{ "metadata": { "benchmark": "SWE-bench Multimodal", "slug": "swebench-multimodal", "description": "Resolving GitHub issues in JavaScript front-end repositories where the report is a screenshot as much as a description", "benchmark_id": "swebench_multimodal", "family": "swebench_multimodal", "version": "1", "updated": "2026-10-13", "dataset_type": "public", "industry": "coding", "tasks": { "overall": "Overall", "bpmn_js": "bpmn-js", "carbon": "Carbon", "eslint": "ESLint", "fusion_next": "Fusion Next", "grommet": "Grommet", "highlight_js": "highlight.js", "lighthouse": "Lighthouse", "openlayers": "OpenLayers", "prettier": "Prettier", "prism": "Prism", "scratch_gui": "Scratch GUI" }, "models": [ "alibaba/qwen3.8-max", "anthropic/claude-fable-5-1", "anthropic/claude-haiku-5-5", "anthropic/claude-opus-5-5", "anthropic/claude-sonnet-5-5", "deepseek/deepseek-v4.1-flash", "google/gemini-3.8-flash", "google/gemini-4-argon", "grok/grok-4.7", "kimi/kimi-k3", "meta/muse-wonder", "meta/muse-wonder-full", "meta/muse_spark_1_3_max", "openai/gpt-6-astra", "openai/gpt-6-luna", "openai/gpt-6.1-sol", "stepfun/step-5-preview", "xiaomi/mimo-v2.6-pro" ], "partners": [], "showBadge": false, "visible": true, "use_cost_per_test": true, "runner": "external", "mode": "agentic", "archived": false, "partner": false, "total_models": 18 }, "tasks": { "overall": { "anthropic/claude-opus-5-5": { "accuracy": 70.208, "latency": 1111.602, "stderr": 2.09, "cost_per_test": 4.920591, "token_totals": { "input_tokens": 3178343409, "output_tokens": 38075346, "reasoning_tokens": 28587621, "cache_read_tokens": 3106799485, "cache_write_tokens": 71481242 }, "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-5-1": { "accuracy": 61.25, "latency": 912.134, "stderr": 2.226, "cost_per_test": 5.463719, "token_totals": { "input_tokens": 2206144347, "output_tokens": 27943847, "reasoning_tokens": 19675139, "cache_read_tokens": 2150887536, "cache_write_tokens": 55199879 }, "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-sonnet-5-5": { "accuracy": 58.333, "latency": 1452.55, "stderr": 2.253, "cost_per_test": 4.528625, "token_totals": { "input_tokens": 6209566764, "output_tokens": 67483450, "reasoning_tokens": 53457799, "cache_read_tokens": 6097813282, "cache_write_tokens": 111671460 }, "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-4-argon": { "accuracy": 56.042, "latency": 2017.534, "stderr": 2.268, "cost_per_test": 11.397153, "token_totals": { "input_tokens": 6541366791, "output_tokens": 56305127, "reasoning_tokens": 51883087, "cache_read_tokens": 5745350936, "cache_write_tokens": null }, "temperature": 1.0, "top_p": null, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "meta/muse-wonder-full": { "accuracy": 47.292, "latency": 862.026, "stderr": 2.281, "cost_per_test": 1.860894, "token_totals": { "input_tokens": 1999150665, "output_tokens": 15546718, "reasoning_tokens": 10952489, "cache_read_tokens": 1951133624, "cache_write_tokens": 0 }, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 46.458, "latency": 1164.341, "stderr": 2.279, "cost_per_test": 0.225505, "token_totals": { "input_tokens": 7132824792, "output_tokens": 41500077, "reasoning_tokens": 30954177, "cache_read_tokens": 7079609940, "cache_write_tokens": null }, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "meta/muse-wonder": { "accuracy": 45.417, "latency": 581.998, "stderr": 2.275, "cost_per_test": 1.693517, "token_totals": { "input_tokens": 1758443234, "output_tokens": 14213668, "reasoning_tokens": 10007486, "cache_read_tokens": 1712329440, "cache_write_tokens": 0 }, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 43.958, "latency": 975.904, "stderr": 2.268, "cost_per_test": 0.704848, "token_totals": { "input_tokens": 4643396325, "output_tokens": 62236326, "reasoning_tokens": 49493415, "cache_read_tokens": 4549542924, "cache_write_tokens": 93785405 }, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "openai/gpt-6.1-sol": { "accuracy": 43.542, "latency": 415.53, "stderr": 2.265, "cost_per_test": 0.35065, "token_totals": { "input_tokens": 242137916, "output_tokens": 8751306, "reasoning_tokens": 4864804, "cache_read_tokens": 218556086, "cache_write_tokens": 23559495 }, "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": 43.333, "latency": 423.272, "stderr": 2.264, "cost_per_test": 1.80573, "token_totals": { "input_tokens": 222905104, "output_tokens": 7780051, "reasoning_tokens": 4452235, "cache_read_tokens": 200740149, "cache_write_tokens": 22143289 }, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 43.125, "latency": 652.092, "stderr": 2.263, "cost_per_test": 0.863821, "token_totals": { "input_tokens": 1828050806, "output_tokens": 16561442, "reasoning_tokens": 10995147, "cache_read_tokens": 1764377868, "cache_write_tokens": 0 }, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "grok/grok-4.7": { "accuracy": 42.917, "latency": 1261.388, "stderr": 2.262, "cost_per_test": 4.662136, "token_totals": { "input_tokens": 3192589415, "output_tokens": 35749853, "reasoning_tokens": 28033326, "cache_read_tokens": 3044927744, "cache_write_tokens": 0 }, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 41.25, "latency": 2763.074, "stderr": 2.249, "cost_per_test": 0.122089, "token_totals": { "input_tokens": 1810237188, "output_tokens": 32392842, "reasoning_tokens": 