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 · deepseek-v4-flash 1 row
Not enough history to chart — a single observation (34.53 on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 34.53aa_slug=deepseek-v4-flash · 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 |
|---|---|---|---|---|---|---|
| #301SonarPerplexity AI | 7.71 | aa_slug=sonar · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #302step-3-vl-10bStepFun | 7.69 | aa_slug=step-3-vl-10b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #303Llama 3.3 70BMeta AI | 7.66 | aa_slug=llama-3-3-instruct-70b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #304qwen3-30b-a3b-instruct-reasoningAlibaba Group | 7.63 | aa_slug=qwen3-30b-a3b-instruct-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #305Sonar ProPerplexity AI | 7.61 | aa_slug=sonar-pro · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #306devstral-smallMistral AI | 7.6 | aa_slug=devstral-small · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #307QwQ-32B-PreviewAlibaba Group | 7.59 | aa_slug=QwQ-32B-Preview · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #308mistral-large-2Mistral AI | 7.56 | aa_slug=mistral-large-2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #309GLM 4.5VZ.ai (Zhipu AI) | 7.56 | aa_slug=glm-4-5v-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #310llama-3-1-nemotron-ultra-253b-v1-reasoningNVIDIA | 7.53 | aa_slug=llama-3-1-nemotron-ultra-253b-v1-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #311qwen3-30b-a3b-2507Alibaba Group | 7.52 | aa_slug=qwen3-30b-a3b-2507 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #312ernie-4-5-300b-a47bBaidu | 7.5 | aa_slug=ernie-4-5-300b-a47b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #313Hermes 4 405BNous Research | 7.49 | aa_slug=hermes-4-llama-3-1-405b-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #314solar-pro-2-reasoningUpstage | 7.49 | aa_slug=solar-pro-2-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #315nvidia-nemotron-nano-12b-v2-vl-reasoningNVIDIA | 7.48 | aa_slug=nvidia-nemotron-nano-12b-v2-vl-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #316gemma-4-e4b-non-reasoningGoogle | 7.46 | aa_slug=gemma-4-e4b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #317granite-4.1-30bIBM | 7.44 | aa_slug=granite-4-1-30b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #318NVIDIA-Nemotron-Nano-9B-v2NVIDIA | 7.43 | aa_slug=nvidia-nemotron-nano-9b-v2-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #319hermes-4-llama-3-1-405bNous Research | 7.41 | aa_slug=hermes-4-llama-3-1-405b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #320gemini-2-0-flash-lite-001Google | 7.41 | aa_slug=gemini-2-0-flash-lite-001 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #321nvidia-nemotron-3-nano-4bNVIDIA | 7.38 | aa_slug=nvidia-nemotron-3-nano-4b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #322llama-nemotron-super-49b-v1-5NVIDIA | 7.36 | aa_slug=llama-nemotron-super-49b-v1-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #323qwen3-32b-instructAlibaba Group | 7.34 | aa_slug=qwen3-32b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #324GPT-4o (2024-05-13)OpenAI | 7.33 | aa_slug=gpt-4o-2024-05-13 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #325gemini-2-0-flash-lite-previewGoogle | 7.33 | aa_slug=gemini-2-0-flash-lite-preview · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #326k2-v2-lowMBZUAI Institute of Foundation Models | 7.31 | aa_slug=k2-v2-low · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #327llama-3-1-nemotron-nano-4b-reasoningNVIDIA | 7.31 | aa_slug=llama-3-1-nemotron-nano-4b-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #328Kimi-Linear-48B-A3B-InstructMoonshot AI | 7.3 | aa_slug=kimi-linear-48b-a3b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #329Llama-3.1-405BMeta AI | 7.29 | aa_slug=llama-3-1-instruct-405b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #330llama-3-3-nemotron-super-49bNVIDIA | 7.28 | aa_slug=llama-3-3-nemotron-super-49b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #331Qwen3 VL 8B InstructQwen | 7.26 | aa_slug=qwen3-vl-8b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #332Qwen3-4BQwen | 7.23 | aa_slug=qwen3-4b-instruct-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #333LFM2.5-8B-A1BLiquid AI | 7.22 | aa_slug=lfm2-5-8b-a1b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #334claude-35-sonnet-june-24Anthropic | 7.21 | aa_slug=claude-35-sonnet-june-24 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #335tulu3-405bAllen Institute for AI | 7.2 | aa_slug=tulu3-405b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #336gpt-4o-chatgptOpenAI | 7.19 | aa_slug=gpt-4o-chatgpt · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #337ring-flash-2-0inclusionAI | 7.15 | aa_slug=ring-flash-2-0 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #338Pixtral LargeMistral AI | 7.15 | aa_slug=pixtral-large-2411 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #339olmo-3-1-32b-thinkAllen Institute for AI | 7.12 | aa_slug=olmo-3-1-32b-think · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #340grok-2xAI | 7.11 | aa_slug=grok-2-1212 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #341gpt-5-nano-minimalOpenAI | 7.09 | aa_slug=gpt-5-nano-minimal · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #342gemini-1-5-flashGoogle | 7.07 | aa_slug=gemini-1-5-flash · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #343qwen3-vl-4b-reasoningAlibaba Group | 7.05 | aa_slug=qwen3-vl-4b-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #344gpt-4-turboOpenAI | 7.04 | aa_slug=gpt-4-turbo · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #345solar-pro-2Upstage | 7 | aa_slug=solar-pro-2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #346Command ACohere | 6.96 | aa_slug=command-a · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #347nova-proAmazon Web Services | 6.96 | aa_slug=nova-pro · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #348Qwen3.5-2BQwen | 6.94 | aa_slug=qwen3-5-2b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #349llama-3-1-nemotron-instruct-70bNVIDIA | 6.94 | aa_slug=llama-3-1-nemotron-instruct-70b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #350Llama 3.1 8BMeta AI | 6.93 | aa_slug=llama-3-1-instruct-8b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #351grok-betaSpaceXAI | 6.89 | aa_slug=grok-beta · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #352qwen2.5-32b-instructAlibaba Group | 6.87 | aa_slug=qwen2.5-32b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #353Nemotron 3 Nano 30B A3BNVIDIA | 6.85 | aa_slug=nvidia-nemotron-3-nano-30b-a3b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #354nvidia-nemotron-nano-9b-v2NVIDIA | 6.84 | aa_slug=nvidia-nemotron-nano-9b-v2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #355Mistral Large 2.0Mistral AI | 6.8 | aa_slug=mistral-large-2407 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #356qwen3-4b-2507-instructAlibaba Group | 6.74 | aa_slug=qwen3-4b-2507-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #357Qwen2.5 Coder 32B InstructQwen | 6.74 | aa_slug=qwen2-5-coder-32b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #358qwen3-14b-instructAlibaba Group | 6.7 | aa_slug=qwen3-14b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #359glm-4-5vZ.ai (Zhipu AI) | 6.7 | aa_slug=glm-4-5v · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #360gpt-4OpenAI | 6.7 | aa_slug=gpt-4 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #361gemini-2-5-flash-liteGoogle | 6.67 | aa_slug=gemini-2-5-flash-lite · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #362nova-liteAmazon Web Services | 6.67 | aa_slug=nova-lite · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #363Mistral Small 3Mistral AI | 6.67 | aa_slug=mistral-small-3 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #364gpt-4o-miniOpenAI | 6.66 | aa_slug=gpt-4o-mini · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #365hermes-4-llama-3-1-70bNous Research | 6.66 | aa_slug=hermes-4-llama-3-1-70b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #366deepseek-v2-5DeepSeek | 6.62 | aa_slug=deepseek-v2-5 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #367qwen3-30b-a3b-instructAlibaba Group | 6.62 | aa_slug=qwen3-30b-a3b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #368qwen3-4b-instructAlibaba Group | 6.61 | aa_slug=qwen3-4b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #369Llama-3.1-70BMeta AI | 6.6 | aa_slug=llama-3-1-instruct-70b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #370granite-4.1-8bIBM | 6.57 | aa_slug=granite-4-1-8b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #371gemini-2-0-flash-thinking-exp-1219Google | 6.56 | aa_slug=gemini-2-0-flash-thinking-exp-1219 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #372sarvam-30bSarvam | 6.56 | aa_slug=sarvam-30b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #373deepseek-v2-5-sep-2024DeepSeek | 6.55 | aa_slug=deepseek-v2-5-sep-2024 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #374olmo-3-1-32b-instructAllen Institute for AI | 6.5 | aa_slug=olmo-3-1-32b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #375Mistral SabaMistral AI | 6.49 | aa_slug=mistral-saba · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #376deepseek-r1-distill-llama-8bDeepSeek | 6.48 | aa_slug=deepseek-r1-distill-llama-8b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #377gemma-4-e2b-non-reasoningGoogle | 6.48 | aa_slug=gemma-4-e2b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #378olmo-3-32b-thinkAllen Institute for AI | 6.47 | aa_slug=olmo-3-32b-think · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #379r1-1776Perplexity AI | 6.44 | aa_slug=r1-1776 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #380gemini-1-5-pro-may-2024Google | 6.44 | aa_slug=gemini-1-5-pro-may-2024 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #381reka-flashrekaai | 6.43 | aa_slug=reka-flash · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #382qwen-turboAlibaba Group | 6.43 | aa_slug=qwen-turbo · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #383llama-3-2-instruct-90b-visionMeta AI | 6.41 | aa_slug=llama-3-2-instruct-90b-vision · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #384solar-miniUpstage | 6.41 | aa_slug=solar-mini · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #385grok-1xAI | 6.34 | aa_slug=grok-1 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #386exaone-4-0-32bLG AI Research | 6.33 | aa_slug=exaone-4-0-32b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #387phi-4-miniMicrosoft | 6.33 | aa_slug=phi-4-mini · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #388qwen2-72b-instructAlibaba Group | 6.33 | aa_slug=qwen2-72b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #389qwen3-5-2b-non-reasoningAlibaba Group | 6.19 | aa_slug=qwen3-5-2b-non-reasoning · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #390gemini-1-5-flash-8bGoogle | 6.15 | aa_slug=gemini-1-5-flash-8b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #391Qwen3.5-0.8BQwen | 6.13 | aa_slug=qwen3-5-0-8b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #392jamba-1-7-largeAI21 Labs | 6.07 | aa_slug=jamba-1-7-large · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #393deephermes-3-mistral-24b-previewNous Research | 6.07 | aa_slug=deephermes-3-mistral-24b-preview · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #394granite-4-0-h-smallIBM | 6.05 | aa_slug=granite-4-0-h-small · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #395qwen3-omni-30b-a3b-instructAlibaba Group | 6.01 | aa_slug=qwen3-omni-30b-a3b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #396jamba-1-5-largeAI21 Labs | 6.01 | aa_slug=jamba-1-5-large · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #397Hermes 3 70B InstructNous Research | 6 | aa_slug=hermes-3-llama-3-1-70b · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #398qwen3-8b-instructAlibaba Group | 5.99 | aa_slug=qwen3-8b-instruct · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #399deepseek-coder-v2DeepSeek | 5.98 | aa_slug=deepseek-coder-v2 · version=4.3 · estimated=true | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #400jamba-1-6-largeAI21 Labs | 5.97 | aa_slug=jamba-1-6-large · 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.