{
    "metadata": {
        "benchmark": "MedCode",
        "slug": "medcode",
        "description": "Can models support the medical billing process?",
        "benchmark_id": "medcode",
        "family": "medcode",
        "version": "1",
        "updated": "2026-10-01",
        "dataset_type": "private",
        "industry": "healthcare",
        "tasks": {
            "overall": "Overall"
        },
        "models": [
            "alibaba/qwen3-max-2026-01-23",
            "alibaba/qwen3-vl-plus-2025-09-23",
            "alibaba/qwen3.5-flash",
            "alibaba/qwen3.6-plus",
            "alibaba/qwen3.7-max",
            "alibaba/qwen3.8-27b",
            "alibaba/qwen3.8-max",
            "ant/ling-3.0-flash-2607",
            "ant/ling-3.0-flash-af-rc3",
            "anthropic/claude-fable-5",
            "anthropic/claude-fable-5-1",
            "anthropic/claude-haiku-4-5-20251001-thinking",
            "anthropic/claude-opus-4-1-20250805",
            "anthropic/claude-opus-4-1-20250805-thinking",
            "anthropic/claude-opus-4-5-20251101",
            "anthropic/claude-opus-4-5-20251101-thinking",
            "anthropic/claude-opus-4-6",
            "anthropic/claude-opus-4-6-thinking",
            "anthropic/claude-opus-4-7",
            "anthropic/claude-opus-4-8",
            "anthropic/claude-opus-5",
            "anthropic/claude-opus-5-5",
            "anthropic/claude-sonnet-4-20250514",
            "anthropic/claude-sonnet-4-20250514-thinking",
            "anthropic/claude-sonnet-4-5-20250929",
            "anthropic/claude-sonnet-4-5-20250929-thinking",
            "anthropic/claude-sonnet-5",
            "anthropic/claude-sonnet-5-5",
            "cohere/command-a-plus-05-2026",
            "deepseek/deepseek-v4-flash-0731",
            "deepseek/deepseek-v4-pro",
            "deepseek/deepseek-v4-pro-0813",
            "deepseek/deepseek-v4.1-flash",
            "fireworks/llama4-maverick-instruct-basic",
            "google/gemini-2.5-flash",
            "google/gemini-2.5-flash-lite",
            "google/gemini-2.5-flash-lite-preview-09-2025",
            "google/gemini-2.5-flash-lite-preview-09-2025-thinking",
            "google/gemini-2.5-flash-preview-09-2025",
            "google/gemini-2.5-flash-preview-09-2025-thinking",
            "google/gemini-2.5-flash-thinking",
            "google/gemini-2.5-pro",
            "google/gemini-3-flash-preview",
            "google/gemini-3-pro-preview",
            "google/gemini-3.1-flash-lite-preview",
            "google/gemini-3.1-pro-preview",
            "google/gemini-3.5-flash",
            "google/gemini-3.5-flash-lite",
            "google/gemini-3.6-flash",
            "google/gemini-3.7-flash",
            "google/gemini-3.8-flash",
            "google/gemini-4-argon",
            "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-4.5",
            "grok/grok-4.6",
            "grok/grok-4.7",
            "inception/mercury-2.5",
            "kimi/kimi-k2.5-thinking",
            "kimi/kimi-k2.6",
            "kimi/kimi-k3",
            "meta/muse_spark",
            "meta/muse_spark_1_2",
            "minimax/MiniMax-M2.1",
            "minimax/MiniMax-M2.7",
            "minimax/MiniMax-M3",
            "mistralai/mistral-medium-3.5",
            "nvidia/nemotron-3-ultra-550b-a55b",
            "openai/gpt-5-2025-08-07",
            "openai/gpt-5-mini-2025-08-07",
            "openai/gpt-5-nano-2025-08-07",
            "openai/gpt-5.1-2025-11-13",
            "openai/gpt-5.2-2025-12-11",
            "openai/gpt-5.4-2026-03-05",
            "openai/gpt-5.4-nano-2026-03-17",
            "openai/gpt-5.5",
            "openai/gpt-5.6-luna",
            "openai/gpt-5.6-sol",
            "openai/gpt-5.6-terra",
            "openai/gpt-6-astra",
            "openai/gpt-6-luna",
            "openai/gpt-6-sol",
            "openai/gpt-6.1-sol",
            "openai/o3-2025-04-16",
            "openai/o4-mini-2025-04-16",
            "poolside/laguna-m.1",
            "poolside/laguna-xs.2",
            "tencent/hy4-preview",
            "thinkingmachines/inkling",
            "thinkingmachines/inkling-small",
            "together/meta-llama/Llama-4-Scout-17B-16E-Instruct",
            "xiaomi/mimo-v2.5",
            "xiaomi/mimo-v2.5-pro",
            "xiaomi/mimo-v2.6-flash",
            "xiaomi/mimo-v2.6-pro",
            "zai/glm-4.7",
            "zai/glm-5.1",
            "zai/glm-5.2",
            "zai/glm-5.3"
        ],
        "partners": [],
        "showBadge": false,
        "visible": true,
        "use_cost_per_test": false,
        "runner": "custom",
        "mode": "one-shot",
        "archived": false,
        "partner": false,
        "total_models": 104
    },
    "tasks": {
        "overall": {
            "anthropic/claude-opus-5": {
                "accuracy": 63.57,
                "latency": 24.5,
                "stderr": 1.993,
                "cost_per_test": 0.156845,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-3.1-pro-preview": {
                "accuracy": 59.062,
                "latency": 38.523,
                "stderr": 1.996,
                "cost_per_test": 0.024714,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "google/gemini-4-argon": {
                "accuracy": 58.801,
