BenchmarkActivecategory · composite
Artificial Analysis Intelligence Index
composite of several evaluations run by Artificial Analysis
quality57
Updated 9 h ago · first seen 11 Sept 2026
bench_01M293SPG0EAFKRT01VFHFK9SC
- Metric
- index
- Direction
- Higher is better
- Results
- 638 · 147 filtered
- Leader
- Claude Fable 5.1 53.37
Score history · granite-4.1-30b 1 row
Not enough history to chart — a single observation (7.44 on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 7.44aa_slug=granite-4-1-30b · version=4.3 · estimated=true11 Sept 2026
Leaderboard 147 current results · config contains “false”
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #1Claude Fable 5.1Anthropic | 53.37 | aa_slug=claude-fable-5-1 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #2claude-fable-5-1-xhighAnthropic | 53.18 | aa_slug=claude-fable-5-1-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #3gpt-6-astraOpenAI | 52.81 | aa_slug=gpt-6-astra · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #4gpt-6-astra-xhighOpenAI | 52.51 | aa_slug=gpt-6-astra-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #5claude-fable-5-1-highAnthropic | 51.21 | aa_slug=claude-fable-5-1-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #6gpt-6-astra-highOpenAI | 51.05 | aa_slug=gpt-6-astra-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #7Claude Opus 5Anthropic | 50.7 | aa_slug=claude-opus-5 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #8Claude Fable 5Anthropic | 49.7 | aa_slug=claude-fable-5 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #9gpt-6-astra-mediumOpenAI | 49.67 | aa_slug=gpt-6-astra-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #10claude-opus-5-xhighAnthropic | 49.65 | aa_slug=claude-opus-5-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #11claude-fable-5-1-mediumAnthropic | 49.06 | aa_slug=claude-fable-5-1-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #12claude-opus-5-highAnthropic | 48.24 | aa_slug=claude-opus-5-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #13Muse Spark 1.3Meta AI | 48.17 | aa_slug=muse-spark-1-3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #14gpt-5-6-solOpenAI | 47.06 | aa_slug=gpt-5-6-sol · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #15claude-fable-5-1-lowAnthropic | 47.04 | aa_slug=claude-fable-5-1-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #16gpt-6-astra-lowOpenAI | 45.99 | aa_slug=gpt-6-astra-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #17gpt-6-astra-non-reasoningOpenAI | 45.17 | aa_slug=gpt-6-astra-non-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #18muse-spark-1-3-xhighMeta AI | 45.16 | aa_slug=muse-spark-1-3-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #19claude-opus-5-mediumAnthropic | 45.06 | aa_slug=claude-opus-5-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #20GLM 5.3Z.ai (Zhipu AI) | 44.86 | aa_slug=glm-5-3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #21Grok 4.6xAI | 44.41 | aa_slug=grok-4-6 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #22grok-4-6-xhighSpaceXAI | 44.27 | aa_slug=grok-4-6-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #23gpt-5-6-sol-xhighOpenAI | 44.14 | aa_slug=gpt-5-6-sol-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #24Kimi K3Moonshot AI | 43.78 | aa_slug=kimi-k3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #25grok-4-6-mediumSpaceXAI | 43.01 | aa_slug=grok-4-6-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #26gpt-5-6-sol-highOpenAI | 42.5 | aa_slug=gpt-5-6-sol-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #27gpt-5.6-terraOpenAI | 42.25 | aa_slug=gpt-5-6-terra · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #28Claude Opus 4.8Anthropic | 41.99 | aa_slug=claude-opus-4-8 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #29GLM 5.3 FlashZ.ai (Zhipu AI) | 41.91 | aa_slug=glm-5-3-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #30Gemini 3.8 FlashGoogle | 41.19 | aa_slug=gemini-3-8-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #31Qwen 3.8 MaxQwen | 40.3 | aa_slug=qwen3-8-max · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #32Qwen3.8 2.4T A95BQwen | 40.04 | aa_slug=qwen3-8-2-4t-a95b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #33gemini-3-8-flash-mediumGoogle | 40 | aa_slug=gemini-3-8-flash-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #34Qwen3.8 FlashQwen | 39.91 | aa_slug=qwen3-8-flash-next · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #35Muse Spark 1.2Meta AI | 39.8 | aa_slug=muse-spark-1-2 