27433951, "cache_read_tokens": 1755109504, "cache_write_tokens": null }, "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 }, "google/gemini-3.8-flash": { "accuracy": 40.833, "latency": 1338.303, "stderr": 2.246, "cost_per_test": 3.688847, "token_totals": { "input_tokens": 6218542064, "output_tokens": 38857502, "reasoning_tokens": 34183849, "cache_read_tokens": 5816508549, "cache_write_tokens": null }, "temperature": 1.0, "top_p": null, "max_output_tokens": 65536, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "stepfun/step-5-preview": { "accuracy": 40.833, "latency": 1565.635, "stderr": 2.246, "cost_per_test": 0.614408, "token_totals": { "input_tokens": 2914876020, "output_tokens": 27191106, "reasoning_tokens": 0, "cache_read_tokens": 2835132928, "cache_write_tokens": null }, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "alibaba/qwen3.8-max": { "accuracy": 39.167, "latency": 1032.464, "stderr": 2.23, "cost_per_test": 0.952593, "token_totals": { "input_tokens": 1042968588, "output_tokens": 17832949, "reasoning_tokens": 14067193, "cache_read_tokens": 1003254016, "cache_write_tokens": null }, "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-6-luna": { "accuracy": 37.5, "latency": 315.874, "stderr": 2.212, "cost_per_test": 0.03193, "token_totals": { "input_tokens": 524114440, "output_tokens": 13085746, "reasoning_tokens": 9069944, "cache_read_tokens": 493305377, "cache_write_tokens": 30777074 }, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "kimi/kimi-k3": { "accuracy": 35.833, "latency": 1280.589, "stderr": 2.191, "cost_per_test": 1.501383, "token_totals": { "input_tokens": 994189747, "output_tokens": 14594981, "reasoning_tokens": 10723372, "cache_read_tokens": 966091776, "cache_write_tokens": 25485360 }, "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 } }, "bpmn_js": { "anthropic/claude-opus-5-5": { "accuracy": 83.019, "latency": null, "stderr": 5.207, "cost_per_test": null, "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-5-1": { "accuracy": 79.245, "latency": null, "stderr": 5.624, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 73.585, "latency": null, "stderr": 6.114, "cost_per_test": null, "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-4-argon": { "accuracy": 71.698, "latency": null, "stderr": 6.247, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "meta/muse-wonder-full": { "accuracy": 69.811, "latency": null, "stderr": 6.366, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse-wonder": { "accuracy": 67.925, "latency": null, "stderr": 6.473, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "grok/grok-4.7": { "accuracy": 66.038, "latency": null, "stderr": 6.567, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 64.151, "latency": null, "stderr": 6.65, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 64.151, "latency": null, "stderr": 6.65, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 65536, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 64.151, "latency": null, "stderr": 6.65, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "alibaba/qwen3.8-max": { "accuracy": 62.264, "latency": null, "stderr": 6.722, "cost_per_test": null, "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-6-astra": { "accuracy": 62.264, "latency": null, "stderr": 6.722, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 60.377, "latency": null, "stderr": 6.783, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "openai/gpt-6.1-sol": { "accuracy": 60.377, "latency": null, "stderr": 6.783, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 60.377, "latency": null, "stderr": 6.783, "cost_per_test": null, "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 }, "stepfun/step-5-preview": { "accuracy": 58.491, "latency": null, "stderr": 6.833, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "openai/gpt-6-luna": { "accuracy": 56.604, "latency": null, "stderr": 6.873, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "kimi/kimi-k3": { "accuracy": 47.17, "latency": null, "stderr": 6.923, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null } }, "carbon": { "anthropic/claude-opus-5-5": { "accuracy": 52.632, "latency": null, "stderr": 4.346, "cost_per_test": null, "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-5-1": { "accuracy": 44.361, "latency": null, "stderr": 4.324, "cost_per_test": null, "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-4-argon": { "accuracy": 43.609, "latency": null, "stderr": 4.316, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 42.857, "latency": null, "stderr": 4.307, "cost_per_test": null, "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-v4.1-flash": { "accuracy": 29.323, "latency": null, "stderr": 3.962, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "meta/muse-wonder-full": { "accuracy": 29.323, "latency": null, "stderr": 3.962, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse-wonder": { "accuracy": 27.068, "latency": null, "stderr": 3.867, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 26.316, "latency": null, "stderr": 3.833, "cost_per_test": null, "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 }, "alibaba/qwen3.8-max": { "accuracy": 24.812, "latency": null, "stderr": 3.759, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "stepfun/step-5-preview": { "accuracy": 