                "latency": 79.527,
                "stderr": 2.1,
                "cost_per_test": 0.13716,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-fable-5": {
                "accuracy": 56.07,
                "latency": 91.439,
                "stderr": 2.203,
                "cost_per_test": 0.591071,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-3-flash-preview": {
                "accuracy": 55.92,
                "latency": 44.149,
                "stderr": 2.112,
                "cost_per_test": 0.006187,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "google/gemini-3.5-flash": {
                "accuracy": 55.825,
                "latency": 25.29,
                "stderr": 2.113,
                "cost_per_test": 0.073716,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-opus-4-7": {
                "accuracy": 54.858,
                "latency": 54.251,
                "stderr": 2.205,
                "cost_per_test": 0.226314,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "anthropic/claude-fable-5-1": {
                "accuracy": 53.509,
                "latency": 215.494,
                "stderr": 2.165,
                "cost_per_test": 1.116862,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-3.7-flash": {
                "accuracy": 53.39,
                "latency": 9.164,
                "stderr": 2.12,
                "cost_per_test": 0.038331,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-opus-4-8": {
                "accuracy": 53.217,
                "latency": 105.915,
                "stderr": 2.165,
                "cost_per_test": 0.350925,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-3.6-flash": {
                "accuracy": 53.153,
                "latency": 16.685,
                "stderr": 2.157,
                "cost_per_test": 0.044216,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-sonnet-5-5": {
                "accuracy": 52.92,
                "latency": 239.171,
                "stderr": 2.119,
                "cost_per_test": 0.391592,
                "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-5.1-2025-11-13": {
                "accuracy": 52.732,
                "latency": 54.546,
                "stderr": 2.151,
                "cost_per_test": 0.014371,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "google/gemini-3-pro-preview": {
                "accuracy": 52.198,
                "latency": 55.836,
                "stderr": 2.073,
                "cost_per_test": 0.028248,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "meta/muse_spark": {
                "accuracy": 51.31,
                "latency": 123.095,
                "stderr": 2.244,
                "cost_per_test": 0.005341,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": null
            },
            "google/gemini-2.5-pro": {
                "accuracy": 50.59,
                "latency": 27.415,
                "stderr": 2.113,
                "cost_per_test": 0.015389,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-opus-5-5": {
                "accuracy": 49.797,
                "latency": 246.876,
                "stderr": 2.273,
                "cost_per_test": 0.658237,
                "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-5.2-2025-12-11": {
                "accuracy": 49.749,
                "latency": 156.651,
                "stderr": 2.262,
                "cost_per_test": 0.018852,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-5-2025-08-07": {
                "accuracy": 49.634,
                "latency": 58.268,
                "stderr": 2.098,
                "cost_per_test": 0.045858,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "grok/grok-4.7": {
                "accuracy": 49.553,
                "latency": 213.135,
                "stderr": 2.171,
                "cost_per_test": 0.105497,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": null,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "kimi/kimi-k3": {
                "accuracy": 49.357,
                "latency": 36.994,
                "stderr": 2.202,
                "cost_per_test": 0.093857,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 262144,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": null
            },
            "meta/muse_spark_1_2": {
                "accuracy": 49.346,
                "latency": 60.17,
                "stderr": 2.187,
                "cost_per_test": 0.039023,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Meta",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101-thinking": {
                "accuracy": 49.156,
                "latency": 60.839,
                "stderr": 2.012,
                "cost_per_test": 0.095846,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "anthropic/claude-opus-4-6-thinking": {
                "accuracy": 49.129,
                "latency": 156.295,
                "stderr": 2.085,
                "cost_per_test": 0.244127,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.5": {
                "accuracy": 49.1,
                "latency": 159.546,
                "stderr": 2.188,
                "cost_per_test": 0.160759,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "openai/gpt-6.1-sol": {
                "accuracy": 48.839,