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #36claude-opus-5-lowAnthropic | 39.79 | aa_slug=claude-opus-5-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #37DeepSeek-V4.1-FlashDeepSeek | 39.55 | aa_slug=deepseek-v4-1-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #38gpt-5-6-sol-mediumOpenAI | 39.48 | aa_slug=gpt-5-6-sol-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #39Gemini 3.7 FlashGoogle | 39.43 | aa_slug=gemini-3-7-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #40Grok 4.5xAI | 39.08 | aa_slug=grok-4-5 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #41gpt-5.5OpenAI | 38.63 | aa_slug=gpt-5-5 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #42Claude Sonnet 5Anthropic | 38.36 | aa_slug=claude-sonnet-5 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #43gpt-5-6-terra-xhighOpenAI | 38.19 | aa_slug=gpt-5-6-terra-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #44gpt-5.6-lunaOpenAI | 37.5 | aa_slug=gpt-5-6-luna · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #45gpt-5-5-highOpenAI | 37.29 | aa_slug=gpt-5-5-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #46deepseek-v4-proDeepSeek | 36.28 | aa_slug=deepseek-v4-pro · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #47grok-4-6-lowSpaceXAI | 35.41 | aa_slug=grok-4-6-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #48deepseek-v4-flash-visionDeepSeek | 35.01 | aa_slug=deepseek-v4-flash-vision · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #49gpt-5-6-luna-xhighOpenAI | 34.77 | aa_slug=gpt-5-6-luna-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #50claude-sonnet-5-xhighAnthropic | 34.71 | aa_slug=claude-sonnet-5-xhigh · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #51deepseek-v4-flashDeepSeek | 34.53 | aa_slug=deepseek-v4-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #52gpt-5-6-terra-highOpenAI | 34.49 | aa_slug=gpt-5-6-terra-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #53Gemini 3.6 FlashGoogle | 34.34 | aa_slug=gemini-3-6-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #54Muse Spark 1.1Meta AI | 34.27 | aa_slug=muse-spark-1-1 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #55gpt-5-5-mediumOpenAI | 34.15 | aa_slug=gpt-5-5-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #56Qwen3.8 27BQwen | 33.9 | aa_slug=qwen3-8-27b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #57gpt-5-6-sol-lowOpenAI | 33.8 | aa_slug=gpt-5-6-sol-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #58gemini-3-8-flash-lowGoogle | 33.79 | aa_slug=gemini-3-8-flash-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #59Gemini 3.5 FlashGoogle | 32.98 | aa_slug=gemini-3-5-flash · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #60gpt-5-6-luna-highOpenAI | 32.41 | aa_slug=gpt-5-6-luna-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #61claude-sonnet-5-highAnthropic | 32.03 | aa_slug=claude-sonnet-5-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #62deepseek-v4-pro-0424DeepSeek | 30.87 | aa_slug=deepseek-v4-pro-0424 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #63claude-sonnet-4-6-adaptiveAnthropic | 30.45 | aa_slug=claude-sonnet-4-6-adaptive · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #64gpt-5-6-terra-mediumOpenAI | 30.42 | aa_slug=gpt-5-6-terra-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #65Gemini 3.1 Pro PreviewGoogle | 30.36 | aa_slug=gemini-3-1-pro-preview · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #66Qwen3.7 MaxQwen | 29.87 | aa_slug=qwen3-7-max · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #67MiniMax M3MiniMax | 29.61 | aa_slug=minimax-m3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #68claude-sonnet-5-mediumAnthropic | 28.44 | aa_slug=claude-sonnet-5-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #69gpt-5-6-terra-lowOpenAI | 27.92 | aa_slug=gpt-5-6-terra-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #70qwen3-8-27b-mediumAlibaba Group | 27.81 | aa_slug=qwen3-8-27b-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #71agnes-2-5-pro-alphaSapiens AI | 27.8 | aa_slug=agnes-2-5-pro-alpha · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #72quasar-438bMultiverse Computing | 27.13 | aa_slug=quasar-438b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #73gpt-5-5-instant-06-26OpenAI | 26.8 | aa_slug=gpt-5-5-instant-06-26 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #74qwen3-8-27b-lowAlibaba Group | 26.49 | aa_slug=qwen3-8-27b-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #75GLM 5.1Z.ai (Zhipu AI) | 26.45 | aa_slug=glm-5-1 