{ "fetched_at": "2026-10-19T03:32:03+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": "2026-10-19T03:32:03+00:00", "page_sha256": "6436a639b78df70518a24d5090c7722515ecc3bdba09a79d989fc252ca1492ef", "published_rows": 268, "parse_method": "embedded-json", "archived_rows": 0 }, { "id": "livebench", "name": "LiveBench", "publisher": "LiveBench research team", "url": "https://livebench.ai/", "status": "ok", "retrieved_at": "2026-10-19T03:32:03+00:00", "data_url": "https://livebench.ai/v1/table_2026_06_25.csv", "table_created": "2026-06-25", "dataset_revision": "2026-10-15", "dataset_revised_at": "2026-10-15T06:04:18Z", "dataset_commit": "3aaf370587c1", "page_sha256": "09d810986777c92b75b40a58a1829e0318e34cb5693ecae970b3145852271ba7", "published_rows": 71, "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": "2026-10-19T03:32:03+00:00", "data_url": "https://epoch.ai/data/benchmark_data.zip", "data_file": "epoch_capabilities_index/eci_scores.csv", "dataset_revision": "2026-10-19", "page_sha256": "2f47e90bef5a2559a0acc08aa65d4d98064c04b7fa964428746fa421e8399109", "published_rows": 277, "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": { "source_model": "gpt-5.6-sol-max", "overall_score": 81.05, "category_scores": { "Reasoning": 91.65, "Coding": 83.94, "Agentic Coding": 56.21, "Mathematics": 96.2, "Data Analysis": 79.84, "Language": 87.68, "IF": 71.85 }, "mapping": "variant", "mapping_target": "GPT-5.6 Sol", "effort": "max" }, "epoch": { "source_model": "GPT-5.6 Sol", "eci": 161.73, "eci_ci_low": 159.47, "eci_ci_high": 165.04, "release_date": "2026-07-09", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.6 Sol", "effort": null }, "matched_source_count": 2, "composite": { "score": 82.6, "source_count": 2, "percentiles": { "livebench": 84.1, "epoch": 81.1 }, "rank": 11, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.6-terra", "display": "GPT-5.6 Terra", "source_model": "GPT-5.6 Terra (max)", "source_slug": "gpt-5-6-terra", "context": 1000000, "creator": "OpenAI", "intelligence_index": 42.1, "cost_per_task_usd": 1.4, "output_tokens_per_second": 142.4, "latency_first_chunk_seconds": 90.74, "total_response_seconds": 94.25, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-5.6 Terra", "effort": "max", "artificial_analysis": { "source_model": "GPT-5.6 Terra (max)", "source_slug": "gpt-5-6-terra", "context": 1000000, "creator": "OpenAI", "intelligence_index": 42.1, "cost_per_task_usd": 1.4, "output_tokens_per_second": 142.4, "latency_first_chunk_seconds": 90.74, "total_response_seconds": 94.25, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-5.6 Terra", "effort": "max" }, "livebench": { "source_model": "gpt-5.6-terra-max", "overall_score": 77.94, "category_scores": { "Reasoning": 90.63, "Coding": 78.25, "Agentic Coding": 54.95, "Mathematics": 94.91, "Data Analysis": 79.31, "Language": 82.89, "IF": 64.62 }, "mapping": "variant", "mapping_target": "GPT-5.6 Terra", "effort": "max" }, "epoch": { "source_model": "GPT-5.6 Terra", "eci": 159.43, "eci_ci_low": 156.79, "eci_ci_high": 162.18, "release_date": "2026-07-09", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.6 Terra", "effort": null }, "matched_source_count": 3, "composite": { "score": 64.3, "source_count": 3, "percentiles": { "artificial_analysis": 50.0, "livebench": 63.6, "epoch": 79.2 }, "rank": 19, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.6-luna", "display": "GPT-5.6 Luna", "artificial_analysis": null, "livebench": { "source_model": "gpt-5.6-luna-max", "overall_score": 73.56, "category_scores": { "Reasoning": 85.64, "Coding": 82.91, "Agentic Coding": 48.43, "Mathematics": 87.2, "Data Analysis": 78.03, "Language": 72.57, "IF": 60.12 }, "mapping": "variant", "mapping_target": "GPT-5.6 Luna", "effort": "max" }, "epoch": { "source_model": "GPT-5.6 Luna", "eci": 156.33, "eci_ci_low": 153.86, "eci_ci_high": 159.04, "release_date": "2026-07-09", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.6 Luna", "effort": null }, "matched_source_count": 2, "composite": { "score": 45.4, "source_count": 2, "percentiles": { "livebench": 34.1, "epoch": 56.6 }, "rank": 31, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.5", "display": "GPT-5.5", "artificial_analysis": null, "livebench": { "source_model": "gpt-5.5-xhigh", "overall_score": 80.19, "category_scores": { "Reasoning": 89.65, "Coding": 82.15, "Agentic Coding": 53.99, "Mathematics": 95.86, "Data Analysis": 81.58, "Language": 87.36, "IF": 70.73 }, "mapping": "variant", "mapping_target": "GPT-5.5", "effort": "xhigh" }, "epoch": { "source_model": "GPT-5.5", "eci": 158.95, "eci_ci_low": 156.4, "eci_ci_high": 161.92, "release_date": "2026-04-23", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.5", "effort": null }, "matched_source_count": 2, "composite": { "score": 77.7, "source_count": 2, "percentiles": { "livebench": 81.8, "epoch": 73.6 }, "rank": 13, "population": 62 }, "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": 161.97, "eci_ci_low": 158.97, "eci_ci_high": 165.09, "release_date": "2026-04-23", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.5 Pro", "effort": null }, "matched_source_count": 1, "composite": { "score": 83.0, "source_count": 1, "percentiles": { "epoch": 83.0 }, "rank": 9, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.4", "display": "GPT-5.4", "artificial_analysis": null, "livebench": { "source_model": "gpt-5.4-xhigh", "overall_score": 77.97, "category_scores": { "Reasoning": 88.12, "Coding": 77.54, "Agentic Coding": 53.84, "Mathematics": 94.15, "Data Analysis": 79.31, "Language": 82.63, "IF": 70.22 }, "mapping": "variant", "mapping_target": "GPT-5.4", "effort": "xhigh" }, "epoch": { "source_model": "GPT-5.4", "eci": 156.72, "eci_ci_low": 155.04, "eci_ci_high": 158.94, "release_date": "2026-03-05", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4", "effort": null }, "matched_source_count": 2, "composite": { "score": 63.2, "source_count": 2, "percentiles": { "livebench": 65.9, "epoch": 60.4 }, "rank": 20, "population": 62 }, "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": 159.0, "eci_ci_low": 156.48, "eci_ci_high": 161.69, "release_date": "2026-03-05", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4 Pro", "effort": null }, "matched_source_count": 1, "composite": { "score": 77.4, "source_count": 1, "percentiles": { "epoch": 77.4 }, "rank": 14, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.4-mini", "display": "GPT-5.4 mini", "artificial_analysis": null, "livebench": { "source_model": "gpt-5.4-mini-xhigh", "overall_score": 66.37, "category_scores": { "Reasoning": 71.32, "Coding": 71.62, "Agentic Coding": 41.67, "Mathematics": 78.46, "Data Analysis": 70.79, "Language": 70.95, "IF": 59.8 }, "mapping": "variant", "mapping_target": "GPT-5.4 mini", "effort": "xhigh" }, "epoch": { "source_model": "GPT-5.4 Mini", "eci": 148.77, "eci_ci_low": 147.08, "eci_ci_high": 150.5, "release_date": "2026-03-17", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4 mini", "effort": null }, "matched_source_count": 2, "composite": { "score": 9.8, "source_count": 2, "percentiles": { "livebench": 4.5, "epoch": 15.1 }, "rank": 54, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.4-nano", "display": "GPT-5.4 nano", "artificial_analysis": null, "livebench": { "source_model": "gpt-5.4-nano-xhigh", "overall_score": 69.58, "category_scores": { "Reasoning": 81.1, "Coding": 70.84, "Agentic Coding": 46.77, "Mathematics": 