                "latency": 115.342,
                "stderr": 2.12,
                "cost_per_test": 0.084726,
                "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-6-astra": {
                "accuracy": 48.486,
                "latency": 102.865,
                "stderr": 2.131,
                "cost_per_test": 0.451358,
                "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-4-6": {
                "accuracy": 48.244,
                "latency": 4.058,
                "stderr": 2.05,
                "cost_per_test": 0.00618,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-3.8-flash": {
                "accuracy": 48.135,
                "latency": 42.892,
                "stderr": 2.18,
                "cost_per_test": 0.0177,
                "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-3.1-flash-lite-preview": {
                "accuracy": 47.602,
                "latency": 8.55,
                "stderr": 2.071,
                "cost_per_test": 0.002029,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "anthropic/claude-sonnet-5": {
                "accuracy": 47.54,
                "latency": 134.934,
                "stderr": 2.274,
                "cost_per_test": 0.278799,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "max",
                "provider": "Anthropic",
                "harness": null
            },
            "openai/o3-2025-04-16": {
                "accuracy": 47.29,
                "latency": 17.676,
                "stderr": 2.161,
                "cost_per_test": 0.029818,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "anthropic/claude-opus-4-1-20250805-thinking": {
                "accuracy": 47.235,
                "latency": 33.263,
                "stderr": 2.067,
                "cost_per_test": 0.269254,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-6-sol": {
                "accuracy": 47.072,
                "latency": 62.714,
                "stderr": 2.119,
                "cost_per_test": 0.085827,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "minimax/MiniMax-M3": {
                "accuracy": 46.289,
                "latency": 63.12,
                "stderr": 2.104,
                "cost_per_test": 0.012125,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "anthropic/claude-opus-4-5-20251101": {
                "accuracy": 45.174,
                "latency": 5.023,
                "stderr": 1.888,
                "cost_per_test": 0.006826,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": "high",
                "provider": "Anthropic",
                "harness": null
            },
            "xiaomi/mimo-v2.6-pro": {
                "accuracy": 44.969,
                "latency": 176.915,
                "stderr": 2.097,
                "cost_per_test": 0.009528,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": null
            },
            "grok/grok-4.6": {
                "accuracy": 44.712,
                "latency": 127.284,
                "stderr": 2.256,
                "cost_per_test": 0.050335,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "openai/gpt-6-luna": {
                "accuracy": 44.685,
                "latency": 108.772,
                "stderr": 2.303,
                "cost_per_test": 0.007323,
                "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-sonnet-4-5-20250929-thinking": {
                "accuracy": 44.134,
                "latency": 74.331,
                "stderr": 1.998,
                "cost_per_test": 0.101495,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.6-sol": {
                "accuracy": 43.974,
                "latency": 96.589,
                "stderr": 2.258,
                "cost_per_test": 0.280517,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "google/gemini-3.5-flash-lite": {
                "accuracy": 43.489,
                "latency": 6.019,
                "stderr": 1.951,
                "cost_per_test": 0.008093,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "openai/gpt-5.6-terra": {
                "accuracy": 43.414,
                "latency": 18.411,
                "stderr": 2.173,
                "cost_per_test": 0.046558,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "grok/grok-4.5": {
                "accuracy": 43.291,
                "latency": 59.637,
                "stderr": 2.313,
                "cost_per_test": 0.048461,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "tencent/hy4-preview": {
                "accuracy": 43.247,
                "latency": 399.284,
                "stderr": 2.134,
                "cost_per_test": 0.062053,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Tencent",
                "harness": null
            },
            "openai/gpt-5-mini-2025-08-07": {
                "accuracy": 43.045,
                "latency": 28.173,
                "stderr": 2.045,
                "cost_per_test": 0.00556,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "zai/glm-5.3": {
                "accuracy": 42.864,
                "latency": 169.01,
                "stderr": 2.111,
                "cost_per_test": 0.081905,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "deepseek/deepseek-v4-pro-0813": {
                "accuracy": 42.47,
