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 10 min ago · first seen 11 Sept 2026

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

Score history · gemini-3-5-flash-medium 1 row

Not enough history to chart — a single observation (33.63 on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.

  • 33.63aa_slug=gemini-3-5-flash-medium · version=4.3 · estimated=true11 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-xhigh Anthropic Independent11 Sept 2026
  3. 51.2claude-fable-5-1-high Anthropic Independent11 Sept 2026
  4. 51.0gpt-6-astra-high OpenAI Independent11 Sept 2026
  5. 49.7gpt-6-astra-medium OpenAI Independent11 Sept 2026
  6. 45.1claude-opus-5-medium 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 638 models

Select models with +, then Compare.

Leaderboard
#ModelScoreTrustConfigurationvs leaderEvaluatedSourceActions
101qwen3-8-27b-mediumOpen weightsAlibaba Group27.8Independentversion4.3Comparable0.00obs. 11 Sept 2026artificialanalysis.aiT2History
102agnes-2-5-pro-alphaOpen weightsSapiens AI27.8Independentversion4.3Comparable-0.01obs. 11 Sept 2026artificialanalysis.aiT2History
103gpt-5-4-lowClosedOpenAI27.6Independentversion4.3Comparable-0.23obs. 11 Sept 2026artificialanalysis.aiT2History
104jt-4-1-flash-236b-a21bClosedChina Mobile27.3Independentversion4.3Comparable-0.52obs. 11 Sept 2026artificialanalysis.aiT2History
105grok-build-0-1-06-16ClosedSpaceXAI27.2Independentversion4.3Comparable-0.64obs. 11 Sept 2026artificialanalysis.aiT2History
106quasar-438bClosedMultiverse Computing27.1Independentversion4.3Comparable-0.68obs. 11 Sept 2026artificialanalysis.aiT2History
107Qwen3.6 PlusClosedQwen27.0Independentversion4.3Comparable-0.80obs. 11 Sept 2026artificialanalysis.aiT2History
108gpt-5-5-instant-06-26ClosedOpenAI26.8Independentversion4.3Comparable-1.01obs. 11 Sept 2026artificialanalysis.aiT2History
109GLM 5 TurboClosedZ.ai (Zhipu AI)26.6Independentversion4.3Comparable-1.21obs. 11 Sept 2026artificialanalysis.aiT2History
110gpt-5-2-mediumClosedOpenAI26.5Independentversion4.3Comparable-1.31obs. 11 Sept 2026artificialanalysis.aiT2History
111qwen3-8-27b-lowOpen weightsAlibaba Group26.5Independentversion4.3Comparable-1.32obs. 11 Sept 2026artificialanalysis.aiT2History
112GLM 5.1Open weightsZ.ai (Zhipu AI)26.4Independentversion4.3Comparable-1.36obs. 11 Sept 2026artificialanalysis.aiT2History
113MiMo-V2.5-ProOpen weightsXiaomi26.4Independentversion4.3Comparable-1.40obs. 11 Sept 2026artificialanalysis.aiT2History
114Claude Opus 4.6ClosedAnthropic · Claude26.4Independentversion4.3Comparable-1.46obs. 11 Sept 2026artificialanalysis.aiT2History
115Gemini 3 Flash PreviewClosedGoogle · Gemini26.3Independentversion4.3Comparable-1.48obs. 11 Sept 2026artificialanalysis.aiT2History
116Kimi K2.7 CodeOpen weightsMoonshot AI26.3Independentversion4.3Comparable-1.54obs. 11 Sept 2026artificialanalysis.aiT2History
117Inkling SmallOpen weightsThinking Machines26.1Independentversion4.3Comparable-1.72obs. 11 Sept 2026artificialanalysis.aiT2History
118Qwen 3.7 PlusClosedQwen25.8Independentversion4.3Comparable-1.99obs. 11 Sept 2026artificialanalysis.aiT2History
119Hy3Open weightsTencent25.8Independentversion4.3Comparable-2.04obs. 11 Sept 2026artificialanalysis.aiT2History
120Grok 4.20ClosedxAI · Grok25.7Independentversion4.3Comparable-2.15obs. 11 Sept 2026artificialanalysis.aiT2History
121InklingOpen weightsThinking Machines25.5Independentversion4.3Comparable-2.27obs. 11 Sept 2026artificialanalysis.aiT2History
122gpt-5-6-luna-mediumClosedOpenAI25.5Independentversion4.3Comparable-2.33obs. 11 Sept 2026artificialanalysis.aiT2History
123Grok 4.3ClosedxAI · Grok25.4Independentversion4.3Comparable-2.42obs. 11 Sept 2026artificialanalysis.aiT2History
124grok-4-20-0309ClosedSpaceXAI25.2Independentversion4.3Comparable-2.59obs. 11 Sept 2026artificialanalysis.aiT2History
125mimo-v2-omni-0327ClosedXiaomi25.1Independentversion4.3Comparable-2.69obs. 11 Sept 2026artificialanalysis.aiT2History
126Ling 3.0 FlashOpen weightsinclusionAI24.9Independentversion4.3Comparable-2.87obs. 11 Sept 2026artificialanalysis.aiT2History