90.98, "Data Analysis": 67.64, "Language": 62.51, "IF": 67.2 }, "mapping": "variant", "mapping_target": "GPT-5.4 nano", "effort": "xhigh" }, "epoch": { "source_model": "GPT-5.4 Nano", "eci": 146.12, "eci_ci_low": 143.63, "eci_ci_high": 148.51, "release_date": "2026-03-17", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.4 nano", "effort": null }, "matched_source_count": 2, "composite": { "score": 10.6, "source_count": 2, "percentiles": { "livebench": 13.6, "epoch": 7.5 }, "rank": 53, "population": 62 }, "flags": [] }, { "litellm_key": "claude-opus-5", "display": "Claude Opus 5", "artificial_analysis": null, "livebench": { "source_model": "claude-opus-5-max-effort", "overall_score": 80.09, "category_scores": { "Reasoning": 91.21, "Coding": 81.45, "Agentic Coding": 65.2, "Mathematics": 95.73, "Data Analysis": 74.55, "Language": 88.69, "IF": 63.77 }, "mapping": "variant", "mapping_target": "Claude Opus 5", "effort": "max" }, "epoch": { "source_model": "Claude Opus 5", "eci": 162.6, "eci_ci_low": 160.0, "eci_ci_high": 165.75, "release_date": "2026-07-24", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Opus 5", "effort": null }, "matched_source_count": 2, "composite": { "score": 84.1, "source_count": 2, "percentiles": { "livebench": 79.5, "epoch": 88.7 }, "rank": 8, "population": 62 }, "flags": [] }, { "litellm_key": "claude-fable-5", "display": "Claude Fable 5", "artificial_analysis": null, "livebench": { "source_model": "claude-fable-5-max-effort", "overall_score": 82.97, "category_scores": { "Reasoning": 89.65, "Coding": 85.99, "Agentic Coding": 62.17, "Mathematics": 95.99, "Data Analysis": 80.54, "Language": 90.68, "IF": 75.77 }, "mapping": "variant", "mapping_target": "Claude Fable 5", "effort": "max" }, "epoch": { "source_model": "Claude Fable 5", "eci": 162.13, "eci_ci_low": 159.53, "eci_ci_high": 166.32, "release_date": "2026-06-09", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Fable 5", "effort": null }, "matched_source_count": 2, "composite": { "score": 90.2, "source_count": 2, "percentiles": { "livebench": 95.5, "epoch": 84.9 }, "rank": 5, "population": 62 }, "flags": [] }, { "litellm_key": "claude-sonnet-5", "display": "Claude Sonnet 5", "artificial_analysis": null, "livebench": { "source_model": "claude-sonnet-5-xhigh-effort", "overall_score": 76.04, "category_scores": { "Reasoning": 88.69, "Coding": 80.68, "Agentic Coding": 59.39, "Mathematics": 92.94, "Data Analysis": 71.74, "Language": 74.97, "IF": 63.86 }, "mapping": "variant", "mapping_target": "Claude Sonnet 5", "effort": "xhigh" }, "epoch": { "source_model": "Claude Sonnet 5", "eci": 156.36, "eci_ci_low": 153.97, "eci_ci_high": 158.94, "release_date": "2026-06-30", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Sonnet 5", "effort": null }, "matched_source_count": 2, "composite": { "score": 53.1, "source_count": 2, "percentiles": { "livebench": 47.7, "epoch": 58.5 }, "rank": 28, "population": 62 }, "flags": [] }, { "litellm_key": "claude-opus-4-8", "display": "Claude Opus 4.8", "artificial_analysis": null, "livebench": { "source_model": "claude-opus-4-8-max-effort", "overall_score": 76.22, "category_scores": { "Reasoning": 89.19, "Coding": 81.83, "Agentic Coding": 50.5, "Mathematics": 94.32, "Data Analysis": 66.03, "Language": 79.66, "IF": 72.03 }, "mapping": "variant", "mapping_target": "Claude Opus 4.8", "effort": "max" }, "epoch": { "source_model": "Claude Opus 4.8", "eci": 158.26, "eci_ci_low": 156.24, "eci_ci_high": 160.79, "release_date": "2026-05-28", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Opus 4.8", "effort": null }, "matched_source_count": 2, "composite": { "score": 62.0, "source_count": 2, "percentiles": { "livebench": 52.3, "epoch": 71.7 }, "rank": 21, "population": 62 }, "flags": [] }, { "litellm_key": "claude-sonnet-4-6", "display": "Claude Sonnet 4.6", "artificial_analysis": null, "livebench": { "source_model": "claude-sonnet-4-6-thinking-auto-medium-effort", "overall_score": 72.99, "category_scores": { "Reasoning": 84.77, "Coding": 79.27, "Agentic Coding": 42.63, "Mathematics": 86.99, "Data Analysis": 77.95, "Language": 76.1, "IF": 63.22 }, "mapping": "variant", "mapping_target": "Claude Sonnet 4.6", "effort": "medium" }, "epoch": { "source_model": "Claude Sonnet 4.6", "eci": 152.39, "eci_ci_low": 150.04, "eci_ci_high": 154.65, "release_date": "2026-02-17", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Sonnet 4.6", "effort": null }, "matched_source_count": 2, "composite": { "score": 28.8, "source_count": 2, "percentiles": { "livebench": 27.3, "epoch": 30.2 }, "rank": 44, "population": 62 }, "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": 142.4, "eci_ci_low": 139.33, "eci_ci_high": 144.11, "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": 62, "population": 62 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.7-flash", "display": "Gemini 3.7 Flash", "artificial_analysis": null, "livebench": { "source_model": "gemini-3.7-flash-high", "overall_score": 78.83, "category_scores": { "Reasoning": 87.8, "Coding": 78.89, "Agentic Coding": 58.28, "Mathematics": 93.47, "Data Analysis": 67.96, "Language": 85.45, "IF": 79.93 }, "mapping": "variant", "mapping_target": "Gemini 3.7 Flash", "effort": "high" }, "epoch": { "source_model": "Gemini 3.7 Flash", "eci": 157.22, "eci_ci_low": 155.33, "eci_ci_high": 159.68, "release_date": "2026-08-13", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.7 Flash", "effort": null }, "matched_source_count": 2, "composite": { "score": 70.3, "source_count": 2, "percentiles": { "livebench": 72.7, "epoch": 67.9 }, "rank": 16, "population": 62 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.6-flash", "display": "Gemini 3.6 Flash", "artificial_analysis": null, "livebench": { "source_model": "gemini-3.6-flash-high", "overall_score": 73.59, "category_scores": { "Reasoning": 85.15, "Coding": 77.86, "Agentic Coding": 43.43, "Mathematics": 86.4, "Data Analysis": 63.0, "Language": 83.9, "IF": 75.37 }, "mapping": "variant", "mapping_target": "Gemini 3.6 Flash", "effort": "high" }, "epoch": { "source_model": "Gemini 3.6 Flash", "eci": 154.24, "eci_ci_low": 152.74, "eci_ci_high": 156.1, "release_date": "2026-07-21", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.6 Flash", "effort": null }, "matched_source_count": 2, "composite": { "score": 37.0, "source_count": 2, "percentiles": { "livebench": 36.4, "epoch": 37.7 }, "rank": 38, "population": 62 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.5-flash", "display": "Gemini 3.5 Flash", "artificial_analysis": null, "livebench": { "source_model": "gemini-3.5-flash-high", "overall_score": 74.64, "category_scores": { "Reasoning": 82.0, "Coding": 78.18, "Agentic Coding": 48.99, "Mathematics": 88.24, "Data Analysis": 64.86, "Language": 84.58, "IF": 75.6 }, "mapping": "variant", "mapping_target": "Gemini 3.5 Flash", "effort": "high" }, "epoch": { "source_model": "Gemini 3.5 Flash", "eci": 154.38, "eci_ci_low": 152.41, "eci_ci_high": 156.5, "release_date": "2026-05-19", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.5 Flash", "effort": null }, "matched_source_count": 2, "composite": { "score": 40.0, "source_count": 2, "percentiles": { "livebench": 38.6, "epoch": 41.5 }, "rank": 33, "population": 62 }, "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": 22.2, "cost_per_task_usd": 0.19, "output_tokens_per_second": 456.0, "latency_first_chunk_seconds": 7.41, "total_response_seconds": 