Skip to content
AI Atlas
BenchmarkActivecategory · compositefamily · artificial-analysis-intelligence-index · variant index

Artificial Analysis Intelligence Index

artificialanalysis.ai

composite of several evaluations run by Artificial Analysis

quality57

Updated 29 min ago · first seen 11 Sept 2026

Metric
index ↑
Current results
638
Models
477
Current leader
Claude Fable 5.1 53.4

Score history · gpt-5 4 rows

Not enough history to chart — 4 observations, all dated 11 Sept 2026. Rows under different configurations count separately; the list below shows each one.

  • 22.98aa_slug=gpt-5 · version=4.3 · estimated=true11 Sept 2026
  • 22.87aa_slug=gpt-5-medium · version=4.3 · estimated=true · aa_variant_slug=gpt-5-medium11 Sept 2026
  • 20.79aa_slug=gpt-5-low · version=4.3 · estimated=true · aa_variant_slug=gpt-5-low11 Sept 2026
  • 11.45aa_slug=gpt-5-minimal · version=4.3 · estimated=true · aa_variant_slug=gpt-5-minimal11 Sept 2026

Back to the leaderboard

Frontier over time · index

8 leader changes recorded, all dated 11 Sept 2026 — the frontier line needs at least two distinct dates. The corpus is young: every result was first observed on the same day, so leader changes will separate in time as sources are re-crawled.

  1. 53.4Claude Fable 5.1 Anthropic Independent11 Sept 2026
  2. 53.2Claude Fable 5.1 Anthropic Independent11 Sept 2026
  3. 51.2Claude Fable 5.1 Anthropic Independent11 Sept 2026
  4. 51.0gpt-6-astra OpenAI Independent11 Sept 2026
  5. 49.7gpt-6-astra OpenAI Independent11 Sept 2026
  6. 45.1Claude Opus 5 Anthropic Independent11 Sept 2026
  7. 14.6grok-3-mini-reasoning SpaceXAI Independent11 Sept 2026
  8. 5.71llama-2-chat-7b Meta AI Independent11 Sept 2026

Includes closed rows (history). A point is emitted whenever a result beats every earlier result of the same group, ordered by evaluated_at when the source publishes it, else observed_at.

Leaderboard 477 models

Select models with +, then Compare.

