_per_test": 1.636035,
                "avg_input_tokens": 462511.7,
                "avg_output_tokens": 16566.7,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "alibaba/qwen3-max-preview": {
                "accuracy": 3.833,
                "latency": 5381.491,
                "stderr": 2.692,
                "cost_per_test": 0.521296,
                "avg_input_tokens": 529220.8,
                "avg_output_tokens": 24479.8,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514": {
                "accuracy": 3.333,
                "latency": 4488.047,
                "stderr": 1.408,
                "cost_per_test": 2.697792,
                "avg_input_tokens": 791843.3,
                "avg_output_tokens": 21484.2,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "zai/glm-4.5": {
                "accuracy": 2.667,
                "latency": 2499.873,
                "stderr": 1.24,
                "cost_per_test": 0.790922,
                "avg_input_tokens": 1051774.3,
                "avg_output_tokens": 72662.3,
                "temperature": 0.6,
                "top_p": 1.0,
                "max_output_tokens": 81920,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "openai/o4-mini-2025-04-16": {
                "accuracy": 2.0,
                "latency": 584.039,
                "stderr": 0.77,
                "cost_per_test": 0.197548,
                "avg_input_tokens": 57871.6,
                "avg_output_tokens": 30429.4,
                "avg_cache_write_tokens": 0.0,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 100000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "together/moonshotai/Kimi-K2-Instruct": {
                "accuracy": 2.0,
                "latency": 1559.318,
                "stderr": 1.179,
                "cost_per_test": 2.309216,
                "avg_input_tokens": 2204779.5,
                "avg_output_tokens": 34812.3,
                "avg_reasoning_tokens": 0.0,
                "temperature": 0.6,
                "top_p": null,
                "max_output_tokens": 32768,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Together AI",
                "harness": null
            },
            "fireworks/deepseek-v3-0324": {
                "accuracy": 1.667,
                "latency": 198.312,
                "stderr": 0.962,
                "cost_per_test": 1.106313,
                "avg_input_tokens": 1217943.8,
                "avg_output_tokens": 11292.5,
                "avg_reasoning_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "grok/grok-4-fast-non-reasoning": {
                "accuracy": 1.5,
                "latency": 848.205,
                "stderr": 0.874,
                "cost_per_test": 0.080245,
                "avg_input_tokens": 109533.0,
                "avg_output_tokens": 116677.3,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 0.95,
                "max_output_tokens": 2000000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "mistralai/mistral-large-2512": {
                "accuracy": 1.5,
                "latency": 5786.766,
                "stderr": 0.874,
                "cost_per_test": 2.20173,
                "avg_input_tokens": 4085677.3,
                "avg_output_tokens": 105927.7,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.065,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "mistralai/labs-devstral-small-2512": {
                "accuracy": 1.333,
                "latency": 14075.052,
                "stderr": 1.217,
                "cost_per_test": 0.497513,
                "avg_input_tokens": 4720891.5,
                "avg_output_tokens": 84744.7,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.2,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "mistralai/devstral-2512": {
                "accuracy": 1.333,
                "latency": 15405.47,
                "stderr": 1.217,
                "cost_per_test": 1.689963,
                "avg_input_tokens": 3960435.5,
                "avg_output_tokens": 52894.5,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.2,
                "top_p": null,
                "max_output_tokens": 256000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "mistralai/magistral-medium-2509": {
                "accuracy": 0.833,
                "latency": 1688.096,
                "stderr": 0.761,
                "cost_per_test": 4.676308,
                "avg_input_tokens": 2180178.3,
                "avg_output_tokens": 63190.3,
                "avg_cache_read_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 0.7,
                "top_p": 1.0,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "google/gemini-2.5-flash": {
                "accuracy": 0.0,
                "latency": 76.555,
                "stderr": 0.0,
                "cost_per_test": 0.003315,
                "avg_input_tokens": 11051.0,
                "avg_output_tokens": 0.0,
                "avg_reasoning_tokens": 0.0,
                "avg_cache_write_tokens": 0.0,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "fireworks/qwen3-235b-a22b": {
                "accuracy": 0.0,
                "latency": 402.103,
                "stderr": 0.0,
                "cost_per_test": 0.152785,
                "avg_input_tokens": 557443.2,
                "avg_output_tokens": 34258.5,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 16384,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            }
        }
    }
}