8.51, "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": 22.2, "cost_per_task_usd": 0.19, "output_tokens_per_second": 456.0, "latency_first_chunk_seconds": 7.41, "total_response_seconds": 8.51, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Gemini 3.5 Flash-Lite", "effort": null }, "livebench": { "source_model": "gemini-3.5-flash-lite-high", "overall_score": 63.94, "category_scores": { "Reasoning": 60.19, "Coding": 76.07, "Agentic Coding": 45.25, "Mathematics": 73.74, "Data Analysis": 53.25, "Language": 71.82, "IF": 67.24 }, "mapping": "variant", "mapping_target": "Gemini 3.5 Flash-Lite", "effort": "high" }, "epoch": { "source_model": "Gemini 3.5 Flash-Lite", "eci": 145.15, "eci_ci_low": 142.7, "eci_ci_high": 146.66, "release_date": "2026-07-21", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.5 Flash-Lite", "effort": null }, "matched_source_count": 3, "composite": { "score": 2.0, "source_count": 3, "percentiles": { "artificial_analysis": 0.0, "livebench": 2.3, "epoch": 3.8 }, "rank": 60, "population": 62 }, "flags": [] }, { "litellm_key": "gemini/gemini-3.1-pro-preview", "display": "Gemini 3.1 Pro", "source_model": "Gemini 3.1 Pro Preview", "source_slug": "gemini-3-1-pro-preview", "context": 1000000, "creator": "Google", "intelligence_index": 29.7, "cost_per_task_usd": 1.3, "output_tokens_per_second": 151.5, "latency_first_chunk_seconds": 19.51, "total_response_seconds": 22.81, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Gemini 3.1 Pro", "effort": null, "artificial_analysis": { "source_model": "Gemini 3.1 Pro Preview", "source_slug": "gemini-3-1-pro-preview", "context": 1000000, "creator": "Google", "intelligence_index": 29.7, "cost_per_task_usd": 1.3, "output_tokens_per_second": 151.5, "latency_first_chunk_seconds": 19.51, "total_response_seconds": 22.81, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Gemini 3.1 Pro", "effort": null }, "livebench": { "source_model": "gemini-3.1-pro-preview-high", "overall_score": 76.95, "category_scores": { "Reasoning": 84.0, "Coding": 76.45, "Agentic Coding": 44.14, "Mathematics": 91.05, "Data Analysis": 78.54, "Language": 85.38, "IF": 79.1 }, "mapping": "variant", "mapping_target": "Gemini 3.1 Pro", "effort": "high" }, "epoch": { "source_model": "Gemini 3.1 Pro", "eci": 154.67, "eci_ci_low": 152.48, "eci_ci_high": 157.11, "release_date": "2026-02-19", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.1 Pro", "effort": null }, "matched_source_count": 3, "composite": { "score": 37.1, "source_count": 3, "percentiles": { "artificial_analysis": 13.3, "livebench": 54.5, "epoch": 43.4 }, "rank": 37, "population": 62 }, "flags": [ { "type": "source_divergence", "spread": 41.2, "percentiles": { "artificial_analysis": 13.3, "livebench": 54.5, "epoch": 43.4 } } ] }, { "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": 144.47, "eci_ci_low": 142.28, "eci_ci_high": 146.04, "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": 61, "population": 62 }, "flags": [] }, { "litellm_key": "gemini/gemini-3-flash-preview", "display": "Gemini 3 Flash", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Gemini 3 Flash", "eci": 151.8, "eci_ci_low": 150.54, "eci_ci_high": 153.39, "release_date": "2025-12-17", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3 Flash", "effort": null }, "matched_source_count": 1, "composite": { "score": 24.5, "source_count": 1, "percentiles": { "epoch": 24.5 }, "rank": 47, "population": 62 }, "flags": [] }, { "litellm_key": "xai/grok-4.6", "display": "Grok 4.6", "artificial_analysis": null, "livebench": { "source_model": "grok-4.6", "overall_score": 78.04, "category_scores": { "Reasoning": 90.51, "Coding": 76.78, "Agentic Coding": 57.02, "Mathematics": 92.57, "Data Analysis": 73.86, "Language": 83.7, "IF": 71.87 }, "mapping": "exact", "mapping_target": "Grok 4.6", "effort": null }, "epoch": { "source_model": "Grok 4.6", "eci": 156.31, "eci_ci_low": 154.54, "eci_ci_high": 158.67, "release_date": "2026-08-12", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.6", "effort": null }, "matched_source_count": 2, "composite": { "score": 61.0, "source_count": 2, "percentiles": { "livebench": 68.2, "epoch": 53.8 }, "rank": 22, "population": 62 }, "flags": [] }, { "litellm_key": "xai/grok-4.5", "display": "Grok 4.5", "artificial_analysis": null, "livebench": { "source_model": "grok-4.5", "overall_score": 75.77, "category_scores": { "Reasoning": 87.17, "Coding": 68.59, "Agentic Coding": 56.46, "Mathematics": 90.82, "Data Analysis": 73.04, "Language": 82.8, "IF": 71.53 }, "mapping": "exact", "mapping_target": "Grok 4.5", "effort": null }, "epoch": { "source_model": "Grok 4.5", "eci": 153.93, "eci_ci_low": 152.47, "eci_ci_high": 155.89, "release_date": "2026-07-08", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.5", "effort": null }, "matched_source_count": 2, "composite": { "score": 39.5, "source_count": 2, "percentiles": { "livebench": 43.2, "epoch": 35.8 }, "rank": 36, "population": 62 }, "flags": [] }, { "litellm_key": "xai/grok-build-0.1", "display": "Grok Build 0.1", "artificial_analysis": null, "livebench": { "source_model": "grok-build-0.1", "overall_score": 67.78, "category_scores": { "Reasoning": 76.37, "Coding": 65.39, "Agentic Coding": 45.81, "Mathematics": 78.43, "Data Analysis": 70.79, "Language": 72.46, "IF": 65.22 }, "mapping": "exact", "mapping_target": "Grok Build 0.1", "effort": null }, "epoch": null, "matched_source_count": 1, "composite": { "score": 9.1, "source_count": 1, "percentiles": { "livebench": 9.1 }, "rank": 56, "population": 62 }, "flags": [] }, { "litellm_key": "xai/grok-4.3", "display": "Grok 4.3", "artificial_analysis": null, "livebench": { "source_model": "grok-4.3", "overall_score": 62.25, "category_scores": { "Reasoning": 70.82, "Coding": 69.93, "Agentic Coding": 18.54, "Mathematics": 84.34, "Data Analysis": 55.77, "Language": 73.58, "IF": 62.75 }, "mapping": "exact", "mapping_target": "Grok 4.3", "effort": null }, "epoch": { "source_model": "Grok 4.3 Beta", "eci": 148.95, "eci_ci_low": 147.27, "eci_ci_high": 150.34, "release_date": "2026-04-17", "organization": "xAI", "mapping": "variant", "mapping_target": "Grok 4.3", "effort": null }, "matched_source_count": 2, "composite": { "score": 8.5, "source_count": 2, "percentiles": { "livebench": 0.0, "epoch": 17.0 }, "rank": 57, "population": 62 }, "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": 36.0, "cost_per_task_usd": 0.67, "output_tokens_per_second": 109.5, "latency_first_chunk_seconds": 1.64, "total_response_seconds": 24.46, "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": 36.0, "cost_per_task_usd": 0.67, "output_tokens_per_second": 109.5, "latency_first_chunk_seconds": 1.64, "total_response_seconds": 24.46, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "DeepSeek V4 Pro", "effort": "max" }, "livebench": { "source_model": "deepseek-v4-pro-0813", "overall_score": 77.44, "category_scores": { "Reasoning": 85.84, "Coding": 77.16, "Agentic Coding": 54.95, "Mathematics": 95.09, "Data Analysis": 79.24, "Language": 82.07, "IF": 67.7 }, "mapping": "variant", "mapping_target": "DeepSeek V4 Pro", "effort": null }, "epoch": { "source_model": "DeepSeek V4 Pro 0813", "eci": 155.29, "eci_ci_low": 153.53, "eci_ci_high": 157.63, "release_date": "2026-08-13", "organization": "DeepSeek", "mapping": "variant", "mapping_target": "DeepSeek V4 Pro", "effort": null }, "matched_source_count": 3, "composite": { "score": 43.2, "source_count": 