24.812, "latency": null, "stderr": 3.759, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 24.06, "latency": null, "stderr": 3.72, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "grok/grok-4.7": { "accuracy": 24.06, "latency": null, "stderr": 3.72, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "openai/gpt-6-astra": { "accuracy": 24.06, "latency": null, "stderr": 3.72, "cost_per_test": null, "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-6.1-sol": { "accuracy": 24.06, "latency": null, "stderr": 3.72, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 22.556, "latency": null, "stderr": 3.638, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "kimi/kimi-k3": { "accuracy": 21.053, "latency": null, "stderr": 3.548, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 19.549, "latency": null, "stderr": 3.452, "cost_per_test": null, "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-6-luna": { "accuracy": 19.549, "latency": null, "stderr": 3.452, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null } }, "eslint": { "anthropic/claude-opus-5-5": { "accuracy": 90.909, "latency": null, "stderr": 9.091, "cost_per_test": null, "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-5-1": { "accuracy": 81.818, "latency": null, "stderr": 12.197, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 81.818, "latency": null, "stderr": 12.197, "cost_per_test": null, "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": 72.727, "latency": null, "stderr": 14.084, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "google/gemini-4-argon": { "accuracy": 72.727, "latency": null, "stderr": 14.084, "cost_per_test": null, "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-haiku-5-5": { "accuracy": 63.636, "latency": null, "stderr": 15.212, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "meta/muse-wonder-full": { "accuracy": 63.636, "latency": null, "stderr": 15.212, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 63.636, "latency": null, "stderr": 15.212, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 54.545, "latency": null, "stderr": 15.746, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 65536, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "kimi/kimi-k3": { "accuracy": 54.545, "latency": null, "stderr": 15.746, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "meta/muse-wonder": { "accuracy": 54.545, "latency": null, "stderr": 15.746, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6-astra": { "accuracy": 54.545, "latency": null, "stderr": 15.746, "cost_per_test": null, "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-6.1-sol": { "accuracy": 54.545, "latency": null, "stderr": 15.746, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "grok/grok-4.7": { "accuracy": 45.455, "latency": null, "stderr": 15.746, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 45.455, "latency": null, "stderr": 15.746, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 45.455, "latency": null, "stderr": 15.746, "cost_per_test": null, "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 }, "deepseek/deepseek-v4.1-flash": { "accuracy": 36.364, "latency": null, "stderr": 15.212, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "openai/gpt-6-luna": { "accuracy": 36.364, "latency": null, "stderr": 15.212, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null } }, "fusion_next": { "anthropic/claude-opus-5-5": { "accuracy": 50.0, "latency": null, "stderr": 8.452, "cost_per_test": null, "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-4-argon": { "accuracy": 47.222, "latency": null, "stderr": 8.438, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 44.444, "latency": null, "stderr": 8.399, "cost_per_test": null, "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-v4.1-flash": { "accuracy": 44.444, "latency": null, "stderr": 8.399, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "anthropic/claude-fable-5-1": { "accuracy": 41.667, "latency": null, "stderr": 8.333, "cost_per_test": null, "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-wonder-full": { "accuracy": 41.667, "latency": null, "stderr": 8.333, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 41.667, "latency": null, "stderr": 8.333, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "alibaba/qwen3.8-max": { "accuracy": 38.889, "latency": null, "stderr": 8.24, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 38.889, "latency": null, "stderr": 8.24, "cost_per_test": null, "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-4.7": { "accuracy": 38.889, "latency": null, "stderr": 8.24, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "meta/muse-wonder": { "accuracy": 38.889, "latency": null, "stderr": 8.24, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6-astra": { "accuracy": 38.889, "latency": null, "stderr": 8.24, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 38.889, "latency": null, "stderr": 8.24, "cost_per_test": null, "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-6.1-sol": { "accuracy": 36.111, "latency": null, "stderr": 8.119, "cost_per_test": null, "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-haiku-5-5": { "accuracy": 33.333, "latency": null, "stderr": 7.968, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "kimi/kimi-k3": { "accuracy": 