Leaderboard
#ModelScoreTrustConfigurationvs leaderEvaluatedSourceActions
101mimo-v2-0206Open weightsXiaomi22.4Independentversion4.3Comparable0.00obs. 11 Sept 2026artificialanalysis.aiT2History
102MiMo-V2.5Open weightsXiaomi22.3Independentversion4.3Comparable-0.14obs. 11 Sept 2026artificialanalysis.aiT2History
103GLM 4.7Open weightsZ.ai (Zhipu AI) · GLM4.7 · best of 2 rows22.2Independentversion4.3Comparable-0.20obs. 11 Sept 2026artificialanalysis.aiT2History
104Kimi K2 ThinkingOpen weightsMoonshot AI · Kimi22.0Independentversion4.3Comparable-0.42obs. 11 Sept 2026artificialanalysis.aiT2History
105Qwen3.6 27BOpen weightsQwen · Qwen3.6 · best of 2 rows21.9Independentversion4.3Comparable-0.53obs. 11 Sept 2026artificialanalysis.aiT2History
106o3-proClosedOpenAI · OpenAI o-series21.9Independentversion4.3Comparable-0.57obs. 11 Sept 2026artificialanalysis.aiT2History
107g9v3-39a5bOpen weightsAI9Stars21.8Independentversion4.3Comparable-0.61obs. 11 Sept 2026artificialanalysis.aiT2History
108KAT-Coder-Pro V2ClosedKwaipilot21.7Independentversion4.3Comparable-0.74obs. 11 Sept 2026artificialanalysis.aiT2History
109DeepSeek V3.2Open weightsDeepSeek · DeepSeek-V321.5Independentversion4.3Comparable-0.95obs. 11 Sept 2026artificialanalysis.aiT2History
110Qwen3.5 397B A17BOpen weightsQwen · Qwen3.5 · best of 2 rows21.4Independentreasoningoffversion4.3Partially comparable-1.00obs. 11 Sept 2026artificialanalysis.aiT2History
111Qwen3 MaxClosedQwen · Qwen3 · best of 2 rows21.3Independentreasoningonversion4.3Partially comparable-1.18obs. 11 Sept 2026artificialanalysis.aiT2History
112gpt-5.4-nanoClosedOpenAI · GPT 5.4 · best of 3 rows21.2Independentversion4.3Comparable-1.20obs. 11 Sept 2026artificialanalysis.aiT2History
113Claude Sonnet 4.5ClosedAnthropic · Claude · best of 2 rows21.2Independentreasoningonversion4.3Partially comparable-1.26obs. 11 Sept 2026artificialanalysis.aiT2History
114MiniMax M2.1Open weightsMiniMax · MiniMax20.9Independentversion4.3Comparable-1.49obs. 11 Sept 2026artificialanalysis.aiT2History
115deepseek-v4-pro-0424-non-reasoningOpen weightsDeepSeek · DeepSeek20.8Independentversion4.3Comparable-1.61obs. 11 Sept 2026artificialanalysis.aiT2History
116mimo-v2-flashOpen weightsXiaomi · best of 2 rows20.8Independentreasoningonversion4.3Partially comparable-1.62obs. 11 Sept 2026artificialanalysis.aiT2History
117Claude Opus 4ClosedAnthropic · Claude20.6Independentversion4.3Comparable-1.80obs. 11 Sept 2026artificialanalysis.aiT2History
118gpt-5-miniClosedOpenAI · GPT 5 · best of 3 rows20.6Independentreasoning_effortmediumversion4.3Partially comparable-1.84obs. 11 Sept 2026artificialanalysis.aiT2History
119GPT-5.1-Codex MiniClosedOpenAI · GPT 5.120.4Independentversion4.3Comparable-2.06obs. 11 Sept 2026artificialanalysis.aiT2History
119qwen3-5-omni-plusClosedAlibaba Group · Qwen3.520.4Independentversion4.3Comparable-2.06obs. 11 Sept 2026artificialanalysis.aiT2History
121grok-4-1-fastClosedSpaceXAI · Grok 4.1 · best of 2 rows20.4Independentreasoningonversion4.3Partially comparable-2.07obs. 11 Sept 2026artificialanalysis.aiT2History
122o3ClosedOpenAI · OpenAI o-series20.2Independentversion4.3Comparable-2.24obs. 11 Sept 2026artificialanalysis.aiT2History
123LongCat 2.0Open weightsMeituan19.7Independentversion4.3Comparable-2.75obs. 11 Sept 2026artificialanalysis.aiT2History
123k-exaone-2-0-0803Open weightsLG AI Research · EXAONE 2.019.7Independentversion4.3Comparable-2.75obs. 11 Sept 2026artificialanalysis.aiT2History
125Step 3.7 FlashOpen weightsStepFun · Step3.719.5Independentversion4.3Comparable-2.96obs. 11 Sept 2026artificialanalysis.aiT2History
126Qwen3.5-35B-A3BOpen weightsQwen · Qwen3.5 · best of 2 rows19.3Independentversion4.3Comparable-3.11obs. 11 Sept 2026artificialanalysis.aiT2History