3, "percentiles": { "artificial_analysis": 23.3, "livebench": 59.1, "epoch": 47.2 }, "rank": 32, "population": 62 }, "flags": [ { "type": "source_divergence", "spread": 35.8, "percentiles": { "artificial_analysis": 23.3, "livebench": 59.1, "epoch": 47.2 } } ] }, { "litellm_key": "deepseek-v4-flash", "display": "DeepSeek V4.1 Flash", "source_model": "DeepSeek V4.1 Flash (max)", "source_slug": "deepseek-v4-1-flash", "context": 1000000, "creator": "DeepSeek", "intelligence_index": 39.5, "cost_per_task_usd": 0.49, "output_tokens_per_second": 232.3, "latency_first_chunk_seconds": 0.91, "total_response_seconds": 11.67, "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 (max)", "source_slug": "deepseek-v4-1-flash", "context": 1000000, "creator": "DeepSeek", "intelligence_index": 39.5, "cost_per_task_usd": 0.49, "output_tokens_per_second": 232.3, "latency_first_chunk_seconds": 0.91, "total_response_seconds": 11.67, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "DeepSeek V4.1 Flash", "effort": "max" }, "livebench": { "source_model": "deepseek-v4.1-flash-max", "overall_score": 81.11, "category_scores": { "Reasoning": 86.69, "Coding": 80.04, "Agentic Coding": 77.27, "Mathematics": 93.29, "Data Analysis": 79.25, "Language": 81.19, "IF": 70.03 }, "mapping": "variant", "mapping_target": "DeepSeek V4.1 Flash", "effort": "max" }, "epoch": { "source_model": "DeepSeek V4.1 Flash", "eci": 155.57, "eci_ci_low": 153.51, "eci_ci_high": 157.55, "release_date": "2026-09-09", "organization": "DeepSeek", "mapping": "exact", "mapping_target": "DeepSeek V4.1 Flash", "effort": null }, "matched_source_count": 3, "composite": { "score": 57.4, "source_count": 3, "percentiles": { "artificial_analysis": 36.7, "livebench": 86.4, "epoch": 49.1 }, "rank": 25, "population": 62 }, "flags": [ { "type": "source_divergence", "spread": 49.7, "percentiles": { "artificial_analysis": 36.7, "livebench": 86.4, "epoch": 49.1 } } ] }, { "litellm_key": "dashscope/qwen3.7-max", "display": "Qwen3.7-Max", "artificial_analysis": null, "livebench": { "source_model": "qwen3.7-max", "overall_score": 73.14, "category_scores": { "Reasoning": 83.34, "Coding": 74.22, "Agentic Coding": 43.59, "Mathematics": 85.25, "Data Analysis": 71.79, "Language": 79.74, "IF": 74.04 }, "mapping": "exact", "mapping_target": "Qwen3.7-Max", "effort": null }, "epoch": { "source_model": "Qwen3.7-Max", "eci": 153.83, "eci_ci_low": 151.98, "eci_ci_high": 156.24, "release_date": "2026-05-19", "organization": "Alibaba", "mapping": "exact", "mapping_target": "Qwen3.7-Max", "effort": null }, "matched_source_count": 2, "composite": { "score": 31.8, "source_count": 2, "percentiles": { "livebench": 29.5, "epoch": 34.0 }, "rank": 41, "population": 62 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k3", "display": "Kimi K3", "source_model": "Kimi K3 (max)", "source_slug": "kimi-k3", "context": 1048576, "creator": "Kimi", "intelligence_index": 43.6, "cost_per_task_usd": 2.0, "output_tokens_per_second": 43.7, "latency_first_chunk_seconds": 3.53, "total_response_seconds": 60.7, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Kimi K3", "effort": "max", "artificial_analysis": { "source_model": "Kimi K3 (max)", "source_slug": "kimi-k3", "context": 1048576, "creator": "Kimi", "intelligence_index": 43.6, "cost_per_task_usd": 2.0, "output_tokens_per_second": 43.7, "latency_first_chunk_seconds": 3.53, "total_response_seconds": 60.7, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Kimi K3", "effort": "max" }, "livebench": { "source_model": "kimi-k3", "overall_score": 79.19, "category_scores": { "Reasoning": 90.67, "Coding": 81.45, "Agentic Coding": 62.17, "Mathematics": 84.44, "Data Analysis": 78.73, "Language": 85.53, "IF": 71.36 }, "mapping": "exact", "mapping_target": "Kimi K3", "effort": null }, "epoch": { "source_model": "Kimi K3", "eci": 157.42, "eci_ci_low": 155.1, "eci_ci_high": 160.11, "release_date": "2026-07-16", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K3", "effort": null }, "matched_source_count": 3, "composite": { "score": 67.2, "source_count": 3, "percentiles": { "artificial_analysis": 56.7, "livebench": 75.0, "epoch": 69.8 }, "rank": 18, "population": 62 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k2.7-code", "display": "Kimi K2.7 Code", "source_model": "Kimi K2.7 Code", "source_slug": "kimi-k2-7-code", "context": 256000, "creator": "Kimi", "intelligence_index": 25.8, "cost_per_task_usd": 0.54, "output_tokens_per_second": 57.2, "latency_first_chunk_seconds": 2.86, "total_response_seconds": 50.6, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Kimi K2.7 Code", "effort": null, "artificial_analysis": { "source_model": "Kimi K2.7 Code", "source_slug": "kimi-k2-7-code", "context": 256000, "creator": "Kimi", "intelligence_index": 25.8, "cost_per_task_usd": 0.54, "output_tokens_per_second": 57.2, "latency_first_chunk_seconds": 2.86, "total_response_seconds": 50.6, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Kimi K2.7 Code", "effort": null }, "livebench": { "source_model": "kimi-k2.7-code", "overall_score": 68.41, "category_scores": { "Reasoning": 82.81, "Coding": 73.96, "Agentic Coding": 45.66, "Mathematics": 79.6, "Data Analysis": 62.66, "Language": 77.91, "IF": 56.29 }, "mapping": "exact", "mapping_target": "Kimi K2.7 Code", "effort": null }, "epoch": { "source_model": "Kimi K2.7 Code", "eci": 149.87, "eci_ci_low": 147.94, "eci_ci_high": 151.71, "release_date": "2026-06-12", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K2.7 Code", "effort": null }, "matched_source_count": 3, "composite": { "score": 11.2, "source_count": 3, "percentiles": { "artificial_analysis": 3.3, "livebench": 11.4, "epoch": 18.9 }, "rank": 52, "population": 62 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k2.6", "display": "Kimi K2.6", "artificial_analysis": null, "livebench": { "source_model": "kimi-k2.6-thinking", "overall_score": 70.54, "category_scores": { "Reasoning": 79.38, "Coding": 78.57, "Agentic Coding": 46.92, "Mathematics": 84.28, "Data Analysis": 65.13, "Language": 75.14, "IF": 64.36 }, "mapping": "variant", "mapping_target": "Kimi K2.6", "effort": "reasoning" }, "epoch": { "source_model": "Kimi K2.6", "eci": 150.92, "eci_ci_low": 149.12, "eci_ci_high": 152.75, "release_date": "2026-04-20", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K2.6", "effort": null }, "matched_source_count": 2, "composite": { "score": 19.2, "source_count": 2, "percentiles": { "livebench": 15.9, "epoch": 22.6 }, "rank": 50, "population": 62 }, "flags": [] }, { "litellm_key": "moonshot/kimi-k2.5", "display": "Kimi K2.5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Kimi K2.5", "eci": 147.98, "eci_ci_low": 146.36, "eci_ci_high": 149.3, "release_date": "2026-01-27", "organization": "Moonshot", "mapping": "exact", "mapping_target": "Kimi K2.5", "effort": null }, "matched_source_count": 1, "composite": { "score": 13.2, "source_count": 1, "percentiles": { "epoch": 13.2 }, "rank": 51, "population": 62 }, "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": 44.8, "cost_per_task_usd": 2.01, "output_tokens_per_second": 95.0, "latency_first_chunk_seconds": 2.46, "total_response_seconds": 28.77, "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": 44.8, "cost_per_task_usd": 2.01, "output_tokens_per_second": 95.0, "latency_first_chunk_seconds": 2.46, "total_response_seconds": 28.77, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GLM-5.3", "effort": "max" }, "livebench": { "source_model": "glm-5.3", "overall_score": 