33.333, "latency": null, "stderr": 7.968, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "openai/gpt-6-luna": { "accuracy": 33.333, "latency": null, "stderr": 7.968, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 30.556, "latency": null, "stderr": 7.786, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null } }, "grommet": { "anthropic/claude-opus-5-5": { "accuracy": 55.0, "latency": null, "stderr": 11.413, "cost_per_test": null, "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-4-argon": { "accuracy": 45.0, "latency": null, "stderr": 11.413, "cost_per_test": null, "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-haiku-5-5": { "accuracy": 35.0, "latency": null, "stderr": 10.942, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "meta/muse-wonder": { "accuracy": 35.0, "latency": null, "stderr": 10.942, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse-wonder-full": { "accuracy": 35.0, "latency": null, "stderr": 10.942, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "alibaba/qwen3.8-max": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "anthropic/claude-fable-5-1": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "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-3.8-flash": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "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-4.7": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "openai/gpt-6-astra": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "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-6.1-sol": { "accuracy": 30.0, "latency": null, "stderr": 10.513, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 25.0, "latency": null, "stderr": 9.934, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "kimi/kimi-k3": { "accuracy": 25.0, "latency": null, "stderr": 9.934, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 25.0, "latency": null, "stderr": 9.934, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6-luna": { "accuracy": 25.0, "latency": null, "stderr": 9.934, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 25.0, "latency": null, "stderr": 9.934, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 20.0, "latency": null, "stderr": 9.177, "cost_per_test": null, "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 } }, "highlight_js": { "anthropic/claude-opus-5-5": { "accuracy": 64.103, "latency": null, "stderr": 7.782, "cost_per_test": null, "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-5-1": { "accuracy": 56.41, "latency": null, "stderr": 8.044, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 51.282, "latency": null, "stderr": 8.108, "cost_per_test": null, "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-haiku-5-5": { "accuracy": 43.59, "latency": null, "stderr": 8.044, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "google/gemini-4-argon": { "accuracy": 43.59, "latency": null, "stderr": 8.044, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 41.026, "latency": null, "stderr": 7.979, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "meta/muse-wonder-full": { "accuracy": 41.026, "latency": null, "stderr": 7.979, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 38.462, "latency": null, "stderr": 7.892, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 65536, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "kimi/kimi-k3": { "accuracy": 35.897, "latency": null, "stderr": 7.782, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "meta/muse-wonder": { "accuracy": 35.897, "latency": null, "stderr": 7.782, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 35.897, "latency": null, "stderr": 7.782, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6.1-sol": { "accuracy": 35.897, "latency": null, "stderr": 7.782, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 35.897, "latency": null, "stderr": 7.782, "cost_per_test": null, "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 }, "alibaba/qwen3.8-max": { "accuracy": 33.333, "latency": null, "stderr": 7.647, "cost_per_test": null, "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-6-astra": { "accuracy": 33.333, "latency": null, "stderr": 7.647, "cost_per_test": null, "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-luna": { "accuracy": 30.769, "latency": null, "stderr": 7.487, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 30.769, "latency": null, "stderr": 7.487, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "grok/grok-4.7": { "accuracy": 28.205, "latency": null, "stderr": 7.3, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null } }, "lighthouse": { "anthropic/claude-opus-5-5": { "accuracy": 72.222, "latency": null, "stderr": 6.152, "cost_per_test": null, "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-5-1": { "accuracy": 64.815, "latency": null, "stderr": 6.56, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 50.0, "latency": null, "stderr": 6.868, "cost_per_test": null, "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-4-argon": { "accuracy": 46.296, "latency": null, "stderr": 6.849, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 37.037, "latency": null, "stderr": 6.633, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "meta/muse-wonder-full": { "accuracy": 29.63, "latency": null, "stderr": 6.272, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 