                "latency": 180.938,
                "stderr": 2.16,
                "cost_per_test": 0.06106,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "openai/gpt-5.6-luna": {
                "accuracy": 42.391,
                "latency": 81.283,
                "stderr": 2.27,
                "cost_per_test": 0.01597,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "zai/glm-5.1": {
                "accuracy": 41.604,
                "latency": 77.578,
                "stderr": 2.124,
                "cost_per_test": 0.024196,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "deepseek/deepseek-v4-flash-0731": {
                "accuracy": 41.415,
                "latency": 127.0,
                "stderr": 2.15,
                "cost_per_test": 0.019659,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "anthropic/claude-opus-4-1-20250805": {
                "accuracy": 41.372,
                "latency": 13.084,
                "stderr": 1.958,
                "cost_per_test": 0.20627,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/gpt-5.4-2026-03-05": {
                "accuracy": 41.292,
                "latency": 187.265,
                "stderr": 2.148,
                "cost_per_test": 0.212108,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "thinkingmachines/inkling": {
                "accuracy": 41.19,
                "latency": 167.123,
                "stderr": 2.23,
                "cost_per_test": 0.127025,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "0.99",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Thinkingmachines",
                "harness": null
            },
            "deepseek/deepseek-v4.1-flash": {
                "accuracy": 41.173,
                "latency": 35.126,
                "stderr": 2.042,
                "cost_per_test": 0.01245,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 384000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "xiaomi/mimo-v2.6-flash": {
                "accuracy": 41.057,
                "latency": 93.373,
                "stderr": 2.032,
                "cost_per_test": 0.002865,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": null
            },
            "openai/gpt-5.4-nano-2026-03-17": {
                "accuracy": 41.029,
                "latency": 8.043,
                "stderr": 2.256,
                "cost_per_test": 0.000844,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "zai/glm-5.2": {
                "accuracy": 40.771,
                "latency": 95.265,
                "stderr": 2.166,
                "cost_per_test": 0.04501,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "alibaba/qwen3.8-max": {
                "accuracy": 40.668,
                "latency": 378.022,
                "stderr": 2.029,
                "cost_per_test": 0.120827,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "anthropic/claude-sonnet-4-5-20250929": {
                "accuracy": 40.569,
                "latency": 12.006,
                "stderr": 1.995,
                "cost_per_test": 0.042403,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "google/gemini-2.5-flash-preview-09-2025": {
                "accuracy": 40.538,
                "latency": 12.702,
                "stderr": 1.932,
                "cost_per_test": 0.003692,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "deepseek/deepseek-v4-pro": {
                "accuracy": 40.455,
                "latency": 382.667,
                "stderr": 2.122,
                "cost_per_test": 0.06071,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 128000,
                "reasoning": null,
                "reasoning_effort": "max",
                "verbosity": null,
                "compute_effort": null,
                "provider": "DeepSeek",
                "harness": null
            },
            "google/gemini-2.5-flash-thinking": {
                "accuracy": 40.357,
                "latency": 22.833,
                "stderr": 1.952,
                "cost_per_test": 0.003661,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "google/gemini-2.5-flash-preview-09-2025-thinking": {
                "accuracy": 40.33,
                "latency": 16.106,
                "stderr": 1.915,
                "cost_per_test": 0.003653,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "kimi/kimi-k2.6": {
                "accuracy": 40.142,
                "latency": 305.421,
                "stderr": 2.041,
                "cost_per_test": 0.041295,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": null
            },
            "kimi/kimi-k2.5-thinking": {
                "accuracy": 39.316,
                "latency": 75.452,
                "stderr": 2.119,
                "cost_per_test": 0.017275,
                "temperature": null,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Moonshot AI",
                "harness": null
            },
            "alibaba/qwen3.7-max": {
                "accuracy": 38.751,
                "latency": 28.755,
                "stderr": 2.196,
                "cost_per_test": 0.042362,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "nvidia/nemotron-3-ultra-550b-a55b": {
                "accuracy": 38.621,
                "latency": 18.675,
                "stderr": 2.001,
