BenchmarkActivecategory · composite
Artificial Analysis Intelligence Index
composite of several evaluations run by Artificial Analysis
quality57
Updated 8 h ago · first seen 11 Sept 2026
bench_01M293SPG0EAFKRT01VFHFK9SC
- Metric
- index
- Direction
- Higher is better
- Results
- 638 · 491 filtered
- Leader
- Claude Fable 5.1 53.37
Score history · Grok 4.3 1 row
Not enough history to chart — a single observation (25.39 on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 25.39aa_slug=grok-4-3 · version=4.3 · estimated=false11 Sept 2026
Leaderboard 491 current results · config contains “true”
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #1Claude Opus 4.7Anthropic | 40.69 | aa_slug=claude-opus-4-7 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #2gemini-3-7-flash-mediumGoogle | 39.62 | aa_slug=gemini-3-7-flash-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #3gpt-5.4OpenAI | 38.98 | aa_slug=gpt-5-4 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #4Z.ai GLM 5.2Z.ai (Zhipu AI) | 38.64 | aa_slug=glm-5-2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #5gemini-3-7-flash-lowGoogle | 36.95 | aa_slug=gemini-3-7-flash-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #6agnes-3-0-flashSapiens AI | 35.5 | aa_slug=agnes-3-0-flash · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #7agnes-2-5-pro-betaSapiens AI | 35.24 | aa_slug=agnes-2-5-pro-beta · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #8kimi-k3-lowMoonshot AI | 34.46 | aa_slug=kimi-k3-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #9gemini-3-5-flash-mediumGoogle | 33.63 | aa_slug=gemini-3-5-flash-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #10motif-3Motif Technologies | 33.57 | aa_slug=motif-3 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #11gpt-5.3-codexOpenAI | 32.5 | aa_slug=gpt-5-3-codex · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #12motif-0714Motif Technologies | 32.31 | aa_slug=motif-0714 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #13claude-opus-4-6-adaptiveAnthropic | 31.95 | aa_slug=claude-opus-4-6-adaptive · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #14Kimi K2.6Moonshot AI | 31.32 | aa_slug=kimi-k2-6 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #15muse-sparkMeta AI | 31.3 | aa_slug=muse-spark · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #16claude-opus-4-7-non-reasoningAnthropic | 30.93 | aa_slug=claude-opus-4-7-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #17gpt-5-5-lowOpenAI | 30.71 | aa_slug=gpt-5-5-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #18k2-horizon-375b-a23bMBZUAI Institute of Foundation Models | 30.7 | aa_slug=k2-horizon-375b-a23b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #19gpt-5.2OpenAI | 30.45 | aa_slug=gpt-5-2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #20apodex-1-1Apodex | 30.37 | aa_slug=apodex-1-1 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #21deepseek-v4-pro-0424-highDeepSeek | 30.11 | aa_slug=deepseek-v4-pro-0424-high · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #22claude-opus-4-5-thinkingAnthropic | 29.1 | aa_slug=claude-opus-4-5-thinking · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #23claude-sonnet-5-non-reasoningAnthropic | 28.94 | aa_slug=claude-sonnet-5-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #24mimo-v2-proXiaomi | 28.64 | aa_slug=mimo-v2-pro · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #25GPT-5.2-CodexOpenAI | 28.5 | aa_slug=gpt-5-2-codex · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #26Qwen3.6 Max PreviewQwen | 28.37 | aa_slug=qwen3-6-max · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #27gpt-5-6-sol-non-reasoningOpenAI | 28.33 | aa_slug=gpt-5-6-sol-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #28nex-n2-proNex AGI | 28.2 | aa_slug=nex-n2-pro · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #29Solar Pro 4Upstage | 28.15 | aa_slug=solar-pro4 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #30gemini-3-proGoogle | 27.96 | aa_slug=gemini-3-pro · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #31GLM 5Z.ai (Zhipu AI) | 27.91 | aa_slug=glm-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #32gpt-5-4-lowOpenAI | 27.58 | aa_slug=gpt-5-4-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #33jt-4-1-flash-236b-a21bChina Mobile | 27.29 | aa_slug=jt-4-1-flash-236b-a21b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #34grok-build-0-1-06-16SpaceXAI | 27.17 | aa_slug=grok-build-0-1-06-16 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #35Qwen3.6 PlusQwen | 27.01 | aa_slug=qwen3-6-plus · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #36GLM 5 TurboZ.ai (Zhipu AI) | 26.6 | aa_slug=glm-5-turbo · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #37gpt-5-2-mediumOpenAI | 26.5 | aa_slug=gpt-5-2-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #38Claude Opus 4.6Anthropic | 26.35 | aa_slug=claude-opus-4-6 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #39Gemini 3 Flash PreviewGoogle | 26.33 | aa_slug=gemini-3-flash-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #40Grok 4.20xAI | 25.66 | aa_slug=grok-4-20 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #41grok-4-20-0309SpaceXAI | 25.22 | aa_slug=grok-4-20-0309 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #42mimo-v2-omni-0327Xiaomi | 25.12 | aa_slug=mimo-v2-omni-0327 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #43Ling 3.0 FlashinclusionAI | 24.94 | aa_slug=ling-3-0-flash · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #44GPT-5-CodexOpenAI | 24.88 | aa_slug=gpt-5-codex · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #45grok-4-3-mediumSpaceXAI | 24.78 | aa_slug=grok-4-3-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #46solar-open2-250bUpstage | 24.74 | aa_slug=solar-open2-250b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #47gpt-5.1OpenAI | 24.74 | aa_slug=gpt-5-1 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #48Claude Sonnet 4.6Anthropic | 24.69 | aa_slug=claude-sonnet-4-6 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #49grok-4-3-lowSpaceXAI | 24.3 | aa_slug=grok-4-3-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #50glm-5-1-non-reasoningZ.ai (Zhipu