{ "fetched_at": "2026-11-05T01:31:29+00:00", "methodology": "Published third-party tables indexed as displayed; TANDIU did not run or reproduce the evaluations. Per model, each source contributes its best published result (non-estimated first); the matched reasoning-effort configuration is recorded in field 'effort'.", "composite_method": "composite.score = mean of the model's percentile within each source, percentiles computed among models tracked by TANDIU (sources with >= 5 matched models). It is a cross-source rank aggregate, not a new benchmark score. flags: source_divergence when two sources' percentiles differ by >= 35 points; effort_mismatch when AA and LiveBench matched configurations differ by >= 2 effort levels; aa_archived when AA lists the model as deprecated.", "sources": [ { "id": "artificial-analysis", "name": "Artificial Analysis", "url": "https://artificialanalysis.ai/leaderboards/models", "status": "ok", "retrieved_at": "2026-11-05T01:31:29+00:00", "page_sha256": "45a8f5c7b5d4fa783dba9e08855f15a3f7c4d1af08199f10a748b0e408056b2e", "published_rows": 93, "parse_method": "embedded-json", "archived_rows": 0, "index_name": "Intelligence Index v5.0.1" }, { "id": "livebench", "name": "LiveBench 2.0", "publisher": "LiveBench research team", "url": "https://livebench.ai/", "status": "ok", "retrieved_at": "2026-11-05T01:31:29+00:00", "data_url": "https://livebench.ai/data/20261025/table.csv", "table_created": "2026-10-25", "dataset_revision": "2026-10-30", "dataset_revised_at": "2026-10-30T22:21:40+00:00", "dataset_commit": null, "page_sha256": "a790e07b2ed710fbaa90eec799fcdfcbc04e4d37c16f7dc45cb3071717694d02", "published_rows": 32, "score_method": "Mean within each published category, then equal-weight mean across categories; mirrors the source leaderboard." }, { "id": "epoch", "name": "Epoch AI · Epoch Capabilities Index", "publisher": "Epoch AI", "url": "https://epoch.ai/benchmarks", "status": "ok", "retrieved_at": "2026-11-05T01:31:29+00:00", "data_url": "https://epoch.ai/data/benchmark_data.zip", "data_file": "epoch_capabilities_index/eci_scores.csv", "dataset_revision": "2026-11-05", "page_sha256": "25f56b00d53775fa31e95b9f81e0ad5ec815d084b1eb9c87894a8d0df15a2c03", "published_rows": 253, "license": "CC BY 4.0", "citation": "Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks", "score_method": "Epoch Capabilities Index (ECI) as published, with 90% bootstrap interval; model-level, no reasoning-effort split." } ], "matched": [ { "litellm_key": "gpt-5.6", "display": "GPT-5.6 Sol", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.6 Sol", "eci": 162.99, "eci_ci_low": 160.72, "eci_ci_high": 165.46, "release_date": "2026-07-09", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.6 Sol", "effort": null }, "matched_source_count": 1, "composite": { "score": 81.5, "source_count": 1, "percentiles": { "epoch": 81.5 }, "rank": 11, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.6-terra", "display": "GPT-5.6 Terra", "artificial_analysis": null, "livebench": { "source_model": "gpt-5.6-terra", "overall_score": 70.84, "category_scores": { "Long Agentic": 33.1, "Reasoning": 90.6, "Coding": 86.2, "Browser": 70.3, "Data Analysis": 79.3, "Research": 60.4, "Design": 76.0 }, "mapping": "exact", "mapping_target": "GPT-5.6 Terra", "effort": null }, "epoch": { "source_model": "GPT-5.6 Terra", "eci": 160.89, "eci_ci_low": 158.67, "eci_ci_high": 163.42, "release_date": "2026-07-09", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.6 Terra", "effort": null }, "matched_source_count": 2, "composite": { "score": 59.7, "source_count": 2, "percentiles": { "livebench": 43.5, "epoch": 75.9 }, "rank": 21, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.6-luna", "display": "GPT-5.6 Luna", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.6 Luna", "eci": 156.79, "eci_ci_low": 154.91, "eci_ci_high": 158.82, "release_date": "2026-07-09", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.6 Luna", "effort": null }, "matched_source_count": 1, "composite": { "score": 51.9, "source_count": 1, "percentiles": { "epoch": 51.9 }, "rank": 25, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.5", "display": "GPT-5.5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.5", "eci": 160.04, "eci_ci_low": 158.05, "eci_ci_high": 162.19, "release_date": "2026-04-23", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.5", "effort": null }, "matched_source_count": 1, "composite": { "score": 70.4, "source_count": 1, "percentiles": { "epoch": 70.4 }, "rank": 15, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.5-pro", "display": "GPT-5.5 Pro", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.5 Pro", "eci": 162.67, "eci_ci_low": 160.02, "eci_ci_high": 165.56, "release_date": "2026-04-23", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.5 Pro", "effort": null }, "matched_source_count": 1, "composite": { "score": 79.6, "source_count": 1, "percentiles": { "epoch": 79.6 }, "rank": 12, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.4", "display": "GPT-5.4", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.4", "eci": 157.82, "eci_ci_low": 155.98, "eci_ci_high": 159.87, "release_date": "2026-03-05", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4", "effort": null }, "matched_source_count": 1, "composite": { "score": 55.6, "source_count": 1, "percentiles": { "epoch": 55.6 }, "rank": 22, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.4-pro", "display": "GPT-5.4 Pro", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.4 Pro", "eci": 160.21, "eci_ci_low": 157.71, "eci_ci_high": 162.95, "release_date": "2026-03-05", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4 Pro", "effort": null }, "matched_source_count": 1, "composite": { "score": 72.2, "source_count": 1, "percentiles": { "epoch": 72.2 }, "rank": 14, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.4-mini", "display": "GPT-5.4 mini", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.4 Mini", "eci": 149.34, "eci_ci_low": 147.69, "eci_ci_high": 151.08, "release_date": "2026-03-17", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4 mini", "effort": null }, "matched_source_count": 1, "composite": { "score": 13.0, "source_count": 1, "percentiles": { "epoch": 13.0 }, "rank": 53, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-5.4-nano", "display": "GPT-5.4 nano", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-5.4 Nano", "eci": 146.4, "eci_ci_low": 144.68, "eci_ci_high": 