BenchmarkActivecategory · composite
Artificial Analysis Intelligence Index
composite of several evaluations run by Artificial Analysis
quality57
Updated 7 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 · gpt-5.5 1 row
Not enough history to chart — a single observation (38.63 on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 38.63aa_slug=gpt-5-5 · version=4.3 · estimated=false11 Sept 2026
Leaderboard 147 current results · config contains “false”
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #101claude-4-5-haiku-reasoningAnthropic | 17.59 | aa_slug=claude-4-5-haiku-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #102gpt-5-miniOpenAI | 17.41 | aa_slug=gpt-5-mini · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #103ring-2-6-1tinclusionAI | 17.28 | aa_slug=ring-2-6-1t · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #104Gemini 2.5 ProGoogle | 16.66 | aa_slug=gemini-2-5-pro · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #105Qwen3.5-122B-A10BQwen | 16.19 | aa_slug=qwen3-5-122b-a10b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #106gemini-3-1-flash-lite-previewGoogle | 16.03 | aa_slug=gemini-3-1-flash-lite-preview · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #107Gemma 4 31BGoogle | 15.42 | aa_slug=gemma-4-31b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #108deepseek-v3-1-terminus-reasoningDeepSeek | 15.4 | aa_slug=deepseek-v3-1-terminus-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #109Mistral Medium 3.5Mistral AI | 14.89 | aa_slug=mistral-medium-3-5 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #110grok-4-3-non-reasoningSpaceXAI | 14.54 | aa_slug=grok-4-3-non-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #111command-a-plusCohere | 13.92 | aa_slug=command-a-plus · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #112Nemotron 3.5 LightningNVIDIA | 13.64 | aa_slug=nemotron-3-5-lightning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #113Nemotron 3 SuperNVIDIA | 13.55 | aa_slug=nvidia-nemotron-3-super-120b-a12b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #114minicpm5-2bOpenBMB | 13.14 | aa_slug=minicpm5-2b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #115Qwen3 235B A22B Instruct 2507Qwen | 12.71 | aa_slug=qwen3-235b-a22b-instruct-2507-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #116gpt-oss-120bOpenAI | 12.35 | aa_slug=gpt-oss-120b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #117ling-3-0-tinyinclusionAI | 11.87 | aa_slug=ling-3-0-tiny · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #118Granite 4.2 8BIBM | 11.81 | aa_slug=granite-4-2-8b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #119Mercury 2Inception | 11.51 | aa_slug=mercury-2 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #120Mistral Small 4Mistral AI | 11.45 | aa_slug=mistral-small-4 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #121deepseek-r1-0120DeepSeek | 11.41 | aa_slug=deepseek-r1-0120 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #122o3 Mini HighOpenAI | 10.96 | aa_slug=o3-mini-high · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #123Trinity Large ThinkingArcee AI | 10.88 | aa_slug=trinity-large-thinking · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #124Qwen3 Coder NextQwen | 10.05 | aa_slug=qwen3-coder-next · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #125qwen3-30b-a3b-2507-reasoningAlibaba Group | 9.81 | aa_slug=qwen3-30b-a3b-2507-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #126DeepSeek V3 0324DeepSeek | 9.72 | aa_slug=deepseek-v3-0324 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #127Mistral Large 3Mistral AI | 9.71 | aa_slug=mistral-large-3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #128Devstral 2Mistral AI | 9.41 | aa_slug=devstral-2 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #129Llama 4 MaverickMeta AI | 9.3 | aa_slug=llama-4-maverick · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #130granite-4.2-3bIBM | 9.06 | aa_slug=granite-4-2-3b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #131gpt-oss-20bOpenAI | 9.04 | aa_slug=gpt-oss-20b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #132nvidia-nemotron-3-nano-30b-a3b-reasoningNVIDIA | 8.9 | aa_slug=nvidia-nemotron-3-nano-30b-a3b-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #133deepseek-v3DeepSeek | 8.49 | aa_slug=deepseek-v3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #134Devstral Small 2Mistral AI | 8.36 | aa_slug=devstral-small-2 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #135Solar Pro 3Upstage | 7.82 | aa_slug=solar-pro-3 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #136Mistral Small 3.1Mistral AI | 7.37 | aa_slug=mistral-small-3-1 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #137Qwen3 32BQwen | 7.22 | aa_slug=qwen3-32b-instruct-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #138Mistral Small 3.2Mistral AI | 6.96 | aa_slug=mistral-small-3-2 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #139Llama 4 ScoutMeta AI | 6.45 | aa_slug=llama-4-scout · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #140Qwen3 14BQwen | 6.39 | aa_slug=qwen3-14b-instruct-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #141celeris-1Celeris | 6.35 | aa_slug=celeris-1 · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #142Ministral 3 14BMistral AI | 6.04 | aa_slug=ministral-3-14b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #143Ministral 3 8BMistral AI | 5.48 | aa_slug=ministral-3-8b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #144Qwen3 8BQwen | 5.16 | aa_slug=qwen3-8b-instruct-reasoning · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #145Gemma 3 27BGoogle | 4.85 | aa_slug=gemma-3-27b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #146Ministral 3 3BMistral AI | 4.84 | aa_slug=ministral-3-3b · version=4.3 · estimated=false | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #147Gemma 3 12BGoogle | 3.75 | aa_slug=gemma-3-12b · 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 7 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 7 h agomedium
- Metric
- index
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 7 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 7 h agomedium
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 7 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 | 5 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.