AI) | 24.24 | aa_slug=glm-5-1-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #51mimo-v2-omniXiaomi | 23.92 | aa_slug=mimo-v2-omni · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #52gemini-3-5-flash-minimalGoogle | 23.85 | aa_slug=gemini-3-5-flash-minimal · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #53GPT-5.1-CodexOpenAI | 23.7 | aa_slug=gpt-5-1-codex · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #54Claude Opus 4.5Anthropic | 23.68 | aa_slug=claude-opus-4-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #55kimi-k2-6-non-reasoningMoonshot AI | 23.57 | aa_slug=kimi-k2-6-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #56GLM 5V TurboZ.ai (Zhipu AI) | 23.5 | aa_slug=glm-5v-turbo · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #57Kimi K2.5Moonshot AI | 23.46 | aa_slug=kimi-k2-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #58claude-sonnet-4-6-non-reasoning-low-effortAnthropic | 23.3 | aa_slug=claude-sonnet-4-6-non-reasoning-low-effort · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #59gpt-5-5-non-reasoningOpenAI | 23.17 | aa_slug=gpt-5-5-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #60gpt-5OpenAI | 22.98 | aa_slug=gpt-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #61Qwen3.5-27BQwen | 22.9 | aa_slug=qwen3-5-27b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #62gpt-5 (medium)OpenAI | 22.87 | aa_slug=gpt-5-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #63claude-4-1-opus-thinkingAnthropic | 22.85 | aa_slug=claude-4-1-opus-thinking · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #64MiniMax M2.5MiniMax | 22.8 | aa_slug=minimax-m2-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #65Hy3 previewTencent | 22.74 | aa_slug=hy3-preview · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #66a-x-k2SK Telecom | 22.7 | aa_slug=a-x-k2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #67gpt-5-5-instant-05-26OpenAI | 22.69 | aa_slug=gpt-5-5-instant-05-26 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #68grok-4SpaceXAI | 22.49 | aa_slug=grok-4 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #69mimo-v2-0206Xiaomi | 22.44 | aa_slug=mimo-v2-0206 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #70glm-5-2-non-reasoningZ.ai (Zhipu AI) | 22.43 | aa_slug=glm-5-2-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #71qwen3-8-27b-non-reasoningAlibaba Group | 22.42 | aa_slug=qwen3-8-27b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #72gemini-3-pro-lowGoogle | 22.32 | aa_slug=gemini-3-pro-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #73gpt-5-6-terra-non-reasoningOpenAI | 22.3 | aa_slug=gpt-5-6-terra-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #74GLM 4.7Z.ai (Zhipu AI) | 22.24 | aa_slug=glm-4-7 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #75Kimi K2 ThinkingMoonshot AI | 22.02 | aa_slug=kimi-k2-thinking · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #76o3-proOpenAI | 21.87 | aa_slug=o3-pro · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #77g9v3-39a5bAI9Stars | 21.83 | aa_slug=g9v3-39a5b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #78glm-5-non-reasoningZ.ai (Zhipu AI) | 21.78 | aa_slug=glm-5-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #79KAT-Coder-Pro V2Kwaipilot | 21.7 | aa_slug=kat-coder-pro-v2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #80DeepSeek V3.2DeepSeek | 21.49 | aa_slug=deepseek-v3-2-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #81qwen3-5-397b-a17b-non-reasoningAlibaba Group | 21.44 | aa_slug=qwen3-5-397b-a17b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #82Qwen3 Max ThinkingQwen | 21.26 | aa_slug=qwen3-max-thinking · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #83MiniMax M2.1MiniMax | 20.95 | aa_slug=minimax-m2-1 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #84deepseek-v4-pro-0424-non-reasoningDeepSeek | 20.83 | aa_slug=deepseek-v4-pro-0424-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #85mimo-v2-flash-reasoningXiaomi | 20.82 | aa_slug=mimo-v2-flash-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #86gpt-5 (low)OpenAI | 20.79 | aa_slug=gpt-5-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #87Claude Opus 4Anthropic | 20.64 | aa_slug=claude-4-opus-thinking · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #88gpt-5-mini-mediumOpenAI | 20.6 | aa_slug=gpt-5-mini-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #89GPT-5.1-Codex MiniOpenAI | 20.38 | aa_slug=gpt-5-1-codex-mini · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #90qwen3-5-omni-plusAlibaba Group | 20.38 | aa_slug=qwen3-5-omni-plus · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #91grok-4-1-fast-reasoningSpaceXAI | 20.37 | aa_slug=grok-4-1-fast-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #92o3OpenAI | 20.2 | aa_slug=o3 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #93gpt-5-4-nano-mediumOpenAI | 20.01 | aa_slug=gpt-5-4-nano-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #94qwen3-6-27b-non-reasoningAlibaba Group | 19.83 | aa_slug=qwen3-6-27b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #95gpt-5-4-mini-mediumOpenAI | 19.75 | aa_slug=gpt-5-4-mini-medium · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #96k-exaone-2-0-0803LG AI Research | 19.69 | aa_slug=k-exaone-2-0-0803 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #97Step 3.7 FlashStepFun | 19.48 | aa_slug=step-3-7-flash · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #98kimi-k2-5-non-reasoningMoonshot AI | 19.43 | aa_slug=kimi-k2-5-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #99qwen3-5-27b-non-reasoningAlibaba Group | 19.37 | aa_slug=qwen3-5-27b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #100Claude Sonnet 4.5Anthropic | 19.34 | aa_slug=claude-4-5-sonnet · version=4.3 · estimated=true | — (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 8 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 8 h agomedium
- Metric
- index
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 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 8 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 8 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 | 6 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.