127Claude Sonnet 4ClosedAnthropic · Claude · best of 2 rows18.9Independentreasoningonversion4.3Partially comparable-3.52obs. 11 Sept 2026artificialanalysis.aiT2History
128deepseek-v4-flash-0420-non-reasoningOpen weightsDeepSeek · DeepSeek18.9Independentversion4.3Comparable-3.56obs. 11 Sept 2026artificialanalysis.aiT2History
129Qwen3.6 35B A3BOpen weightsQwen · Qwen3.6 · best of 2 rows18.8Independentversion4.3Comparable-3.63obs. 11 Sept 2026artificialanalysis.aiT2History
130jt-35b-flashClosedChina Mobile18.7Independentversion4.3Comparable-3.78obs. 11 Sept 2026artificialanalysis.aiT2History
131MiniMax M2Open weightsMiniMax · MiniMax18.6Independentversion4.3Comparable-3.81obs. 11 Sept 2026artificialanalysis.aiT2History
132kat-coder-pro-v1ClosedKwaiKAT18.6Independentversion4.3Comparable-3.85obs. 11 Sept 2026artificialanalysis.aiT2History
133GLM 4.6Open weightsZ.ai (Zhipu AI) · GLM4.6 · best of 2 rows18.5Independentreasoningonversion4.3Partially comparable-3.91obs. 11 Sept 2026artificialanalysis.aiT2History
134Muse Glimmer 30BOpen weightsMeta AI18.1Independentversion4.3Comparable-4.37obs. 11 Sept 2026artificialanalysis.aiT2History
135grok-4-fastClosedSpaceXAI · Grok 4 · best of 2 rows17.9Independentreasoningonversion4.3Partially comparable-4.50obs. 11 Sept 2026artificialanalysis.aiT2History
136gemini-3-flashClosedGoogle · Gemini 317.9Independentversion4.3Comparable-4.51obs. 11 Sept 2026artificialanalysis.aiT2History
137Qwen3.5-122B-A10BOpen weightsQwen · Qwen3.5 · best of 2 rows17.8Independentreasoningoffversion4.3Partially comparable-4.69obs. 11 Sept 2026artificialanalysis.aiT2History
138Claude 3.7 SonnetClosedAnthropic · Claude · best of 2 rows17.7Independentreasoningonversion4.3Partially comparable-4.73obs. 11 Sept 2026artificialanalysis.aiT2History
139Claude Haiku 4.5ClosedAnthropic · Claude · best of 2 rows17.6Independentreasoningonversion4.3Partially comparable-4.85obs. 11 Sept 2026artificialanalysis.aiT2History
140ring-2-6-1tOpen weightsinclusionAI17.3Independentversion4.3Comparable-5.16obs. 11 Sept 2026artificialanalysis.aiT2History
141ling-2-6-1tOpen weightsinclusionAI17Independentversion4.3Comparable-5.44obs. 11 Sept 2026artificialanalysis.aiT2History
142Step 3.5 FlashOpen weightsStepFun · Step3.5 · best of 2 rows17.0Independentversion4.3Comparable-5.48obs. 11 Sept 2026artificialanalysis.aiT2History
143doubao-seed-codeClosedByteDance · Seed16.9Independentversion4.3Comparable-5.49obs. 11 Sept 2026artificialanalysis.aiT2History
144Gemma 4 26B A4BOpen weightsGoogle · Gemma 4 · best of 2 rows16.7Independentversion4.3Comparable-5.77obs. 11 Sept 2026artificialanalysis.aiT2History
145Gemini 2.5 ProClosedGoogle · Gemini 2.516.7Independentversion4.3Comparable-5.78obs. 11 Sept 2026artificialanalysis.aiT2History
146o4-miniClosedOpenAI · OpenAI o-series16.6Independentversion4.3Comparable-5.79obs. 11 Sept 2026artificialanalysis.aiT2History
147claude-4-opusClosedAnthropic · Claude 416.6Independentversion4.3Comparable-5.83obs. 11 Sept 2026artificialanalysis.aiT2History
148DeepSeek V3.2 ExpOpen weightsDeepSeek · DeepSeek-V316.6Independentversion4.3Comparable-5.86obs. 11 Sept 2026artificialanalysis.aiT2History
149qwen3-max-thinking-previewClosedAlibaba Group · Qwen316.3Independentversion4.3Comparable-6.15obs. 11 Sept 2026artificialanalysis.aiT2History
150DeepSeek V3Open weightsDeepSeek · DeepSeek · best of 2 rows16.0Independentversion4.3Comparable-6.40obs. 11 Sept 2026artificialanalysis.aiT2History
151Gemini 3.1 Flash-Lite PreviewClosedGoogle · Gemini 3.116.0Independentversion4.3Comparable-6.41obs. 11 Sept 2026artificialanalysis.aiT2History