148.09, "release_date": "2026-03-17", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4 nano", "effort": null }, "matched_source_count": 1, "composite": { "score": 5.6, "source_count": 1, "percentiles": { "epoch": 5.6 }, "rank": 58, "population": 61 }, "flags": [] }, { "litellm_key": "claude-opus-5", "display": "Claude Opus 5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Claude Opus 5", "eci": 164.45, "eci_ci_low": 162.0, "eci_ci_high": 167.17, "release_date": "2026-07-24", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Opus 5", "effort": null }, "matched_source_count": 1, "composite": { "score": 87.0, "source_count": 1, "percentiles": { "epoch": 87.0 }, "rank": 4, "population": 61 }, "flags": [] }, { "litellm_key": "claude-fable-5", "display": "Claude Fable 5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Claude Fable 5", "eci": 164.19, "eci_ci_low": 161.77, "eci_ci_high": 166.87, "release_date": "2026-06-09", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Fable 5", "effort": null }, "matched_source_count": 1, "composite": { "score": 85.2, "source_count": 1, "percentiles": { "epoch": 85.2 }, "rank": 6, "population": 61 }, "flags": [] }, { "litellm_key": "claude-sonnet-5", "display": "Claude Sonnet 5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Claude Sonnet 5", "eci": 156.71, "eci_ci_low": 154.7, "eci_ci_high": 158.8, "release_date": "2026-06-30", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Sonnet 5", "effort": null }, "matched_source_count": 1, "composite": { "score": 50.0, "source_count": 1, "percentiles": { "epoch": 50.0 }, "rank": 27, "population": 61 }, "flags": [] }, { "litellm_key": "claude-opus-4-8", "display": "Claude Opus 4.8", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Claude Opus 4.8", "eci": 159.89, "eci_ci_low": 157.9, "eci_ci_high": 162.19, "release_date": "2026-05-28", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Opus 4.8", "effort": null }, "matched_source_count": 1, "composite": { "score": 68.5, "source_count": 1, "percentiles": { "epoch": 68.5 }, "rank": 16, "population": 61 }, "flags": [] }, { "litellm_key": "claude-sonnet-4-6", "display": "Claude Sonnet 4.6", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Claude Sonnet 4.6", "eci": 152.86, "eci_ci_low": 151.21, "eci_ci_high": 154.68, "release_date": "2026-02-17", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Sonnet 4.6", "effort": null }, "matched_source_count": 1, "composite": { "score": 25.9, "source_count": 1, "percentiles": { "epoch": 25.9 }, "rank": 43, "population": 61 }, "flags": [] }, { "litellm_key": "claude-haiku-4-5", "display": "Claude Haiku 4.5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Claude Haiku 4.5", "eci": 142.82, "eci_ci_low": 141.09, "eci_ci_high": 144.42, "release_date": "2025-10-15", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Haiku 4.5", "effort": null }, "matched_source_count": 1, "composite": { "score": 0.0, "source_count": 1, "percentiles": { "epoch": 0.0 }, "rank": 61, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.7-flash", "display": "Gemini 3.7 Flash", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3.7 Flash", "eci": 158.4, "eci_ci_low": 156.44, "eci_ci_high": 160.56, "release_date": "2026-08-13", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.7 Flash", "effort": null }, "matched_source_count": 1, "composite": { "score": 61.1, "source_count": 1, "percentiles": { "epoch": 61.1 }, "rank": 20, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.6-flash", "display": "Gemini 3.6 Flash", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3.6 Flash", "eci": 155.21, "eci_ci_low": 153.45, "eci_ci_high": 157.14, "release_date": "2026-07-21", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.6 Flash", "effort": null }, "matched_source_count": 1, "composite": { "score": 37.0, "source_count": 1, "percentiles": { "epoch": 37.0 }, "rank": 36, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.5-flash", "display": "Gemini 3.5 Flash", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3.5 Flash", "eci": 155.24, "eci_ci_low": 153.39, "eci_ci_high": 157.22, "release_date": "2026-05-19", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.5 Flash", "effort": null }, "matched_source_count": 1, "composite": { "score": 38.9, "source_count": 1, "percentiles": { "epoch": 38.9 }, "rank": 33, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.5-flash-lite", "display": "Gemini 3.5 Flash-Lite", "source_model": "Gemini 3.5 Flash-Lite", "source_slug": "gemini-3-5-flash-lite", "context": 1000000, "creator": "Google", "intelligence_index": 11.7, "cost_per_task_usd": 0.69, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Gemini 3.5 Flash-Lite", "effort": null, "artificial_analysis": { "source_model": "Gemini 3.5 Flash-Lite", "source_slug": "gemini-3-5-flash-lite", "context": 1000000, "creator": "Google", "intelligence_index": 11.7, "cost_per_task_usd": 0.69, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Gemini 3.5 Flash-Lite", "effort": null }, "livebench": null, "epoch": { "source_model": "Gemini 3.5 Flash-Lite", "eci": 145.59, "eci_ci_low": 143.92, "eci_ci_high": 147.23, "release_date": "2026-07-21", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.5 Flash-Lite", "effort": null }, "matched_source_count": 2, "composite": { "score": 1.9, "source_count": 2, "percentiles": { "artificial_analysis": 0.0, "epoch": 3.7 }, "rank": 59, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.1-pro-preview", "display": "Gemini 3.1 Pro", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3.1 Pro", "eci": 156.24, "eci_ci_low": 154.57, "eci_ci_high": 158.09, "release_date": "2026-02-19", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.1 Pro", "effort": null }, "matched_source_count": 1, "composite": { "score": 46.3, "source_count": 1, "percentiles": { "epoch": 46.3 }, "rank": 29, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.1-flash-lite", "display": "Gemini 3.1 Flash-Lite", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3.1 Flash-Lite", "eci": 144.91, "eci_ci_low": 142.66, "eci_ci_high": 147.19, "release_date": "2026-03-03", "organization": "Google", "mapping": "exact", "mapping_target": "Gemini 3.1 Flash-Lite", "effort": null }, "matched_source_count": 1, "composite": { "score": 1.9, "source_count": 1, "percentiles": { "epoch": 1.9 }, "rank": 60, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3-flash-preview", "display": "Gemini 3 Flash", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3 Flash", "eci": 