76.14, "category_scores": { "Reasoning": 85.8, "Coding": 78.95, "Agentic Coding": 60.91, "Mathematics": 87.9, "Data Analysis": 70.24, "Language": 79.86, "IF": 69.3 }, "mapping": "exact", "mapping_target": "GLM-5.3", "effort": null }, "epoch": { "source_model": "GLM-5.3", "eci": 155.91, "eci_ci_low": 154.04, "eci_ci_high": 158.39, "release_date": "2026-08-14", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5.3", "effort": null }, "matched_source_count": 3, "composite": { "score": 54.7, "source_count": 3, "percentiles": { "artificial_analysis": 63.3, "livebench": 50.0, "epoch": 50.9 }, "rank": 27, "population": 62 }, "flags": [] }, { "litellm_key": "zai/glm-5.2", "display": "GLM-5.2", "artificial_analysis": null, "livebench": { "source_model": "glm-5.2", "overall_score": 73.16, "category_scores": { "Reasoning": 78.62, "Coding": 79.65, "Agentic Coding": 51.77, "Mathematics": 89.78, "Data Analysis": 73.74, "Language": 76.24, "IF": 62.29 }, "mapping": "exact", "mapping_target": "GLM-5.2", "effort": null }, "epoch": { "source_model": "GLM-5.2", "eci": 151.86, "eci_ci_low": 150.07, "eci_ci_high": 154.0, "release_date": "2026-06-16", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5.2", "effort": null }, "matched_source_count": 2, "composite": { "score": 29.1, "source_count": 2, "percentiles": { "livebench": 31.8, "epoch": 26.4 }, "rank": 43, "population": 62 }, "flags": [] }, { "litellm_key": "zai/glm-5.1", "display": "GLM-5.1", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GLM-5.1", "eci": 149.99, "eci_ci_low": 148.05, "eci_ci_high": 151.77, "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": 20.8, "source_count": 1, "percentiles": { "epoch": 20.8 }, "rank": 49, "population": 62 }, "flags": [] }, { "litellm_key": "zai/glm-5", "display": "GLM-5", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "GLM-5", "eci": 145.78, "eci_ci_low": 143.79, "eci_ci_high": 147.65, "release_date": "2026-02-11", "organization": "Z.ai (Zhipu AI)", "mapping": "exact", "mapping_target": "GLM-5", "effort": null }, "matched_source_count": 1, "composite": { "score": 5.7, "source_count": 1, "percentiles": { "epoch": 5.7 }, "rank": 59, "population": 62 }, "flags": [] }, { "litellm_key": "minimax/MiniMax-M3", "display": "MiniMax M3", "source_model": "MiniMax-M3", "source_slug": "minimax-m3", "context": 1000000, "creator": "MiniMax", "intelligence_index": 29.2, "cost_per_task_usd": 0.51, "output_tokens_per_second": 122.7, "latency_first_chunk_seconds": 0.99, "total_response_seconds": 21.37, "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": 29.2, "cost_per_task_usd": 0.51, "output_tokens_per_second": 122.7, "latency_first_chunk_seconds": 0.99, "total_response_seconds": 21.37, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiniMax M3", "effort": null }, "livebench": { "source_model": "minimax-m3", "overall_score": 67.26, "category_scores": { "Reasoning": 74.48, "Coding": 68.2, "Agentic Coding": 40.66, "Mathematics": 76.95, "Data Analysis": 76.17, "Language": 76.84, "IF": 57.51 }, "mapping": "exact", "mapping_target": "MiniMax M3", "effort": null }, "epoch": { "source_model": "MiniMax-M3", "eci": 147.13, "eci_ci_low": 142.79, "eci_ci_high": 150.0, "release_date": "2026-06-01", "organization": "MiniMax", "mapping": "exact", "mapping_target": "MiniMax M3", "effort": null }, "matched_source_count": 3, "composite": { "score": 9.4, "source_count": 3, "percentiles": { "artificial_analysis": 10.0, "livebench": 6.8, "epoch": 11.3 }, "rank": 55, "population": 62 }, "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": 52.7, "cost_per_task_usd": 3.26, "output_tokens_per_second": 70.4, "latency_first_chunk_seconds": 249.75, "total_response_seconds": 256.85, "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": 52.7, "cost_per_task_usd": 3.26, "output_tokens_per_second": 70.4, "latency_first_chunk_seconds": 249.75, "total_response_seconds": 256.85, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6 Astra", "effort": "max" }, "livebench": { "source_model": "gpt-6-astra-max", "overall_score": 82.16, "category_scores": { "Reasoning": 92.65, "Coding": 80.36, "Agentic Coding": 57.32, "Mathematics": 96.81, "Data Analysis": 82.97, "Language": 89.43, "IF": 75.58 }, "mapping": "variant", "mapping_target": "GPT-6 Astra", "effort": "max" }, "epoch": { "source_model": "GPT-6 Astra", "eci": 166.41, "eci_ci_low": 163.35, "eci_ci_high": 171.23, "release_date": "2026-09-03", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6 Astra", "effort": null }, "matched_source_count": 3, "composite": { "score": 92.7, "source_count": 3, "percentiles": { "artificial_analysis": 86.7, "livebench": 93.2, "epoch": 98.1 }, "rank": 4, "population": 62 }, "flags": [] }, { "litellm_key": "claude-fable-5-1", "display": "Claude Fable 5.1", "source_model": "Claude Fable 5.1 (max with fallback)", "source_slug": "claude-fable-5-1", "context": 1000000, "creator": "Anthropic", "intelligence_index": 53.4, "cost_per_task_usd": 7.63, "output_tokens_per_second": 68.9, "latency_first_chunk_seconds": 126.65, "total_response_seconds": 133.91, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Fable 5.1", "effort": "max", "artificial_analysis": { "source_model": "Claude Fable 5.1 (max with fallback)", "source_slug": "claude-fable-5-1", "context": 1000000, "creator": "Anthropic", "intelligence_index": 53.4, "cost_per_task_usd": 7.63, "output_tokens_per_second": 68.9, "latency_first_chunk_seconds": 126.65, "total_response_seconds": 133.91, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Fable 5.1", "effort": "max" }, "livebench": { "source_model": "claude-fable-5-1-max-effort", "overall_score": 83.42, "category_scores": { "Reasoning": 91.69, "Coding": 86.38, "Agentic Coding": 66.06, "Mathematics": 97.01, "Data Analysis": 80.28, "Language": 89.5, "IF": 72.99 }, "mapping": "variant", "mapping_target": "Claude Fable 5.1", "effort": "max" }, "epoch": { "source_model": "Claude Fable 5.1", "eci": 164.65, "eci_ci_low": 161.92, "eci_ci_high": 168.48, "release_date": "2026-09-01", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Fable 5.1", "effort": null }, "matched_source_count": 3, "composite": { "score": 94.8, "source_count": 3, "percentiles": { "artificial_analysis": 90.0, "livebench": 100.0, "epoch": 94.3 }, "rank": 2, "population": 62 }, "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": 40.9, "cost_per_task_usd": 1.24, "output_tokens_per_second": 160.8, "latency_first_chunk_seconds": 23.18, "total_response_seconds": 26.29, "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": 40.9, "cost_per_task_usd": 1.24, "output_tokens_per_second": 160.8, "latency_first_chunk_seconds": 23.18, "total_response_seconds": 26.29, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Gemini 3.8 Flash", "effort": "high" }, "livebench": { "source_model": "gemini-3.8-flash-high", "overall_score": 75.83, "category_scores": { "Reasoning": 89.29, "Coding": 72.49, "Agentic Coding": 54.24, "Mathematics": 91.56, "Data Analysis": 54.01, "Language": 87.79, "IF": 81.41 }, "mapping": "variant", "mapping_target": "Gemini 3.8 Flash", "effort": "high" }, "epoch": { "source_model": "Gemini 3.8 Flash", "eci": 157.2, "eci_ci_low": 154.97, "eci_ci_high": 160.45, "release_date": "2026-09-02", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 3.8 Flash", "effort": null }, "matched_source_count": 3, "composite": { "score": 