                "cost_per_test": null,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Nvidia",
                "harness": null
            },
            "google/gemini-2.5-flash": {
                "accuracy": 38.425,
                "latency": 22.145,
                "stderr": 1.923,
                "cost_per_test": 0.003698,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "grok/grok-4-0709": {
                "accuracy": 38.078,
                "latency": 89.002,
                "stderr": 2.206,
                "cost_per_test": 0.034103,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "grok/grok-4.3": {
                "accuracy": 38.068,
                "latency": 43.924,
                "stderr": 2.081,
                "cost_per_test": 0.022202,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "thinkingmachines/inkling-small": {
                "accuracy": 37.893,
                "latency": 191.049,
                "stderr": 2.206,
                "cost_per_test": 0.016656,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "0.99",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Thinkingmachines",
                "harness": null
            },
            "grok/grok-4-fast-reasoning": {
                "accuracy": 37.385,
                "latency": 17.515,
                "stderr": 1.941,
                "cost_per_test": 0.002143,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "alibaba/qwen3.6-plus": {
                "accuracy": 36.894,
                "latency": 56.222,
                "stderr": 2.017,
                "cost_per_test": 0.015673,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "fireworks/llama4-maverick-instruct-basic": {
                "accuracy": 36.514,
                "latency": 21.241,
                "stderr": 1.994,
                "cost_per_test": 0.002888,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Fireworks AI",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514-thinking": {
                "accuracy": 34.959,
                "latency": 39.799,
                "stderr": 1.939,
                "cost_per_test": 0.069896,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "minimax/MiniMax-M2.7": {
                "accuracy": 34.44,
                "latency": 30.252,
                "stderr": 1.985,
                "cost_per_test": 0.007424,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "google/gemini-2.5-flash-lite-preview-09-2025-thinking": {
                "accuracy": 34.191,
                "latency": 10.49,
                "stderr": 1.736,
                "cost_per_test": 0.001182,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "minimax/MiniMax-M2.1": {
                "accuracy": 34.083,
                "latency": 19.548,
                "stderr": 1.943,
                "cost_per_test": null,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "MiniMax",
                "harness": null
            },
            "anthropic/claude-sonnet-4-20250514": {
                "accuracy": 33.943,
                "latency": 7.298,
                "stderr": 1.906,
                "cost_per_test": 0.03946,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "openai/o4-mini-2025-04-16": {
                "accuracy": 33.791,
                "latency": 21.062,
                "stderr": 2.021,
                "cost_per_test": 0.017605,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "mistralai/mistral-medium-3.5": {
                "accuracy": 33.752,
                "latency": 34.879,
                "stderr": 1.148,
                "cost_per_test": 0.05337,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Mistral AI",
                "harness": null
            },
            "alibaba/qwen3.5-flash": {
                "accuracy": 32.997,
                "latency": 63.074,
                "stderr": 1.787,
                "cost_per_test": 0.003934,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "zai/glm-4.7": {
                "accuracy": 32.772,
                "latency": 123.441,
                "stderr": 1.996,
                "cost_per_test": 0.00671,
                "temperature": 1.0,
                "top_p": 1.0,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Zhipu AI",
                "harness": null
            },
            "anthropic/claude-haiku-4-5-20251001-thinking": {
                "accuracy": 32.678,
                "latency": 34.291,
                "stderr": 1.998,
                "cost_per_test": 0.020099,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Anthropic",
                "harness": null
            },
            "xiaomi/mimo-v2.5-pro": {
                "accuracy": 32.484,
                "latency": 38.448,
                "stderr": 1.907,
                "cost_per_test": 0.006719,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": null
            },
            "ant/ling-3.0-flash-2607": {
                "accuracy": 32.275,
                "latency": 9.647,
                "stderr": 1.908,
                "cost_per_test": 0.001645,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Ant",
                "harness": null
            },
            "grok/grok-4.20-0309-reasoning": {
                "accuracy": 32.156,
                "latency": 16.546,
                "stderr": 2.124,