152gemini-2-5-flash-preview-09-2025ClosedGoogle · Gemini 2.5 · best of 2 rows15.5Independentreasoningonversion4.3Partially comparable-6.97obs. 11 Sept 2026artificialanalysis.aiT2History
153Gemma 4 31BOpen weightsGoogle · Gemma 4 · best of 2 rows15.4Independentversion4.3Comparable-7.02obs. 11 Sept 2026artificialanalysis.aiT2History
154DeepSeek V3.1 TerminusOpen weightsDeepSeek · DeepSeek · best of 2 rows15.4Independentreasoningonversion4.3Partially comparable-7.04obs. 11 Sept 2026artificialanalysis.aiT2History
155Kimi K2 0905Open weightsMoonshot AI · Kimi15.3Independentversion4.3Comparable-7.15obs. 11 Sept 2026artificialanalysis.aiT2History
156o1ClosedOpenAI · OpenAI o-series15.2Independentversion4.3Comparable-7.21obs. 11 Sept 2026artificialanalysis.aiT2History
157gemini-2-5-pro-03-25ClosedGoogle · Gemini 2.515.0Independentversion4.3Comparable-7.48obs. 11 Sept 2026artificialanalysis.aiT2History
158Mistral Medium 3.5Open weightsMistral AI · Mistral14.9Independentversion4.3Comparable-7.55obs. 11 Sept 2026artificialanalysis.aiT2History
159GLM 4.7 FlashOpen weightsZ.ai (Zhipu AI) · GLM4.7 · best of 2 rows14.9Independentversion4.3Comparable-7.57obs. 11 Sept 2026artificialanalysis.aiT2History
160granite-4.2-30bOpen weightsIBM · Granite 4.214.8Independentversion4.3Comparable-7.61obs. 11 Sept 2026artificialanalysis.aiT2History
161grok-3-mini-reasoningClosedSpaceXAI · Grok 314.6Independentversion4.3Comparable-7.82obs. 11 Sept 2026artificialanalysis.aiT2History
162gemini-2-5-pro-05-06ClosedGoogle · Gemini 2.514.5Independentversion4.3Comparable-7.92obs. 11 Sept 2026artificialanalysis.aiT2History
163deepseek-v3-2-specialeOpen weightsDeepSeek · DeepSeek14.5Independentversion4.3Comparable-7.98obs. 11 Sept 2026artificialanalysis.aiT2History
164k-exaoneOpen weightsLG AI Research · EXAONE · best of 2 rows14.4Independentversion4.3Comparable-8.07obs. 11 Sept 2026artificialanalysis.aiT2History
165ernie-5-0-thinking-previewClosedBaidu · ERNIE 5.014.3Independentversion4.3Comparable-8.18obs. 11 Sept 2026artificialanalysis.aiT2History
166grok-4.20-0309-non-reasoningClosedxAI · Grok14.2Independentversion4.3Comparable-8.24obs. 11 Sept 2026artificialanalysis.aiT2History
167gemma-4-12BOpen weightsGoogle · Gemma 4 · best of 2 rows14.2Independentversion4.3Comparable-8.26obs. 11 Sept 2026artificialanalysis.aiT2History
168nova-2-0-proClosedAmazon Web Services · Nova 2.0 · best of 3 rows14.2Independentreasoningonreasoning_effortmediumversion4.3Partially comparable-8.28obs. 11 Sept 2026artificialanalysis.aiT2History
169Grok Build 0.1ClosedxAI · Grok14.1Independentversion4.3Comparable-8.38obs. 11 Sept 2026artificialanalysis.aiT2History
170command-a-plusOpen weightsCohere · Command13.9Independentversion4.3Comparable-8.52obs. 11 Sept 2026artificialanalysis.aiT2History
171deepseek-v3-2-0925Open weightsDeepSeek · DeepSeek13.9Independentversion4.3Comparable-8.56obs. 11 Sept 2026artificialanalysis.aiT2History
172apriel-v1-5-15b-thinkerOpen weightsServiceNow13.8Independentversion4.3Comparable-8.62obs. 11 Sept 2026artificialanalysis.aiT2History
173DeepSeek V3.1Open weightsDeepSeek · DeepSeek-V3 · best of 2 rows13.7Independentversion4.3Comparable-8.73obs. 11 Sept 2026artificialanalysis.aiT2History
174Qwen3.5-9BOpen weightsQwen · Qwen3.5 · best of 2 rows13.7Independentversion4.3Comparable-8.79obs. 11 Sept 2026artificialanalysis.aiT2History
174nova-2-0-omniClosedAmazon Web Services · Nova 2.0 · best of 3 rows13.7Independentreasoningonreasoning_effortmediumversion4.3Partially comparable-8.79obs. 11 Sept 2026artificialanalysis.aiT2History
176NVIDIA Nemotron 3.5 Lightning 30B A3BOpen weightsNVIDIA · Nemotron 3.513.6Independentversion4.3Comparable-8.80obs. 11 Sept 2026artificialanalysis.aiT2History