152.25, "eci_ci_low": 150.67, "eci_ci_high": 153.98, "release_date": "2025-12-17", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3 Flash", "effort": null }, "matched_source_count": 1, "composite": { "score": 22.2, "source_count": 1, "percentiles": { "epoch": 22.2 }, "rank": 45, "population": 61 }, "flags": [] }, { "litellm_key": "xai/grok-4.6", "display": "Grok 4.6", "artificial_analysis": null, "livebench": { "source_model": "grok-4.6", "overall_score": 71.04, "category_scores": { "Long Agentic": 28.0, "Reasoning": 91.2, "Coding": 89.1, "Browser": 49.4, "Data Analysis": 75.3, "Research": 84.5, "Design": 79.8 }, "mapping": "exact", "mapping_target": "Grok 4.6", "effort": null }, "epoch": { "source_model": "Grok 4.6", "eci": 157.92, "eci_ci_low": 155.99, "eci_ci_high": 160.09, "release_date": "2026-08-12", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.6", "effort": null }, "matched_source_count": 2, "composite": { "score": 52.6, "source_count": 2, "percentiles": { "livebench": 47.8, "epoch": 57.4 }, "rank": 24, "population": 61 }, "flags": [] }, { "litellm_key": "xai/grok-4.5", "display": "Grok 4.5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Grok 4.5", "eci": 155.08, "eci_ci_low": 153.29, "eci_ci_high": 157.04, "release_date": "2026-07-08", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.5", "effort": null }, "matched_source_count": 1, "composite": { "score": 35.2, "source_count": 1, "percentiles": { "epoch": 35.2 }, "rank": 38, "population": 61 }, "flags": [] }, { "litellm_key": "xai/grok-4.3", "display": "Grok 4.3", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Grok 4.3 Beta", "eci": 150.0, "eci_ci_low": 148.05, "eci_ci_high": 151.98, "release_date": "2026-04-17", "organization": "xAI", "mapping": "variant", "mapping_target": "Grok 4.3", "effort": null }, "matched_source_count": 1, "composite": { "score": 14.8, "source_count": 1, "percentiles": { "epoch": 14.8 }, "rank": 52, "population": 61 }, "flags": [] }, { "litellm_key": "deepseek-v4-pro", "display": "DeepSeek V4 Pro", "source_model": "DeepSeek V4 Pro 0813 (max)", "source_slug": "deepseek-v4-pro", "context": 1000000, "creator": "DeepSeek", "intelligence_index": 23.1, "cost_per_task_usd": 1.77, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "DeepSeek V4 Pro", "effort": "max", "artificial_analysis": { "source_model": "DeepSeek V4 Pro 0813 (max)", "source_slug": "deepseek-v4-pro", "context": 1000000, "creator": "DeepSeek", "intelligence_index": 23.1, "cost_per_task_usd": 1.77, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "DeepSeek V4 Pro", "effort": "max" }, "livebench": null, "epoch": { "source_model": "DeepSeek V4 Pro 0813", "eci": 155.87, "eci_ci_low": 154.01, "eci_ci_high": 157.89, "release_date": "2026-08-13", "organization": "DeepSeek", "mapping": "variant", "mapping_target": "DeepSeek V4 Pro", "effort": null }, "matched_source_count": 2, "composite": { "score": 27.3, "source_count": 2, "percentiles": { "artificial_analysis": 12.0, "epoch": 42.6 }, "rank": 41, "population": 61 }, "flags": [] }, { "litellm_key": "deepseek-v4-flash", "display": "DeepSeek V4.1 Flash", "source_model": "DeepSeek V4.1 Flash 1017 (max)", "source_slug": "deepseek-v4-1-flash-1017", "context": 1000000, "creator": "DeepSeek", "intelligence_index": 32.6, "cost_per_task_usd": 0.6, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "DeepSeek V4.1 Flash", "effort": "max", "artificial_analysis": { "source_model": "DeepSeek V4.1 Flash 1017 (max)", "source_slug": "deepseek-v4-1-flash-1017", "context": 1000000, "creator": "DeepSeek", "intelligence_index": 32.6, "cost_per_task_usd": 0.6, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "DeepSeek V4.1 Flash", "effort": "max" }, "livebench": { "source_model": "deepseek-v4.1-flash-1017", "overall_score": 75.77, "category_scores": { "Long Agentic": 35.7, "Reasoning": 89.1, "Coding": 96.0, "Browser": 67.2, "Data Analysis": 79.5, "Research": 79.5, "Design": 83.4 }, "mapping": "variant", "mapping_target": "DeepSeek V4.1 Flash", "effort": null }, "epoch": { "source_model": "DeepSeek V4.1 Flash 1017", "eci": 159.31, "eci_ci_low": 157.04, "eci_ci_high": 161.78, "release_date": "2026-10-17", "organization": "DeepSeek", "mapping": "variant", "mapping_target": "DeepSeek V4.1 Flash", "effort": null }, "matched_source_count": 3, "composite": { "score": 62.8, "source_count": 3, "percentiles": { "artificial_analysis": 52.0, "livebench": 69.6, "epoch": 66.7 }, "rank": 19, "population": 61 }, "flags": [] }, { "litellm_key": "dashscope/qwen3.7-max", "display": "Qwen3.7-Max", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Qwen3.7-Max", "eci": 154.5, "eci_ci_low": 152.53, "eci_ci_high": 156.63, "release_date": "2026-05-19", "organization": "Alibaba", "mapping": "exact", "mapping_target": "Qwen3.7-Max", "effort": null }, "matched_source_count": 1, "composite": { "score": 31.5, "source_count": 1, "percentiles": { "epoch": 31.5 }, "rank": 39, "population": 61 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k3", "display": "Kimi K3", "artificial_analysis": null, "livebench": { "source_model": "kimi-k3", "overall_score": 69.5, "category_scores": { "Long Agentic": 26.4, "Reasoning": 90.7, "Coding": 59.3, "Browser": 75.2, "Data Analysis": 78.7, "Research": 79.0, "Design": 77.2 }, "mapping": "exact", "mapping_target": "Kimi K3", "effort": null }, "epoch": { "source_model": "Kimi K3", "eci": 158.51, "eci_ci_low": 156.53, "eci_ci_high": 160.59, "release_date": "2026-07-16", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K3", "effort": null }, "matched_source_count": 2, "composite": { "score": 48.9, "source_count": 2, "percentiles": { "livebench": 34.8, "epoch": 63.0 }, "rank": 28, "population": 61 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k2.7-code", "display": "Kimi K2.7 Code", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Kimi K2.7 Code", "eci": 151.16, "eci_ci_low": 149.13, "eci_ci_high": 153.27, "release_date": "2026-06-12", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K2.7 Code", "effort": null }, "matched_source_count": 1, "composite": { "score": 18.5, "source_count": 1, "percentiles": { "epoch": 18.5 }, "rank": 49, "population": 61 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k2.6", "display": "Kimi K2.6", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Kimi K2.6", "eci": 151.56, "eci_ci_low": 149.79, "eci_ci_high": 153.4, "release_date": "2026-04-20", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K2.6", "effort": null }, "matched_source_count": 