                "cost_per_test": 0.036189,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "xiaomi/mimo-v2.5": {
                "accuracy": 31.895,
                "latency": 17.704,
                "stderr": 2.025,
                "cost_per_test": 0.002162,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Xiaomi",
                "harness": null
            },
            "alibaba/qwen3-vl-plus-2025-09-23": {
                "accuracy": 31.651,
                "latency": 9.952,
                "stderr": 1.845,
                "cost_per_test": 0.002519,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "alibaba/qwen3-max-2026-01-23": {
                "accuracy": 31.373,
                "latency": 182.194,
                "stderr": 1.888,
                "cost_per_test": 0.014776,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "inception/mercury-2.5": {
                "accuracy": 31.326,
                "latency": 7.93,
                "stderr": 1.953,
                "cost_per_test": 0.004535,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 65536,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Inception",
                "harness": null
            },
            "openai/gpt-5-nano-2025-08-07": {
                "accuracy": 30.441,
                "latency": 29.741,
                "stderr": 1.948,
                "cost_per_test": 0.001729,
                "temperature": null,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "high",
                "verbosity": null,
                "compute_effort": null,
                "provider": "OpenAI",
                "harness": null
            },
            "grok/grok-4-fast-non-reasoning": {
                "accuracy": 30.036,
                "latency": 18.211,
                "stderr": 1.974,
                "cost_per_test": 0.002149,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "ant/ling-3.0-flash-af-rc3": {
                "accuracy": 29.305,
                "latency": 31.167,
                "stderr": 1.943,
                "cost_per_test": 0.001354,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 131072,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Ant",
                "harness": null
            },
            "alibaba/qwen3.8-27b": {
                "accuracy": 28.698,
                "latency": 89.379,
                "stderr": 1.971,
                "cost_per_test": 0.050145,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": "xhigh",
                "verbosity": null,
                "compute_effort": null,
                "provider": "Alibaba",
                "harness": null
            },
            "grok/grok-4-1-fast-non-reasoning": {
                "accuracy": 28.349,
                "latency": 4.496,
                "stderr": 1.921,
                "cost_per_test": 0.002193,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "grok/grok-4-1-fast-reasoning": {
                "accuracy": 28.08,
                "latency": 46.5,
                "stderr": 1.992,
                "cost_per_test": 0.002108,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "SpaceXAI",
                "harness": null
            },
            "google/gemini-2.5-flash-lite": {
                "accuracy": 27.115,
                "latency": 5.746,
                "stderr": 1.843,
                "cost_per_test": 0.001342,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "google/gemini-2.5-flash-lite-preview-09-2025": {
                "accuracy": 27.079,
                "latency": 6.239,
                "stderr": 1.911,
                "cost_per_test": 0.00144,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Google",
                "harness": null
            },
            "together/meta-llama/Llama-4-Scout-17B-16E-Instruct": {
                "accuracy": 23.311,
                "latency": 10.736,
                "stderr": 1.749,
                "cost_per_test": 0.002176,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Together AI",
                "harness": null
            },
            "poolside/laguna-m.1": {
                "accuracy": 23.106,
                "latency": 70.995,
                "stderr": 1.693,
                "cost_per_test": 0.002973,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Poolside",
                "harness": null
            },
            "poolside/laguna-xs.2": {
                "accuracy": 21.251,
                "latency": 33.094,
                "stderr": 1.703,
                "cost_per_test": 0.001445,
                "temperature": 1.0,
                "top_p": null,
                "max_output_tokens": 30000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Poolside",
                "harness": null
            },
            "cohere/command-a-plus-05-2026": {
                "accuracy": 19.718,
                "latency": 103.751,
                "stderr": 1.835,
                "cost_per_test": 0.055695,
                "temperature": 1.0,
                "top_p": 0.95,
                "max_output_tokens": 64000,
                "reasoning": null,
                "reasoning_effort": null,
                "verbosity": null,
                "compute_effort": null,
                "provider": "Cohere",
                "harness": null
            }
        }
    }
}