177Nemotron 3 SuperOpen weightsNVIDIA · Nemotron 313.6Independentversion4.3Comparable-8.89obs. 11 Sept 2026artificialanalysis.aiT2History
178Qwen3 VL 235B A22B InstructOpen weightsQwen · Qwen3 · best of 2 rows13.4Independentreasoningonversion4.3Partially comparable-9.00obs. 11 Sept 2026artificialanalysis.aiT2History
179apriel-v1-6-15b-thinkerOpen weightsServiceNow13.4Independentversion4.3Comparable-9.04obs. 11 Sept 2026artificialanalysis.aiT2History
180nova-2-0-liteClosedAmazon Web Services · Nova 2.0 · best of 4 rows13.4Independentreasoningonversion4.3Partially comparable-9.07obs. 11 Sept 2026artificialanalysis.aiT2History
181exaone-4-5-33bOpen weightsLG AI Research · EXAONE 4.513.2Independentversion4.3Comparable-9.23obs. 11 Sept 2026artificialanalysis.aiT2History
182minicpm5-2bOpen weightsOpenBMB13.1Independentversion4.3Comparable-9.30obs. 11 Sept 2026artificialanalysis.aiT2History
183Qwen3.5-4BOpen weightsQwen · Qwen3.5 · best of 2 rows13.1Independentversion4.3Comparable-9.32obs. 11 Sept 2026artificialanalysis.aiT2History
183deepseek-r1Open weightsDeepSeek · DeepSeek-R113.1Independentversion4.3Comparable-9.32obs. 11 Sept 2026artificialanalysis.aiT2History
185Gemini 2.5 FlashClosedGoogle · Gemini 2.5 · best of 2 rows13.1Independentreasoningonversion4.3Partially comparable-9.33obs. 11 Sept 2026artificialanalysis.aiT2History
186gpt-5-nanoClosedOpenAI · GPT 5 · best of 3 rows13.0Independentversion4.3Comparable-9.45obs. 11 Sept 2026artificialanalysis.aiT2History
187North Mini Code (free)Open weightsCohere12.8Independentversion4.3Comparable-9.60obs. 11 Sept 2026artificialanalysis.aiT2History
188GLM 4.5Open weightsZ.ai (Zhipu AI) · GLM4.512.8Independentversion4.3Comparable-9.67obs. 11 Sept 2026artificialanalysis.aiT2History
189Kimi K2 0711Open weightsMoonshot AI · Kimi12.7Independentversion4.3Comparable-9.72obs. 11 Sept 2026artificialanalysis.aiT2History
190Qwen3 235B A22B Instruct 2507Open weightsQwen · Qwen3 · best of 2 rows12.7Independentversion4.3Comparable-9.73obs. 11 Sept 2026artificialanalysis.aiT2History
191gpt-4.1ClosedOpenAI · GPT 4.112.7Independentversion4.3Comparable-9.75obs. 11 Sept 2026artificialanalysis.aiT2History
192qwen3-max-previewClosedAlibaba Group · Qwen312.6Independentversion4.3Comparable-9.85obs. 11 Sept 2026artificialanalysis.aiT2History
193o3-miniClosedOpenAI · OpenAI o-series · best of 2 rows12.5Independentversion4.3Comparable-9.97obs. 11 Sept 2026artificialanalysis.aiT2History
193qwen3-5-omni-flashClosedAlibaba Group · Qwen3.512.5Independentversion4.3Comparable-9.97obs. 11 Sept 2026artificialanalysis.aiT2History
195o1-proClosedOpenAI · OpenAI o-series12.4Independentversion4.3Comparable-10.0obs. 11 Sept 2026artificialanalysis.aiT2History
196gpt-oss-120bOpen weightsOpenAI · gpt-oss · best of 2 rows12.3Independentversion4.3Comparable-10.1obs. 11 Sept 2026artificialanalysis.aiT2History
197jt-miniClosedChina Mobile12.2Independentversion4.3Comparable-10.2obs. 11 Sept 2026artificialanalysis.aiT2History
198grok-3ClosedSpaceXAI · Grok 3 · best of 2 rows12.1Independentversion4.3Comparable-10.3obs. 11 Sept 2026artificialanalysis.aiT2History
199Seed-OSS-36B-InstructOpen weightsByteDance · Seed12.1Independentversion4.3Comparable-10.3obs. 11 Sept 2026artificialanalysis.aiT2History
200qwen3-coder-480b-a35b-instructOpen weightsAlibaba Group · Qwen3-Coder11.9Independentversion4.3Comparable-10.5obs. 11 Sept 2026artificialanalysis.aiT2History

One row per canonical model — its best current row inside this comparability group (effort variants are folded into the model). Bars are relative to the page's best score. “vs leader” reads comparability: partially comparable = same task, conditions differ (reasoning effort, temperature, judge). Rules →