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #76MiMo-V2.5-ProXiaomi | 26.41 | aa_slug=mimo-v2-5-pro · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #77Kimi K2.7 CodeMoonshot AI | 26.27 | aa_slug=kimi-k2-7-code · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #78Inkling SmallThinking Machines | 26.09 | aa_slug=inkling-small · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #79Qwen 3.7 PlusQwen | 25.82 | aa_slug=qwen3-7-plus · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #80Hy3Tencent | 25.77 | aa_slug=hy3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #81InklingThinking Machines | 25.54 | aa_slug=inkling · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #82gpt-5-6-luna-mediumOpenAI | 25.48 | aa_slug=gpt-5-6-luna-medium · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #83Grok 4.3xAI | 25.39 | aa_slug=grok-4-3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #84deepseek-v4-flash-0420-highDeepSeek | 24.84 | aa_slug=deepseek-v4-flash-0420-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #85Ling 3.0 Flash VLinclusionAI | 24.77 | aa_slug=ling-3-0-flash-vl · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #86claude-sonnet-5-lowAnthropic | 24.74 | aa_slug=claude-sonnet-5-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #87deepseek-v4-flash-0420DeepSeek | 24.63 | aa_slug=deepseek-v4-flash-0420 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #88gpt-5.4-miniOpenAI | 24.58 | aa_slug=gpt-5-4-mini · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #89Nemotron 3 UltraNVIDIA | 23.41 | aa_slug=nvidia-nemotron-3-ultra-550b-a55b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #90MiniMax M2.7MiniMax | 23.22 | aa_slug=minimax-m2-7 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #91Gemini 3.5 Flash-LiteGoogle | 22.66 | aa_slug=gemini-3-5-flash-lite · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #92MiMo-V2.5Xiaomi | 22.3 | aa_slug=mimo-v2-5-0424 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #93Qwen3.6 27BQwen | 21.91 | aa_slug=qwen3-6-27b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #94gpt-5-6-luna-lowOpenAI | 21.55 | aa_slug=gpt-5-6-luna-low · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #95gpt-5.4-nanoOpenAI | 21.24 | aa_slug=gpt-5-4-nano · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #96claude-4-5-sonnet-thinkingAnthropic | 21.18 | aa_slug=claude-4-5-sonnet-thinking · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #97LongCat 2.0Meituan | 19.69 | aa_slug=longcat-2-0 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #98Qwen3.5 397B A17BQwen | 19.11 | aa_slug=qwen3-5-397b-a17b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #99Qwen3.6 35B A3BQwen | 18.81 | aa_slug=qwen3-6-35b-a3b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #100Muse Glimmer 30BMeta AI | 18.07 | aa_slug=muse-glimmer · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.
The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.
Definition
- Category
- composite
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Task
- composite of several evaluations run by Artificial Analysis
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Metric
- index
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Direction
- Higher is better
- Known limitations
- Proprietary composite; methodology versions change.
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →
- Evaluated models
- llama-2-chat-7b, grok-3-mini-reasoning, claude-opus-5-medium, gemma-4-12B, deepseek-v4-flash, grok-4-3-low, llama-65b, gemini-2.0-flash-exp +630(638 total)
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
5 claims · 5 properties
Categorycategory1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| composite | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Known limitationsknown_limitations1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Proprietary composite; methodology versions change. | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Metricmetric1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| index | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Tasktask1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| composite of several evaluations run by Artificial Analysis | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://artificialanalysis.ai | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
New benchmark: Artificial Analysis Intelligence Index
registry
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 7 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.