1, "composite": { "score": 20.4, "source_count": 1, "percentiles": { "epoch": 20.4 }, "rank": 46, "population": 61 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k2.5", "display": "Kimi K2.5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Kimi K2.5", "eci": 148.72, "eci_ci_low": 147.15, "eci_ci_high": 150.34, "release_date": "2026-01-27", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K2.5", "effort": null }, "matched_source_count": 1, "composite": { "score": 11.1, "source_count": 1, "percentiles": { "epoch": 11.1 }, "rank": 54, "population": 61 }, "flags": [] }, { "litellm_key": "zai/glm-5.3", "display": "GLM-5.3", "source_model": "GLM-5.3 (max)", "source_slug": "glm-5-3", "context": 1000000, "creator": "Z AI", "intelligence_index": 31.7, "cost_per_task_usd": 5.01, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GLM-5.3", "effort": "max", "artificial_analysis": { "source_model": "GLM-5.3 (max)", "source_slug": "glm-5-3", "context": 1000000, "creator": "Z AI", "intelligence_index": 31.7, "cost_per_task_usd": 5.01, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GLM-5.3", "effort": "max" }, "livebench": null, "epoch": { "source_model": "GLM-5.3", "eci": 156.91, "eci_ci_low": 154.8, "eci_ci_high": 159.23, "release_date": "2026-08-14", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5.3", "effort": null }, "matched_source_count": 2, "composite": { "score": 50.9, "source_count": 2, "percentiles": { "artificial_analysis": 48.0, "epoch": 53.7 }, "rank": 26, "population": 61 }, "flags": [] }, { "litellm_key": "zai/glm-5.2", "display": "GLM-5.2", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GLM-5.2", "eci": 152.99, "eci_ci_low": 151.27, "eci_ci_high": 154.77, "release_date": "2026-06-16", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5.2", "effort": null }, "matched_source_count": 1, "composite": { "score": 27.8, "source_count": 1, "percentiles": { "epoch": 27.8 }, "rank": 40, "population": 61 }, "flags": [] }, { "litellm_key": "zai/glm-5.1", "display": "GLM-5.1", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GLM-5.1", "eci": 150.67, "eci_ci_low": 148.71, "eci_ci_high": 152.73, "release_date": "2026-04-07", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5.1", "effort": null }, "matched_source_count": 1, "composite": { "score": 16.7, "source_count": 1, "percentiles": { "epoch": 16.7 }, "rank": 50, "population": 61 }, "flags": [] }, { "litellm_key": "zai/glm-5", "display": "GLM-5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GLM-5", "eci": 146.43, "eci_ci_low": 144.87, "eci_ci_high": 148.04, "release_date": "2026-02-11", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5", "effort": null }, "matched_source_count": 1, "composite": { "score": 7.4, "source_count": 1, "percentiles": { "epoch": 7.4 }, "rank": 55, "population": 61 }, "flags": [] }, { "litellm_key": "minimax/MiniMax-M3", "display": "MiniMax M3", "source_model": "MiniMax-M3", "source_slug": "minimax-m3", "context": 1000000, "creator": "MiniMax", "intelligence_index": 18.9, "cost_per_task_usd": 1.29, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiniMax M3", "effort": null, "artificial_analysis": { "source_model": "MiniMax-M3", "source_slug": "minimax-m3", "context": 1000000, "creator": "MiniMax", "intelligence_index": 18.9, "cost_per_task_usd": 1.29, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiniMax M3", "effort": null }, "livebench": null, "epoch": { "source_model": "MiniMax-M3", "eci": 147.6, "eci_ci_low": 145.44, "eci_ci_high": 149.76, "release_date": "2026-06-01", "organization": "MiniMax", "mapping": "exact", "mapping_target": "MiniMax M3", "effort": null }, "matched_source_count": 2, "composite": { "score": 6.7, "source_count": 2, "percentiles": { "artificial_analysis": 4.0, "epoch": 9.3 }, "rank": 56, "population": 61 }, "flags": [] }, { "litellm_key": "minimax/MiniMax-M3.1-Flash", "display": "MiniMax M3.1 Flash", "source_model": "MiniMax-M3.1-Flash", "source_slug": "minimax-m3-1-flash", "context": 1000000, "creator": "MiniMax", "intelligence_index": 29.1, "cost_per_task_usd": 0.49, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiniMax M3.1 Flash", "effort": null, "artificial_analysis": { "source_model": "MiniMax-M3.1-Flash", "source_slug": "minimax-m3-1-flash", "context": 1000000, "creator": "MiniMax", "intelligence_index": 29.1, "cost_per_task_usd": 0.49, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiniMax M3.1 Flash", "effort": null }, "livebench": { "source_model": "minimax-m3.1-flash", "overall_score": 70.61, "category_scores": { "Long Agentic": 28.8, "Reasoning": 82.9, "Coding": 83.9, "Browser": 80.6, "Data Analysis": 71.4, "Research": 72.7, "Design": 74.0 }, "mapping": "exact", "mapping_target": "MiniMax M3.1 Flash", "effort": null }, "epoch": null, "matched_source_count": 2, "composite": { "score": 37.5, "source_count": 2, "percentiles": { "artificial_analysis": 36.0, "livebench": 39.1 }, "rank": 35, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-6-astra", "display": "GPT-6 Astra", "source_model": "GPT-6 Astra (max)", "source_slug": "gpt-6-astra", "context": 1000000, "creator": "OpenAI", "intelligence_index": 56.9, "cost_per_task_usd": 6.24, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6 Astra", "effort": "max", "artificial_analysis": { "source_model": "GPT-6 Astra (max)", "source_slug": "gpt-6-astra", "context": 1000000, "creator": "OpenAI", "intelligence_index": 56.9, "cost_per_task_usd": 6.24, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6 Astra", "effort": "max" }, "livebench": { "source_model": "gpt-6-astra", "overall_score": 86.49, "category_scores": { "Long Agentic": 77.5, "Reasoning": 92.7, "Coding": 93.7, "Browser": 91.3, "Data Analysis": 83.0, "Research": 85.2, "Design": 82.0 }, "mapping": "exact", "mapping_target": "GPT-6 Astra", "effort": null }, "epoch": { "source_model": "GPT-6 Astra", "eci": 169.07, "eci_ci_low": 166.16, "eci_ci_high": 172.28, "release_date": "2026-09-03", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6 Astra", "effort": null }, "matched_source_count": 3, "composite": { "score": 98.7, "source_count": 3, "percentiles": { "artificial_analysis": 96.0, "livebench": 100.0, "epoch": 100.0 }, "rank": 1, "population": 61 }, "flags": [] }, { "litellm_key": "claude-fable-5-1", "display": "Claude Fable 5.1", "source_model": "Claude Fable 5.1 (xhigh)", "source_slug": "claude-fable-5-1-xhigh", "context": 1000000, "creator": "Anthropic", "intelligence_index": 50.0, "cost_per_task_usd": 