51.6, "source_count": 3, "percentiles": { "artificial_analysis": 43.3, "livebench": 45.5, "epoch": 66.0 }, "rank": 29, "population": 62 }, "flags": [] }, { "litellm_key": "xai/grok-4.20", "display": "Grok 4.20", "artificial_analysis": null, "livebench": null, "epoch": { "source_model": "Grok 4.20", "eci": 152.08, "eci_ci_low": 149.51, "eci_ci_high": 154.2, "release_date": "2026-02-17", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.20", "effort": null }, "matched_source_count": 1, "composite": { "score": 28.3, "source_count": 1, "percentiles": { "epoch": 28.3 }, "rank": 45, "population": 62 }, "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": 45.4, "cost_per_task_usd": 5.41, "output_tokens_per_second": 37.6, "latency_first_chunk_seconds": 3.09, "total_response_seconds": 69.64, "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": 45.4, "cost_per_task_usd": 5.41, "output_tokens_per_second": 37.6, "latency_first_chunk_seconds": 3.09, "total_response_seconds": 69.64, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Qwen3.8-Max", "effort": null }, "livebench": { "source_model": "qwen3.8-max", "overall_score": 78.46, "category_scores": { "Reasoning": 88.21, "Coding": 72.87, "Agentic Coding": 64.65, "Mathematics": 91.31, "Data Analysis": 78.41, "Language": 79.69, "IF": 74.08 }, "mapping": "exact", "mapping_target": "Qwen3.8-Max", "effort": null }, "epoch": { "source_model": "Qwen3.8 Max (0902)", "eci": 154.91, "eci_ci_low": 153.11, "eci_ci_high": 156.7, "release_date": "2026-09-01", "organization": "Alibaba", "mapping": "variant", "mapping_target": "Qwen3.8-Max", "effort": null }, "matched_source_count": 3, "composite": { "score": 60.8, "source_count": 3, "percentiles": { "artificial_analysis": 66.7, "livebench": 70.5, "epoch": 45.3 }, "rank": 23, "population": 62 }, "flags": [] }, { "litellm_key": "meta/muse-spark-1.3", "display": "Muse Spark 1.3", "source_model": "Muse Spark 1.3 (max)", "source_slug": "muse-spark-1-3", "context": 1000000, "creator": "Meta", "intelligence_index": 48.1, "cost_per_task_usd": 1.6, "output_tokens_per_second": 145.6, "latency_first_chunk_seconds": 53.64, "total_response_seconds": 70.81, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Muse Spark 1.3", "effort": "max", "artificial_analysis": { "source_model": "Muse Spark 1.3 (max)", "source_slug": "muse-spark-1-3", "context": 1000000, "creator": "Meta", "intelligence_index": 48.1, "cost_per_task_usd": 1.6, "output_tokens_per_second": 145.6, "latency_first_chunk_seconds": 53.64, "total_response_seconds": 70.81, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Muse Spark 1.3", "effort": "max" }, "livebench": { "source_model": "muse-spark-1.3-xhigh", "overall_score": 81.59, "category_scores": { "Reasoning": 89.65, "Coding": 81.06, "Agentic Coding": 64.09, "Mathematics": 95.95, "Data Analysis": 79.57, "Language": 82.79, "IF": 78.0 }, "mapping": "variant", "mapping_target": "Muse Spark 1.3", "effort": "xhigh" }, "epoch": { "source_model": "Muse Spark 1.3", "eci": 156.76, "eci_ci_low": 154.89, "eci_ci_high": 158.88, "release_date": "2026-09-02", "organization": "Meta AI", "mapping": "exact", "mapping_target": "Muse Spark 1.3", "effort": null }, "matched_source_count": 3, "composite": { "score": 76.2, "source_count": 3, "percentiles": { "artificial_analysis": 76.7, "livebench": 88.6, "epoch": 63.2 }, "rank": 15, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-5.3-codex", "display": "GPT-5.3 Codex", "source_model": "GPT-5.3 Codex (xhigh)", "source_slug": "gpt-5-3-codex", "context": 400000, "creator": "OpenAI", "intelligence_index": 32.5, "cost_per_task_usd": null, "output_tokens_per_second": 124.0, "latency_first_chunk_seconds": 48.09, "total_response_seconds": 52.12, "is_reasoning": true, "estimated": true, "archived": false, "mapping": "variant", "mapping_target": "GPT-5.3 Codex", "effort": "xhigh", "artificial_analysis": { "source_model": "GPT-5.3 Codex (xhigh)", "source_slug": "gpt-5-3-codex", "context": 400000, "creator": "OpenAI", "intelligence_index": 32.5, "cost_per_task_usd": null, "output_tokens_per_second": 124.0, "latency_first_chunk_seconds": 48.09, "total_response_seconds": 52.12, "is_reasoning": true, "estimated": true, "archived": false, "mapping": "variant", "mapping_target": "GPT-5.3 Codex", "effort": "xhigh" }, "livebench": null, "epoch": { "source_model": "GPT-5.3 Codex", "eci": 156.76, "eci_ci_low": 152.86, "eci_ci_high": 160.49, "release_date": "2026-02-05", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-5.3 Codex", "effort": null }, "matched_source_count": 2, "composite": { "score": 40.0, "source_count": 2, "percentiles": { "artificial_analysis": 16.7, "epoch": 63.2 }, "rank": 34, "population": 62 }, "flags": [ { "type": "source_divergence", "spread": 46.5, "percentiles": { "artificial_analysis": 16.7, "epoch": 63.2 } } ] }, { "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": 46.4, "cost_per_task_usd": 3.74, "output_tokens_per_second": 95.5, "latency_first_chunk_seconds": 47.44, "total_response_seconds": 52.67, "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": 46.4, "cost_per_task_usd": 3.74, "output_tokens_per_second": 95.5, "latency_first_chunk_seconds": 47.44, "total_response_seconds": 52.67, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Grok 4.7", "effort": "xhigh" }, "livebench": { "source_model": "grok-4.7-xhigh", "overall_score": 77.4, "category_scores": { "Reasoning": 82.65, "Coding": 77.16, "Agentic Coding": 53.99, "Mathematics": 95.68, "Data Analysis": 76.88, "Language": 80.14, "IF": 75.28 }, "mapping": "variant", "mapping_target": "Grok 4.7", "effort": "xhigh" }, "epoch": { "source_model": "Grok 4.7", "eci": 154.37, "eci_ci_low": 152.73, "eci_ci_high": 156.49, "release_date": "2026-09-21", "organization": "xAI", "mapping": "exact", "mapping_target": "Grok 4.7", "effort": null }, "matched_source_count": 3, "composite": { "score": 56.6, "source_count": 3, "percentiles": { "artificial_analysis": 73.3, "livebench": 56.8, "epoch": 39.6 }, "rank": 26, "population": 62 }, "flags": [] }, { "litellm_key": "claude-opus-5-5", "display": "Claude Opus 5.5", "source_model": "Claude Opus 5.5 (max with fallback)", "source_slug": "claude-opus-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 57.6, "cost_per_task_usd": 5.98, "output_tokens_per_second": 98.3, "latency_first_chunk_seconds": 514.59, "total_response_seconds": 519.68, "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 with fallback)", "source_slug": "claude-opus-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 57.6, "cost_per_task_usd": 5.98, "output_tokens_per_second": 98.3, "latency_first_chunk_seconds": 514.59, "total_response_seconds": 519.68, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Opus 5.5", "effort": "max" }, "livebench": { "source_model": "claude-opus-5-5-max-effort", "overall_score": 83.22, "category_scores": { "Reasoning": 92.15, "Coding": 89.25, "Agentic Coding": 71.72, "Mathematics": 97.08, "Data Analysis": 80.31, "Language": 86.27, "IF": 65.74 }, "mapping": "variant", "mapping_target": "Claude Opus 5.5", "effort": "max" }, "epoch": { "source_model": "Claude Opus 5.5", "eci": 166.82, "eci_ci_low": 163.54, "eci_ci_high": 170.99, "release_date": "2026-09-22", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Opus 5.5", "effort": null }, "matched_source_count": 3, "composite": { "score": 99.2, "source_count": 3, "percentiles": { "artificial_analysis": 