29.63, "latency": null, "stderr": 6.272, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "kimi/kimi-k3": { "accuracy": 25.926, "latency": null, "stderr": 6.02, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "meta/muse-wonder": { "accuracy": 25.926, "latency": null, "stderr": 6.02, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 24.074, "latency": null, "stderr": 5.873, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "grok/grok-4.7": { "accuracy": 24.074, "latency": null, "stderr": 5.873, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "openai/gpt-6-astra": { "accuracy": 24.074, "latency": null, "stderr": 5.873, "cost_per_test": null, "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-6.1-sol": { "accuracy": 24.074, "latency": null, "stderr": 5.873, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 24.074, "latency": null, "stderr": 5.873, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 22.222, "latency": null, "stderr": 5.711, "cost_per_test": null, "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 }, "google/gemini-3.8-flash": { "accuracy": 20.37, "latency": null, "stderr": 5.532, "cost_per_test": null, "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/qwen3.8-max": { "accuracy": 18.519, "latency": null, "stderr": 5.336, "cost_per_test": null, "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-6-luna": { "accuracy": 16.667, "latency": null, "stderr": 5.119, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null } }, "openlayers": { "anthropic/claude-opus-5-5": { "accuracy": 92.208, "latency": null, "stderr": 3.075, "cost_per_test": null, "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-5-1": { "accuracy": 87.013, "latency": null, "stderr": 3.856, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 84.416, "latency": null, "stderr": 4.161, "cost_per_test": null, "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-6.1-sol": { "accuracy": 84.416, "latency": null, "stderr": 4.161, "cost_per_test": null, "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": 83.117, "latency": null, "stderr": 4.297, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "meta/muse-wonder": { "accuracy": 81.818, "latency": null, "stderr": 4.424, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "google/gemini-4-argon": { "accuracy": 80.519, "latency": null, "stderr": 4.543, "cost_per_test": null, "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-haiku-5-5": { "accuracy": 79.221, "latency": null, "stderr": 4.654, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "grok/grok-4.7": { "accuracy": 79.221, "latency": null, "stderr": 4.654, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "meta/muse-wonder-full": { "accuracy": 79.221, "latency": null, "stderr": 4.654, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 77.922, "latency": null, "stderr": 4.758, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6-luna": { "accuracy": 77.922, "latency": null, "stderr": 4.758, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 77.922, "latency": null, "stderr": 4.758, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 76.623, "latency": null, "stderr": 4.855, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 76.623, "latency": null, "stderr": 4.855, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 65536, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 74.026, "latency": null, "stderr": 5.03, "cost_per_test": null, "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 }, "kimi/kimi-k3": { "accuracy": 61.039, "latency": null, "stderr": 5.594, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "alibaba/qwen3.8-max": { "accuracy": 57.143, "latency": null, "stderr": 5.677, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null } }, "prettier": { "anthropic/claude-opus-5-5": { "accuracy": 92.308, "latency": null, "stderr": 7.692, "cost_per_test": null, "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-5-1": { "accuracy": 76.923, "latency": null, "stderr": 12.163, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 76.923, "latency": null, "stderr": 12.163, "cost_per_test": null, "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": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "google/gemini-4-argon": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "grok/grok-4.7": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "meta/muse-wonder": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse-wonder-full": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6-astra": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "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-6.1-sol": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 61.538, "latency": null, "stderr": 14.044, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 53.846, "latency": null, "stderr": 14.391, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 53.846, "latency": null, "stderr": 14.391, "cost_per_test": null, "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 }, "google/gemini-3.8-flash": { "accuracy": 46.154, "latency": null, "stderr": 14.391, "cost_per_test": null, "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-6-luna": { "accuracy": 46.154, "latency": null, "stderr": 14.391, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "kimi/kimi-k3": { "accuracy": 