10.85, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Fable 5.1", "effort": "xhigh", "artificial_analysis": { "source_model": "Claude Fable 5.1 (xhigh)", "source_slug": "claude-fable-5-1-xhigh", "context": 1000000, "creator": "Anthropic", "intelligence_index": 50.0, "cost_per_task_usd": 10.85, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Fable 5.1", "effort": "xhigh" }, "livebench": { "source_model": "claude-fable-5.1", "overall_score": 86.11, "category_scores": { "Long Agentic": 77.9, "Reasoning": 91.7, "Coding": 97.7, "Browser": 89.8, "Data Analysis": 80.3, "Research": 82.0, "Design": 83.4 }, "mapping": "exact", "mapping_target": "Claude Fable 5.1", "effort": null }, "epoch": { "source_model": "Claude Fable 5.1", "eci": 166.9, "eci_ci_low": 164.27, "eci_ci_high": 169.85, "release_date": "2026-09-01", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Fable 5.1", "effort": null }, "matched_source_count": 3, "composite": { "score": 86.8, "source_count": 3, "percentiles": { "artificial_analysis": 72.0, "livebench": 95.7, "epoch": 92.6 }, "rank": 5, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.8-flash", "display": "Gemini 3.8 Flash", "source_model": "Gemini 3.8 Flash (high)", "source_slug": "gemini-3-8-flash", "context": 1000000, "creator": "Google", "intelligence_index": 30.8, "cost_per_task_usd": 7.77, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Gemini 3.8 Flash", "effort": "high", "artificial_analysis": { "source_model": "Gemini 3.8 Flash (high)", "source_slug": "gemini-3-8-flash", "context": 1000000, "creator": "Google", "intelligence_index": 30.8, "cost_per_task_usd": 7.77, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Gemini 3.8 Flash", "effort": "high" }, "livebench": { "source_model": "gemini-3.8-flash", "overall_score": 62.7, "category_scores": { "Long Agentic": 16.5, "Reasoning": 89.3, "Coding": 82.2, "Browser": 45.1, "Data Analysis": 54.0, "Research": 79.1, "Design": 72.7 }, "mapping": "exact", "mapping_target": "Gemini 3.8 Flash", "effort": null }, "epoch": { "source_model": "Gemini 3.8 Flash", "eci": 158.63, "eci_ci_low": 156.65, "eci_ci_high": 160.79, "release_date": "2026-09-02", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.8 Flash", "effort": null }, "matched_source_count": 3, "composite": { "score": 40.6, "source_count": 3, "percentiles": { "artificial_analysis": 44.0, "livebench": 13.0, "epoch": 64.8 }, "rank": 31, "population": 61 }, "flags": [ { "type": "source_divergence", "spread": 51.8, "percentiles": { "artificial_analysis": 44.0, "livebench": 13.0, "epoch": 64.8 } } ] }, { "litellm_key": "xai/grok-4.20", "display": "Grok 4.20", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Grok 4.20", "eci": 152.27, "eci_ci_low": 150.62, "eci_ci_high": 154.08, "release_date": "2026-02-17", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.20", "effort": null }, "matched_source_count": 1, "composite": { "score": 24.1, "source_count": 1, "percentiles": { "epoch": 24.1 }, "rank": 44, "population": 61 }, "flags": [] }, { "litellm_key": "dashscope/qwen3.8-max", "display": "Qwen3.8-Max", "source_model": "Qwen3.8 Max (0902)", "source_slug": "qwen3-8-max", "context": 983616, "creator": "Alibaba", "intelligence_index": 33.7, "cost_per_task_usd": 10.02, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Qwen3.8-Max", "effort": null, "artificial_analysis": { "source_model": "Qwen3.8 Max (0902)", "source_slug": "qwen3-8-max", "context": 983616, "creator": "Alibaba", "intelligence_index": 33.7, "cost_per_task_usd": 10.02, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Qwen3.8-Max", "effort": null }, "livebench": { "source_model": "qwen3.8-max", "overall_score": 64.96, "category_scores": { "Long Agentic": 29.9, "Reasoning": 88.2, "Coding": 60.3, "Browser": 49.4, "Data Analysis": 78.4, "Research": 69.9, "Design": 78.6 }, "mapping": "exact", "mapping_target": "Qwen3.8-Max", "effort": null }, "epoch": { "source_model": "Qwen3.8 Max (0902)", "eci": 155.85, "eci_ci_low": 153.66, "eci_ci_high": 158.11, "release_date": "2026-09-01", "organization": "Alibaba", "mapping": "variant", "mapping_target": "Qwen3.8-Max", "effort": null }, "matched_source_count": 3, "composite": { "score": 38.0, "source_count": 3, "percentiles": { "artificial_analysis": 56.0, "livebench": 17.4, "epoch": 40.7 }, "rank": 34, "population": 61 }, "flags": [ { "type": "source_divergence", "spread": 38.6, "percentiles": { "artificial_analysis": 56.0, "livebench": 17.4, "epoch": 40.7 } } ] }, { "litellm_key": "meta/muse-spark-1.3", "display": "Muse Spark 1.3", "artificial_analysis": null, "livebench": { "source_model": "muse-spark-1.3", "overall_score": 65.61, "category_scores": { "Long Agentic": 25.5, "Reasoning": 89.7, "Coding": 90.2, "Browser": 30.9, "Data Analysis": 79.6, "Research": 68.6, "Design": 74.8 }, "mapping": "exact", "mapping_target": "Muse Spark 1.3", "effort": null }, "epoch": { "source_model": "Muse Spark 1.3", "eci": 157.98, "eci_ci_low": 155.93, "eci_ci_high": 160.19, "release_date": "2026-09-02", "organization": "Meta AI", "mapping": "exact", "mapping_target": "Muse Spark 1.3", "effort": null }, "matched_source_count": 2, "composite": { "score": 40.5, "source_count": 2, "percentiles": { "livebench": 21.7, "epoch": 59.3 }, "rank": 32, "population": 61 }, "flags": [ { "type": "source_divergence", "spread": 37.6, "percentiles": { "livebench": 21.7, "epoch": 59.3 } } ] }, { "litellm_key": "xai/grok-4.7", "display": "Grok 4.7", "source_model": "Grok 4.7 (xhigh)", "source_slug": "grok-4-7", "context": 500000, "creator": "SpaceXAI", "intelligence_index": 35.5, "cost_per_task_usd": 7.77, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Grok 4.7", "effort": "xhigh", "artificial_analysis": { "source_model": "Grok 4.7 (xhigh)", "source_slug": "grok-4-7", "context": 500000, "creator": "SpaceXAI", "intelligence_index": 35.5, "cost_per_task_usd": 7.77, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Grok 4.7", "effort": "xhigh" }, "livebench": { "source_model": "grok-4.7", "overall_score": 71.99, "category_scores": { "Long Agentic": 46.1, "Reasoning": 82.7, "Coding": 84.5, "Browser": 49.3, "Data Analysis": 76.9, "Research": 86.4, "Design": 78.0 }, "mapping": "exact", "mapping_target": "Grok 4.7", "effort": null }, "epoch": { "source_model": "Grok 4.7", "eci": 156.07, "eci_ci_low": 154.2, "eci_ci_high": 158.03, "release_date": "2026-09-21", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.7", "effort": null }, "matched_source_count": 3, "composite": { "score": 