100.0, "livebench": 97.7, "epoch": 100.0 }, "rank": 1, "population": 62 }, "flags": [] }, { "litellm_key": "gpt-6-sol", "display": "GPT-6 Sol", "artificial_analysis": null, "livebench": { "source_model": "gpt-6-sol-max", "overall_score": 79.25, "category_scores": { "Reasoning": 88.65, "Coding": 81.77, "Agentic Coding": 52.88, "Mathematics": 96.36, "Data Analysis": 81.19, "Language": 85.3, "IF": 68.57 }, "mapping": "variant", "mapping_target": "GPT-6 Sol", "effort": "max" }, "epoch": { "source_model": "GPT-6 Sol", "eci": 162.55, "eci_ci_low": 160.03, "eci_ci_high": 165.84, "release_date": "2026-09-22", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6 Sol", "effort": null }, "matched_source_count": 2, "composite": { "score": 82.0, "source_count": 2, "percentiles": { "livebench": 77.3, "epoch": 86.8 }, "rank": 12, "population": 62 }, "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": 38.1, "cost_per_task_usd": 0.07, "output_tokens_per_second": 126.2, "latency_first_chunk_seconds": 74.33, "total_response_seconds": 78.29, "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": 38.1, "cost_per_task_usd": 0.07, "output_tokens_per_second": 126.2, "latency_first_chunk_seconds": 74.33, "total_response_seconds": 78.29, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6 Luna", "effort": "max" }, "livebench": { "source_model": "gpt-6-luna-max", "overall_score": 72.03, "category_scores": { "Reasoning": 81.77, "Coding": 78.95, "Agentic Coding": 51.21, "Mathematics": 89.12, "Data Analysis": 73.37, "Language": 73.83, "IF": 55.93 }, "mapping": "variant", "mapping_target": "GPT-6 Luna", "effort": "max" }, "epoch": { "source_model": "GPT-6 Luna", "eci": 156.31, "eci_ci_low": 153.91, "eci_ci_high": 158.75, "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": 30.0, "livebench": 22.7, "epoch": 53.8 }, "rank": 39, "population": 62 }, "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": 43.7, "cost_per_task_usd": 1.03, "output_tokens_per_second": 93.8, "latency_first_chunk_seconds": 2.2, "total_response_seconds": 28.86, "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": 43.7, "cost_per_task_usd": 1.03, "output_tokens_per_second": 93.8, "latency_first_chunk_seconds": 2.2, "total_response_seconds": 28.86, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Step 5 Preview", "effort": null }, "livebench": null, "epoch": null, "matched_source_count": 1, "composite": { "score": 60.0, "source_count": 1, "percentiles": { "artificial_analysis": 60.0 }, "rank": 24, "population": 62 }, "flags": [] }, { "litellm_key": "dashscope/qwen3.8-2.4t-a95b", "display": "Qwen3.8 2.4T A95B", "source_model": "Qwen3.8 2.4T A95B", "source_slug": "qwen3-8-2-4t-a95b", "context": 262000, "creator": "Alibaba", "intelligence_index": 39.9, "cost_per_task_usd": 2.16, "output_tokens_per_second": 38.3, "latency_first_chunk_seconds": 3.07, "total_response_seconds": 68.39, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Qwen3.8 2.4T A95B", "effort": null, "artificial_analysis": { "source_model": "Qwen3.8 2.4T A95B", "source_slug": "qwen3-8-2-4t-a95b", "context": 262000, "creator": "Alibaba", "intelligence_index": 39.9, "cost_per_task_usd": 2.16, "output_tokens_per_second": 38.3, "latency_first_chunk_seconds": 3.07, "total_response_seconds": 68.39, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Qwen3.8 2.4T A95B", "effort": null }, "livebench": null, "epoch": null, "matched_source_count": 1, "composite": { "score": 40.0, "source_count": 1, "percentiles": { "artificial_analysis": 40.0 }, "rank": 35, "population": 62 }, "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": 33.7, "cost_per_task_usd": 1.01, "output_tokens_per_second": 44.4, "latency_first_chunk_seconds": 4.02, "total_response_seconds": 60.36, "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": 33.7, "cost_per_task_usd": 1.01, "output_tokens_per_second": 44.4, "latency_first_chunk_seconds": 4.02, "total_response_seconds": 60.36, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Qwen3.8 27B", "effort": "xhigh" }, "livebench": { "source_model": "qwen3.8-27b", "overall_score": 75.27, "category_scores": { "Reasoning": 80.03, "Coding": 75.69, "Agentic Coding": 61.36, "Mathematics": 86.21, "Data Analysis": 76.59, "Language": 74.35, "IF": 72.66 }, "mapping": "exact", "mapping_target": "Qwen3.8 27B", "effort": null }, "epoch": null, "matched_source_count": 2, "composite": { "score": 30.4, "source_count": 2, "percentiles": { "artificial_analysis": 20.0, "livebench": 40.9 }, "rank": 42, "population": 62 }, "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": 46.3, "cost_per_task_usd": 0.13, "output_tokens_per_second": 50.8, "latency_first_chunk_seconds": 4.01, "total_response_seconds": 53.2, "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": 46.3, "cost_per_task_usd": 0.13, "output_tokens_per_second": 50.8, "latency_first_chunk_seconds": 4.01, "total_response_seconds": 53.2, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "MiMo-V2.6-Pro", "effort": null }, "livebench": null, "epoch": null, "matched_source_count": 1, "composite": { "score": 70.0, "source_count": 1, "percentiles": { "artificial_analysis": 70.0 }, "rank": 17, "population": 62 }, "flags": [] }, { "litellm_key": "auto/upstage-solar-pro4", "display": "Solar Pro 4", "source_model": "Solar Pro 4", "source_slug": "solar-pro4", "context": 512000, "creator": "Upstage", "intelligence_index": 26.6, "cost_per_task_usd": 0.71, "output_tokens_per_second": 118.4, "latency_first_chunk_seconds": 1.65, "total_response_seconds": 22.76, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Solar Pro 4", "effort": null, "artificial_analysis": { "source_model": "Solar Pro 4", "source_slug": "solar-pro4", "context": 512000, "creator": "Upstage", "intelligence_index": 26.6, "cost_per_task_usd": 0.71, "output_tokens_per_second": 118.4, "latency_first_chunk_seconds": 1.65, "total_response_seconds": 22.76, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Solar Pro 4", "effort": null }, "livebench": null, "epoch": null, "matched_source_count": 1, "composite": { "score": 6.7, "source_count": 1, "percentiles": { "artificial_analysis": 6.7 }, "rank": 58, "population": 62 }, "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": 37.9, "cost_per_task_usd": 0.06, "output_tokens_per_second": 51.2, "latency_first_chunk_seconds": 6.38, "total_response_seconds": 55.17, "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": 37.9, "cost_per_task_usd": 0.06, "output_tokens_per_second": 51.2, "latency_first_chunk_seconds": 6.38, "total_response_seconds": 55.17, "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": 26.7, "source_count": 1, "percentiles": { "artificial_analysis": 26.7 }, "rank": 46, "population": 62 }, "flags": [] }, { "litellm_key": "claude-sonnet-5-5", "display": "Claude Sonnet 5.5", "source_model": "Claude Sonnet 5.5 (max with fallback)", "source_slug": "claude-sonnet-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 56.0, "cost_per_task_usd": 5.46, "output_tokens_per_second": 136.7, "latency_first_chunk_seconds": 384.37, "total_response_seconds": 388.03, "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 with fallback)", "source_slug": "claude-sonnet-5-5", "context": 1000000, "creator": "Anthropic", "intelligence_index": 56.0, "cost_per_task_usd": 5.46, "output_tokens_per_second": 136.7, "latency_first_chunk_seconds": 384.37, "total_response_seconds": 388.03, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Sonnet 