0.0, "latency": null, "stderr": 0.0, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null } }, "prism": { "anthropic/claude-opus-5-5": { "accuracy": 89.474, "latency": null, "stderr": 5.045, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 73.684, "latency": null, "stderr": 7.239, "cost_per_test": null, "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-5-1": { "accuracy": 71.053, "latency": null, "stderr": 7.456, "cost_per_test": null, "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-4-argon": { "accuracy": 63.158, "latency": null, "stderr": 7.93, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 60.526, "latency": null, "stderr": 8.036, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "kimi/kimi-k3": { "accuracy": 55.263, "latency": null, "stderr": 8.174, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 52.632, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "grok/grok-4.7": { "accuracy": 52.632, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "meta/muse-wonder-full": { "accuracy": 50.0, "latency": null, "stderr": 8.22, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6.1-sol": { "accuracy": 50.0, "latency": null, "stderr": 8.22, "cost_per_test": null, "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": 47.368, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 47.368, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 65536, "reasoning": null, "reasoning_effort": "high", "verbosity": null, "compute_effort": null, "provider": "Google", "harness": null }, "meta/muse-wonder": { "accuracy": 47.368, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 47.368, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "openai/gpt-6-astra": { "accuracy": 47.368, "latency": null, "stderr": 8.209, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 44.737, "latency": null, "stderr": 8.174, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 44.737, "latency": null, "stderr": 8.174, "cost_per_test": null, "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-6-luna": { "accuracy": 39.474, "latency": null, "stderr": 8.036, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null } }, "scratch_gui": { "anthropic/claude-opus-5-5": { "accuracy": 50.0, "latency": null, "stderr": 22.361, "cost_per_test": null, "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-sonnet-5-5": { "accuracy": 50.0, "latency": null, "stderr": 22.361, "cost_per_test": null, "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-4-argon": { "accuracy": 50.0, "latency": null, "stderr": 22.361, "cost_per_test": null, "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-5-1": { "accuracy": 33.333, "latency": null, "stderr": 21.082, "cost_per_test": null, "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-wonder": { "accuracy": 33.333, "latency": null, "stderr": 21.082, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "meta/muse-wonder-full": { "accuracy": 33.333, "latency": null, "stderr": 21.082, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null }, "alibaba/qwen3.8-max": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "temperature": 0.7, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Alibaba", "harness": null }, "anthropic/claude-haiku-5-5": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": "max", "provider": "Anthropic", "harness": null }, "deepseek/deepseek-v4.1-flash": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "temperature": 1.0, "top_p": 1.0, "max_output_tokens": 384000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "DeepSeek", "harness": null }, "google/gemini-3.8-flash": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "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-4.7": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "temperature": 0.7, "top_p": 0.95, "max_output_tokens": null, "reasoning": null, "reasoning_effort": "xhigh", "verbosity": null, "compute_effort": null, "provider": "SpaceXAI", "harness": null }, "openai/gpt-6-astra": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "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-luna": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "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-6.1-sol": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "temperature": null, "top_p": null, "max_output_tokens": 128000, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "OpenAI", "harness": null }, "stepfun/step-5-preview": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 1024000, "reasoning": null, "reasoning_effort": null, "verbosity": null, "compute_effort": null, "provider": "Stepfun", "harness": null }, "xiaomi/mimo-v2.6-pro": { "accuracy": 16.667, "latency": null, "stderr": 16.667, "cost_per_test": null, "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 }, "kimi/kimi-k3": { "accuracy": 0.0, "latency": null, "stderr": 0.0, "cost_per_test": null, "temperature": 1.0, "top_p": 0.95, "max_output_tokens": 262144, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Moonshot AI", "harness": null }, "meta/muse_spark_1_3_max": { "accuracy": 0.0, "latency": null, "stderr": 0.0, "cost_per_test": null, "temperature": 1.0, "top_p": null, "max_output_tokens": 131072, "reasoning": null, "reasoning_effort": "max", "verbosity": null, "compute_effort": null, "provider": "Meta", "harness": null } } } }