55.1, "source_count": 3, "percentiles": { "artificial_analysis": 60.0, "livebench": 60.9, "epoch": 44.4 }, "rank": 23, "population": 61 }, "flags": [] }, { "litellm_key": "claude-opus-5-5", "display": "Claude Opus 5.5", "source_model": "Claude Opus 5.5 (max)", "source_slug": "claude-opus-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 59.1, "cost_per_task_usd": 10.04, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Opus 5.5", "effort": "max", "artificial_analysis": { "source_model": "Claude Opus 5.5 (max)", "source_slug": "claude-opus-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 59.1, "cost_per_task_usd": 10.04, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Opus 5.5", "effort": "max" }, "livebench": { "source_model": "claude-opus-5.5", "overall_score": 85.99, "category_scores": { "Long Agentic": 72.8, "Reasoning": 92.2, "Coding": 96.3, "Browser": 88.4, "Data Analysis": 80.3, "Research": 85.0, "Design": 86.9 }, "mapping": "exact", "mapping_target": "Claude Opus 5.5", "effort": null }, "epoch": { "source_model": "Claude Opus 5.5", "eci": 168.36, "eci_ci_low": 165.54, "eci_ci_high": 171.51, "release_date": "2026-09-22", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Opus 5.5", "effort": null }, "matched_source_count": 3, "composite": { "score": 95.9, "source_count": 3, "percentiles": { "artificial_analysis": 100.0, "livebench": 91.3, "epoch": 96.3 }, "rank": 2, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-6-sol", "display": "GPT-6 Sol", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GPT-6 Sol", "eci": 164.06, "eci_ci_low": 161.58, "eci_ci_high": 166.8, "release_date": "2026-09-22", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6 Sol", "effort": null }, "matched_source_count": 1, "composite": { "score": 83.3, "source_count": 1, "percentiles": { "epoch": 83.3 }, "rank": 10, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-6-luna", "display": "GPT-6 Luna", "source_model": "GPT-6 Luna (max)", "source_slug": "gpt-6-luna", "context": 1000000, "creator": "OpenAI", "intelligence_index": 27.9, "cost_per_task_usd": 0.15, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6 Luna", "effort": "max", "artificial_analysis": { "source_model": "GPT-6 Luna (max)", "source_slug": "gpt-6-luna", "context": 1000000, "creator": "OpenAI", "intelligence_index": 27.9, "cost_per_task_usd": 0.15, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6 Luna", "effort": "max" }, "livebench": { "source_model": "gpt-6-luna", "overall_score": 66.7, "category_scores": { "Long Agentic": 30.9, "Reasoning": 81.8, "Coding": 84.5, "Browser": 70.3, "Data Analysis": 73.4, "Research": 43.5, "Design": 82.5 }, "mapping": "exact", "mapping_target": "GPT-6 Luna", "effort": null }, "epoch": { "source_model": "GPT-6 Luna", "eci": 156.68, "eci_ci_low": 154.78, "eci_ci_high": 158.74, "release_date": "2026-09-22", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6 Luna", "effort": null }, "matched_source_count": 3, "composite": { "score": 35.5, "source_count": 3, "percentiles": { "artificial_analysis": 28.0, "livebench": 30.4, "epoch": 48.1 }, "rank": 37, "population": 61 }, "flags": [] }, { "litellm_key": "stepfun/step-5-preview", "display": "Step 5 Preview", "source_model": "Step 5 Preview", "source_slug": "step-5", "context": 1000000, "creator": "StepFun", "intelligence_index": 28.5, "cost_per_task_usd": 2.35, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Step 5 Preview", "effort": null, "artificial_analysis": { "source_model": "Step 5 Preview", "source_slug": "step-5", "context": 1000000, "creator": "StepFun", "intelligence_index": 28.5, "cost_per_task_usd": 2.35, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Step 5 Preview", "effort": null }, "livebench": { "source_model": "step-5-preview", "overall_score": 60.97, "category_scores": { "Long Agentic": 19.4, "Reasoning": 83.8, "Coding": 85.6, "Browser": 24.8, "Data Analysis": 63.5, "Research": 72.8, "Design": 76.9 }, "mapping": "exact", "mapping_target": "Step 5 Preview", "effort": null }, "epoch": null, "matched_source_count": 2, "composite": { "score": 20.4, "source_count": 2, "percentiles": { "artificial_analysis": 32.0, "livebench": 8.7 }, "rank": 47, "population": 61 }, "flags": [] }, { "litellm_key": "dashscope/qwen3.8-27b", "display": "Qwen3.8 27B", "source_model": "Qwen3.8 27B (xhigh)", "source_slug": "qwen3-8-27b", "context": 256000, "creator": "Alibaba", "intelligence_index": 20.1, "cost_per_task_usd": 3.53, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Qwen3.8 27B", "effort": "xhigh", "artificial_analysis": { "source_model": "Qwen3.8 27B (xhigh)", "source_slug": "qwen3-8-27b", "context": 256000, "creator": "Alibaba", "intelligence_index": 20.1, "cost_per_task_usd": 3.53, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Qwen3.8 27B", "effort": "xhigh" }, "livebench": { "source_model": "qwen3.8-27b", "overall_score": 60.5, "category_scores": { "Long Agentic": 20.6, "Reasoning": 80.0, "Coding": 86.8, "Browser": 24.2, "Data Analysis": 76.6, "Research": 59.4, "Design": 75.9 }, "mapping": "exact", "mapping_target": "Qwen3.8 27B", "effort": null }, "epoch": null, "matched_source_count": 2, "composite": { "score": 6.2, "source_count": 2, "percentiles": { "artificial_analysis": 8.0, "livebench": 4.3 }, "rank": 57, "population": 61 }, "flags": [] }, { "litellm_key": "xiaomi_mimo/mimo-v2.6-pro", "display": "MiMo-V2.6-Pro", "source_model": "MiMo-V2.6-Pro", "source_slug": "mimo-v2-6-pro", "context": 1000000, "creator": "Xiaomi", "intelligence_index": 29.9, "cost_per_task_usd": 0.26, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiMo-V2.6-Pro", "effort": null, "artificial_analysis": { "source_model": "MiMo-V2.6-Pro", "source_slug": "mimo-v2-6-pro", "context": 1000000, "creator": "Xiaomi", "intelligence_index": 29.9, "cost_per_task_usd": 0.26, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiMo-V2.6-Pro", "effort": null }, "livebench": { "source_model": "mimo-v2.6-pro", "overall_score": 71.59, "category_scores": { "Long Agentic": 35.2, "Reasoning": 79.6, "Coding": 81.5, "Browser": 77.3, "Data Analysis": 72.3, "Research": 76.7, "Design": 78.5 }, "mapping": "exact", "mapping_target": "MiMo-V2.6-Pro", "effort": null }, "epoch": null, "matched_source_count": 2, "composite": { "score": 46.1, "source_count": 2, "percentiles": { "artificial_analysis": 40.0, "livebench": 52.2 }, "rank": 30, "population": 61 }, "flags": [] }, { "litellm_key": "xiaomi_mimo/mimo-v2.6-flash", "display": "MiMo-V2.6-Flash", "source_model": "MiMo-V2.6-Flash", "source_slug": "mimo-v2-6-flash", "context": 