5.5", "effort": "max" }, "livebench": { "source_model": "claude-sonnet-5-5-xhigh-effort", "overall_score": 77.75, "category_scores": { "Reasoning": 86.81, "Coding": 88.87, "Agentic Coding": 39.34, "Mathematics": 96.69, "Data Analysis": 78.62, "Language": 83.43, "IF": 70.52 }, "mapping": "variant", "mapping_target": "Claude Sonnet 5.5", "effort": "xhigh" }, "epoch": { "source_model": "Claude Sonnet 5.5", "eci": 164.45, "eci_ci_low": 161.35, "eci_ci_high": 168.26, "release_date": "2026-09-28", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Sonnet 5.5", "effort": null }, "matched_source_count": 3, "composite": { "score": 82.9, "source_count": 3, "percentiles": { "artificial_analysis": 96.7, "livebench": 61.4, "epoch": 90.6 }, "rank": 10, "population": 62 }, "flags": [ { "type": "source_divergence", "spread": 35.3, "percentiles": { "artificial_analysis": 96.7, "livebench": 61.4, "epoch": 90.6 } } ] }, { "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": 51.8, "cost_per_task_usd": 0.72, "output_tokens_per_second": 60.1, "latency_first_chunk_seconds": 178.42, "total_response_seconds": 186.73, "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": 51.8, "cost_per_task_usd": 0.72, "output_tokens_per_second": 60.1, "latency_first_chunk_seconds": 178.42, "total_response_seconds": 186.73, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "GPT-6.1 Sol", "effort": "max" }, "livebench": { "source_model": "gpt-6.1-sol-max", "overall_score": 81.62, "category_scores": { "Reasoning": 92.63, "Coding": 80.36, "Agentic Coding": 54.55, "Mathematics": 96.83, "Data Analysis": 82.66, "Language": 90.13, "IF": 74.15 }, "mapping": "variant", "mapping_target": "GPT-6.1 Sol", "effort": "max" }, "epoch": { "source_model": "GPT-6.1 Sol", "eci": 166.32, "eci_ci_low": 163.17, "eci_ci_high": 170.82, "release_date": "2026-09-29", "organization": "OpenAI", "mapping": "exact", "mapping_target": "GPT-6.1 Sol", "effort": null }, "matched_source_count": 3, "composite": { "score": 89.0, "source_count": 3, "percentiles": { "artificial_analysis": 80.0, "livebench": 90.9, "epoch": 96.2 }, "rank": 6, "population": 62 }, "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": 41.8, "cost_per_task_usd": 0.28, "output_tokens_per_second": 78.4, "latency_first_chunk_seconds": 2.58, "total_response_seconds": 34.46, "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": 41.8, "cost_per_task_usd": 0.28, "output_tokens_per_second": 78.4, "latency_first_chunk_seconds": 2.58, "total_response_seconds": 34.46, "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": 71.59, "category_scores": { "Reasoning": 77.64, "Coding": 78.95, "Agentic Coding": 56.77, "Mathematics": 81.24, "Data Analysis": 76.4, "Language": 77.31, "IF": 52.82 }, "mapping": "exact", "mapping_target": "GLM-5.3-Flash", "effort": null }, "epoch": { "source_model": "GLM-5.3-Flash", "eci": 153.23, "eci_ci_low": 150.95, "eci_ci_high": 155.4, "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": 32.3, "source_count": 3, "percentiles": { "artificial_analysis": 46.7, "livebench": 18.2, "epoch": 32.1 }, "rank": 40, "population": 62 }, "flags": [] }, { "litellm_key": "mistral/mistral-large-4", "display": "Mistral Large 4 Preview", "source_model": "Mistral Large 4 Preview", "source_slug": "mistral-large-4", "context": 524288, "creator": "Mistral", "intelligence_index": 38.4, "cost_per_task_usd": 1.13, "output_tokens_per_second": 74.2, "latency_first_chunk_seconds": 1.61, "total_response_seconds": 35.32, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Mistral Large 4 Preview", "effort": null, "artificial_analysis": { "source_model": "Mistral Large 4 Preview", "source_slug": "mistral-large-4", "context": 524288, "creator": "Mistral", "intelligence_index": 38.4, "cost_per_task_usd": 1.13, "output_tokens_per_second": 74.2, "latency_first_chunk_seconds": 1.61, "total_response_seconds": 35.32, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "exact", "mapping_target": "Mistral Large 4 Preview", "effort": null }, "livebench": { "source_model": "mistral-large-4-high", "overall_score": 71.84, "category_scores": { "Reasoning": 83.94, "Coding": 77.16, "Agentic Coding": 57.17, "Mathematics": 93.58, "Data Analysis": 76.54, "Language": 49.64, "IF": 64.82 }, "mapping": "variant", "mapping_target": "Mistral Large 4 Preview", "effort": "high" }, "epoch": { "source_model": "Mistral Large 4", "eci": 146.9, "eci_ci_low": 143.68, "eci_ci_high": 150.94, "release_date": "2026-10-06", "organization": "Mistral AI", "mapping": "exact", "mapping_target": "Mistral Large 4 Preview", "effort": null }, "matched_source_count": 3, "composite": { "score": 21.1, "source_count": 3, "percentiles": { "artificial_analysis": 33.3, "livebench": 20.5, "epoch": 9.4 }, "rank": 48, "population": 62 }, "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": 43.4, "cost_per_task_usd": 0.21, "output_tokens_per_second": 234.1, "latency_first_chunk_seconds": 287.2, "total_response_seconds": 289.33, "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": 43.4, "cost_per_task_usd": 0.21, "output_tokens_per_second": 234.1, "latency_first_chunk_seconds": 287.2, "total_response_seconds": 289.33, "is_reasoning": true, "estimated": false, "archived": false, "mapping": "variant", "mapping_target": "Claude Haiku 5.5", "effort": "max" }, "livebench": { "source_model": "claude-haiku-5-5-xhigh-effort", "overall_score": 72.07, "category_scores": { "Reasoning": 81.23, "Coding": 76.39, "Agentic Coding": 51.36, "Mathematics": 92.75, "Data Analysis": 72.75, "Language": 63.52, "IF": 66.47 }, "mapping": "variant", "mapping_target": "Claude Haiku 5.5", "effort": "xhigh" }, "epoch": { "source_model": "Claude Haiku 5.5", "eci": 158.98, "eci_ci_low": 156.59, "eci_ci_high": 162.07, "release_date": "2026-10-07", "organization": "Anthropic", "mapping": "exact", "mapping_target": "Claude Haiku 5.5", "effort": null }, "matched_source_count": 3, "composite": { "score": 51.3, "source_count": 3, "percentiles": { "artificial_analysis": 53.3, "livebench": 25.0, "epoch": 75.5 }, "rank": 30, "population": 62 }, "flags": [ { "type": "source_divergence", "spread": 50.5, "percentiles": { "artificial_analysis": 53.3, "livebench": 25.0, "epoch": 75.5 } } ] }, { "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": 55.8, "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": 55.8, "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": null, "matched_source_count": 1, "composite": { "score": 93.3, "source_count": 1, "percentiles": { "artificial_analysis": 93.3 }, "rank": 3, "population": 62 }, "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": 52.6, "cost_per_task_usd": 1.99, "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": 52.6, "cost_per_task_usd": 1.99, "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": null, "epoch": { "source_model": "Gemini 4 Argon", "eci": 164.56, "eci_ci_low": 161.67, "eci_ci_high": 168.7, "release_date": "2026-09-30", "organization": "Google DeepMind", "mapping": "exact", "mapping_target": "Gemini 4 Argon", "effort": null }, "matched_source_count": 2, "composite": { "score": 87.9, "source_count": 2, "percentiles": { "artificial_analysis": 83.3, "epoch": 92.5 }, "rank": 7, "population": 62 }, "flags": [] } ], "unmatched": [ { "litellm_key": "manual/gpt-5-6-cyber", "display": "GPT-5.6 Cyber" }, { "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" } ], "alias_misses": [] }