1000000, "creator": "Xiaomi", "intelligence_index": 26.7, "cost_per_task_usd": 0.13, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiMo-V2.6-Flash", "effort": null, "artificial_analysis": { "source_model": "MiMo-V2.6-Flash", "source_slug": "mimo-v2-6-flash", "context": 1000000, "creator": "Xiaomi", "intelligence_index": 26.7, "cost_per_task_usd": 0.13, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiMo-V2.6-Flash", "effort": null }, "livebench": null, "epoch": null, "matched_source_count": 1, "composite": { "score": 20.0, "source_count": 1, "percentiles": { "artificial_analysis": 20.0 }, "rank": 48, "population": 61 }, "flags": [] }, { "litellm_key": "claude-sonnet-5-5", "display": "Claude Sonnet 5.5", "source_model": "Claude Sonnet 5.5 (max)", "source_slug": "claude-sonnet-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 54.5, "cost_per_task_usd": 10.02, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Sonnet 5.5", "effort": "max", "artificial_analysis": { "source_model": "Claude Sonnet 5.5 (max)", "source_slug": "claude-sonnet-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 54.5, "cost_per_task_usd": 10.02, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Sonnet 5.5", "effort": "max" }, "livebench": { "source_model": "claude-sonnet-5.5", "overall_score": 81.01, "category_scores": { "Long Agentic": 63.4, "Reasoning": 91.6, "Coding": 94.7, "Browser": 89.3, "Data Analysis": 59.5, "Research": 83.6, "Design": 85.0 }, "mapping": "exact", "mapping_target": "Claude Sonnet 5.5", "effort": null }, "epoch": { "source_model": "Claude Sonnet 5.5", "eci": 166.24, "eci_ci_low": 163.52, "eci_ci_high": 169.23, "release_date": "2026-09-28", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Sonnet 5.5", "effort": null }, "matched_source_count": 3, "composite": { "score": 85.1, "source_count": 3, "percentiles": { "artificial_analysis": 88.0, "livebench": 78.3, "epoch": 88.9 }, "rank": 7, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-6.1-sol", "display": "GPT-6.1 Sol", "source_model": "GPT-6.1 Sol (max)", "source_slug": "gpt-6-1-sol", "context": 1000000, "creator": "OpenAI", "intelligence_index": 54.6, "cost_per_task_usd": 1.27, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6.1 Sol", "effort": "max", "artificial_analysis": { "source_model": "GPT-6.1 Sol (max)", "source_slug": "gpt-6-1-sol", "context": 1000000, "creator": "OpenAI", "intelligence_index": 54.6, "cost_per_task_usd": 1.27, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6.1 Sol", "effort": "max" }, "livebench": { "source_model": "gpt-6.1-sol", "overall_score": 85.56, "category_scores": { "Long Agentic": 68.7, "Reasoning": 92.6, "Coding": 96.0, "Browser": 93.3, "Data Analysis": 82.7, "Research": 83.5, "Design": 82.1 }, "mapping": "exact", "mapping_target": "GPT-6.1 Sol", "effort": null }, "epoch": { "source_model": "GPT-6.1 Sol", "eci": 168.94, "eci_ci_low": 165.97, "eci_ci_high": 172.19, "release_date": "2026-09-29", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6.1 Sol", "effort": null }, "matched_source_count": 3, "composite": { "score": 92.4, "source_count": 3, "percentiles": { "artificial_analysis": 92.0, "livebench": 87.0, "epoch": 98.1 }, "rank": 3, "population": 61 }, "flags": [] }, { "litellm_key": "zai/glm-5.3-flash", "display": "GLM-5.3-Flash", "source_model": "GLM-5.3-Flash", "source_slug": "glm-5-3-flash", "context": 1000000, "creator": "Z AI", "intelligence_index": 27.8, "cost_per_task_usd": 0.58, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "GLM-5.3-Flash", "effort": null, "artificial_analysis": { "source_model": "GLM-5.3-Flash", "source_slug": "glm-5-3-flash", "context": 1000000, "creator": "Z AI", "intelligence_index": 27.8, "cost_per_task_usd": 0.58, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "GLM-5.3-Flash", "effort": null }, "livebench": { "source_model": "glm-5.3-flash", "overall_score": 65.81, "category_scores": { "Long Agentic": 19.0, "Reasoning": 77.6, "Coding": 80.6, "Browser": 59.8, "Data Analysis": 76.4, "Research": 70.1, "Design": 77.2 }, "mapping": "exact", "mapping_target": "GLM-5.3-Flash", "effort": null }, "epoch": { "source_model": "GLM-5.3-Flash", "eci": 153.64, "eci_ci_low": 151.85, "eci_ci_high": 155.52, "release_date": "2026-08-20", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5.3-Flash", "effort": null }, "matched_source_count": 3, "composite": { "score": 26.6, "source_count": 3, "percentiles": { "artificial_analysis": 24.0, "livebench": 26.1, "epoch": 29.6 }, "rank": 42, "population": 61 }, "flags": [] }, { "litellm_key": "mistral/mistral-large-4", "display": "Mistral Large 4 Preview", "source_model": "Mistral Large 4 (high)", "source_slug": "mistral-large-4", "context": 1000000, "creator": "Mistral", "intelligence_index": 26.1, "cost_per_task_usd": 2.06, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Mistral Large 4 Preview", "effort": "high", "artificial_analysis": { "source_model": "Mistral Large 4 (high)", "source_slug": "mistral-large-4", "context": 1000000, "creator": "Mistral", "intelligence_index": 26.1, "cost_per_task_usd": 2.06, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Mistral Large 4 Preview", "effort": "high" }, "livebench": { "source_model": "mistral-large-4", "overall_score": 46.21, "category_scores": { "Long Agentic": 8.8, "Reasoning": 83.9, "Coding": 60.0, "Browser": 0.6, "Data Analysis": 76.5, "Research": 28.1, "Design": 65.6 }, "mapping": "exact", "mapping_target": "Mistral Large 4 Preview", "effort": null }, "epoch": { "source_model": "Mistral Large 4", "eci": 154.66, "eci_ci_low": 151.89, "eci_ci_high": 157.31, "release_date": "2026-10-29", "organization": "Mistral AI", "mapping": "exact", "mapping_target": "Mistral Large 4 Preview", "effort": null }, "matched_source_count": 3, "composite": { "score": 16.4, "source_count": 3, "percentiles": { "artificial_analysis": 16.0, "livebench": 0.0, "epoch": 33.3 }, "rank": 51, "population": 61 }, "flags": [] }, { "litellm_key": "claude-haiku-5-5", "display": "Claude Haiku 5.5", "source_model": "Claude Haiku 5.5 (max)", "source_slug": "claude-haiku-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 36.5, "cost_per_task_usd": 0.41, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Haiku 5.5", "effort": "max", "artificial_analysis": { "source_model": "Claude Haiku 5.5 (max)", "source_slug": "claude-haiku-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 36.5, "cost_per_task_usd": 0.41, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Haiku 5.5", "effort": "max" }, "livebench": { "source_model": "claude-haiku-5.5", "overall_score": 71.63, "category_scores": { "Long Agentic": 40.0, "Reasoning": 82.4, "Coding": 91.4, "Browser": 69.5, "Data Analysis": 53.1, "Research": 81.9, "Design": 83.1 }, "mapping": "exact", "mapping_target": "Claude Haiku 5.5", "effort": null }, "epoch": { "source_model": "Claude Haiku 5.5", "eci": 160.22, "eci_ci_low": 158.04, "eci_ci_high": 162.57, "release_date": "2026-10-07", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Haiku 5.5", "effort": null }, "matched_source_count": 3, "composite": { "score": 64.9, "source_count": 3, "percentiles": { "artificial_analysis": 64.0, "livebench": 56.5, "epoch": 74.1 }, "rank": 18, "population": 61 }, "flags": [] }, { "litellm_key": "auto/meta-muse-wonder", "display": "Muse Wonder", "source_model": "Muse Wonder Full (max)", "source_slug": "muse-wonder-full", "context": 1000000, "creator": "Meta", "intelligence_index": 50.1, "cost_per_task_usd": null, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Muse Wonder", "effort": "max", "artificial_analysis": { "source_model": "Muse Wonder Full (max)", "source_slug": "muse-wonder-full", "context": 1000000, "creator": "Meta", "intelligence_index": 50.1, "cost_per_task_usd": null, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Muse Wonder", "effort": "max" }, "livebench": null, "epoch": { "source_model": "Muse Wonder", "eci": 162.02, "eci_ci_low": 159.57, "eci_ci_high": 164.58, "release_date": "2026-10-12", "organization": "Meta AI", "mapping": "exact", "mapping_target": "Muse Wonder", "effort": null }, "matched_source_count": 2, "composite": { "score": 76.9, "source_count": 2, "percentiles": { "artificial_analysis": 76.0, "epoch": 77.8 }, "rank": 13, "population": 61 }, "flags": [] }, { "litellm_key": "gemini/gemini-4-argon", "display": "Gemini 4 Argon", "source_model": "Gemini 4 Argon (high)", "source_slug": "gemini-4-argon", "context": 1000000, "creator": "Google", "intelligence_index": 50.4, "cost_per_task_usd": 9.95, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Gemini 4 Argon", "effort": "high", "artificial_analysis": { "source_model": "Gemini 4 Argon (high)", "source_slug": "gemini-4-argon", "context": 1000000, "creator": "Google", "intelligence_index": 50.4, "cost_per_task_usd": 9.95, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Gemini 4 Argon", "effort": "high" }, "livebench": { "source_model": "gemini-4-argon", "overall_score": 81.54, "category_scores": { "Long Agentic": 61.2, "Reasoning": 95.1, "Coding": 89.7, "Browser": 82.8, "Data Analysis": 85.2, "Research": 83.1, "Design": 73.7 }, "mapping": "exact", "mapping_target": "Gemini 4 Argon", "effort": null }, "epoch": { "source_model": "Gemini 4 Argon", "eci": 166.45, "eci_ci_low": 163.83, "eci_ci_high": 169.38, "release_date": "2026-09-30", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 4 Argon", "effort": null }, "matched_source_count": 3, "composite": { "score": 84.4, "source_count": 3, "percentiles": { "artificial_analysis": 80.0, "livebench": 82.6, "epoch": 90.7 }, "rank": 8, "population": 61 }, "flags": [] }, { "litellm_key": "auto/moonshotai-kimi-k3.1-pro", "display": "Kimi K3.1 Pro", "source_model": "Kimi K3.1 Pro", "source_slug": "kimi-k3-1-pro", "context": 1000000, "creator": "Kimi", "intelligence_index": 46.5, "cost_per_task_usd": 3.68, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Kimi K3.1 Pro", "effort": null, "artificial_analysis": { "source_model": "Kimi K3.1 Pro", "source_slug": "kimi-k3-1-pro", "context": 1000000, "creator": "Kimi", "intelligence_index": 46.5, "cost_per_task_usd": 3.68, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Kimi K3.1 Pro", "effort": null }, "livebench": { "source_model": "kimi-k3.1-pro", "overall_score": 74.67, "category_scores": { "Long Agentic": 39.1, "Reasoning": 91.1, "Coding": 81.8, "Browser": 75.9, "Data Analysis": 79.1, "Research": 77.9, "Design": 77.8 }, "mapping": "exact", "mapping_target": "Kimi K3.1 Pro", "effort": null }, "epoch": null, "matched_source_count": 2, "composite": { "score": 66.6, "source_count": 2, "percentiles": { "artificial_analysis": 68.0, "livebench": 65.2 }, "rank": 17, "population": 61 }, "flags": [] }, { "litellm_key": "gpt-6.1-terra", "display": "GPT-6.1 Terra", "source_model": "GPT-6.1 Terra (max)", "source_slug": "gpt-6-1-terra", "context": 1000000, "creator": "OpenAI", "intelligence_index": 51.3, "cost_per_task_usd": 0.96, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6.1 Terra", "effort": "max", "artificial_analysis": { "source_model": "GPT-6.1 Terra (max)", "source_slug": "gpt-6-1-terra", "context": 1000000, "creator": "OpenAI", "intelligence_index": 51.3, "cost_per_task_usd": 0.96, "output_tokens_per_second": null, "latency_first_chunk_seconds": null, "total_response_seconds": null, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6.1 Terra", "effort": "max" }, "livebench": { "source_model": "gpt-6.1-terra", "overall_score": 80.46, "category_scores": { "Long Agentic": 48.6, "Reasoning": 88.7, "Coding": 94.3, "Browser": 93.1, "Data Analysis": 82.3, "Research": 73.9, "Design": 82.3 }, "mapping": "exact", "mapping_target": "GPT-6.1 Terra", "effort": null }, "epoch": { "source_model": "GPT-6.1 Terra", "eci": 167.82, "eci_ci_low": 164.88, "eci_ci_high": 171.17, "release_date": "2026-10-26", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6.1 Terra", "effort": null }, "matched_source_count": 3, "composite": { "score": 84.1, "source_count": 3, "percentiles": { "artificial_analysis": 84.0, "livebench": 73.9, "epoch": 94.4 }, "rank": 9, "population": 61 }, "flags": [] } ], "unmatched": [ { "litellm_key": "manual/gpt-5-6-cyber", "display": "GPT-5.6 Cyber" }, { "litellm_key": "xai/grok-build-0.1", "display": "Grok Build 0.1" }, { "litellm_key": "dashscope/qwen-max", "display": "Qwen-Max" }, { "litellm_key": "dashscope/qwen-plus", "display": "Qwen-Plus" }, { "litellm_key": "zai/glm-5-turbo", "display": "GLM-5-Turbo" }, { "litellm_key": "manual/doubao-seed-2-0-pro", "display": "Doubao Seed 2.0 Pro" }, { "litellm_key": "manual/doubao-seed-2-0-lite", "display": "Doubao Seed 2.0 Lite" }, { "litellm_key": "manual/hunyuan-a13b", "display": "混元 A13B" }, { "litellm_key": "gpt-5.3-codex", "display": "GPT-5.3 Codex" }, { "litellm_key": "dashscope/qwen3.8-2.4t-a95b", "display": "Qwen3.8 2.4T A95B" }, { "litellm_key": "auto/upstage-solar-pro4", "display": "Solar Pro 4" } ], "alias_misses": [] }