127GPT-5-CodexClosedOpenAI24.9Independentversion4.3Comparable-2.93obs. 11 Sept 2026artificialanalysis.aiT2History
128deepseek-v4-flash-0420-highOpen weightsDeepSeek24.8Independentversion4.3Comparable-2.97obs. 11 Sept 2026artificialanalysis.aiT2History
129grok-4-3-mediumClosedSpaceXAI24.8Independentversion4.3Comparable-3.03obs. 11 Sept 2026artificialanalysis.aiT2History
130Ling 3.0 Flash VLOpen weightsinclusionAI24.8Independentversion4.3Comparable-3.04obs. 11 Sept 2026artificialanalysis.aiT2History
131claude-sonnet-5-lowClosedAnthropic24.7Independentversion4.3Comparable-3.07obs. 11 Sept 2026artificialanalysis.aiT2History
131gpt-5.1ClosedOpenAI24.7Independentversion4.3Comparable-3.07obs. 11 Sept 2026artificialanalysis.aiT2History
131solar-open2-250bOpen weightsUpstage24.7Independentversion4.3Comparable-3.07obs. 11 Sept 2026artificialanalysis.aiT2History
134Claude Sonnet 4.6ClosedAnthropic · Claude24.7Independentversion4.3Comparable-3.12obs. 11 Sept 2026artificialanalysis.aiT2History
135deepseek-v4-flash-0420Open weightsDeepSeek24.6Independentversion4.3Comparable-3.18obs. 11 Sept 2026artificialanalysis.aiT2History
136gpt-5.4-miniClosedOpenAI24.6Independentversion4.3Comparable-3.23obs. 11 Sept 2026artificialanalysis.aiT2History
137grok-4-3-lowClosedSpaceXAI24.3Independentversion4.3Comparable-3.51obs. 11 Sept 2026artificialanalysis.aiT2History
138glm-5-1-non-reasoningOpen weightsZ.ai (Zhipu AI)24.2Independentversion4.3Comparable-3.57obs. 11 Sept 2026artificialanalysis.aiT2History
139mimo-v2-omniClosedXiaomi23.9Independentversion4.3Comparable-3.89obs. 11 Sept 2026artificialanalysis.aiT2History
140gemini-3-5-flash-minimalClosedGoogle23.9Independentversion4.3Comparable-3.96obs. 11 Sept 2026artificialanalysis.aiT2History
141GPT-5.1-CodexClosedOpenAI23.7Independentversion4.3Comparable-4.11obs. 11 Sept 2026artificialanalysis.aiT2History
142Claude Opus 4.5ClosedAnthropic · Claude23.7Independentversion4.3Comparable-4.13obs. 11 Sept 2026artificialanalysis.aiT2History
143kimi-k2-6-non-reasoningOpen weightsMoonshot AI23.6Independentversion4.3Comparable-4.24obs. 11 Sept 2026artificialanalysis.aiT2History
144GLM 5V TurboClosedZ.ai (Zhipu AI)23.5Independentversion4.3Comparable-4.31obs. 11 Sept 2026artificialanalysis.aiT2History
145Kimi K2.5Open weightsMoonshot AI23.5Independentversion4.3Comparable-4.35obs. 11 Sept 2026artificialanalysis.aiT2History
146Nemotron 3 UltraOpen weightsNVIDIA23.4Independentversion4.3Comparable-4.40obs. 11 Sept 2026artificialanalysis.aiT2History
147claude-sonnet-4-6-non-reasoning-low-effortClosedAnthropic23.3Independentversion4.3Comparable-4.51obs. 11 Sept 2026artificialanalysis.aiT2History
148MiniMax M2.7Open weightsMiniMax23.2Independentversion4.3Comparable-4.59obs. 11 Sept 2026artificialanalysis.aiT2History
149gpt-5-5-non-reasoningClosedOpenAI23.2Independentversion4.3Comparable-4.64obs. 11 Sept 2026artificialanalysis.aiT2History
150gpt-5ClosedOpenAI23.0Independentversion4.3Comparable-4.83obs. 11 Sept 2026artificialanalysis.aiT2History
151Qwen3.5-27BOpen weightsQwen22.9Independentversion4.3Comparable-4.91obs. 11 Sept 2026artificialanalysis.aiT2History
152gpt-5 (medium)ClosedOpenAI22.9Independentversion4.3Comparable-4.94obs. 11 Sept 2026artificialanalysis.aiT2History
153claude-4-1-opus-thinkingClosedAnthropic22.9Independentversion4.3Comparable-4.96obs. 11 Sept 2026artificialanalysis.aiT2History
154MiniMax M2.5Open weightsMiniMax22.8Independentversion4.3Comparable-5.01obs. 11 Sept 2026artificialanalysis.aiT2History
155Hy3 previewOpen weightsTencent22.7Independentversion4.3Comparable-5.07obs. 11 Sept 2026artificialanalysis.aiT2History
156a-x-k2Open weightsSK Telecom22.7Independentversion4.3Comparable-5.11obs. 11 Sept 2026artificialanalysis.aiT2History
157gpt-5-5-instant-05-26ClosedOpenAI22.7Independentversion4.3Comparable-5.12obs. 11 Sept 2026artificialanalysis.aiT2History
158Gemini 3.5 Flash-LiteClosedGoogle · Gemini22.7Independentversion4.3Comparable-5.15obs. 11 Sept 2026artificialanalysis.aiT2History
159grok-4ClosedSpaceXAI22.5Independentversion4.3Comparable-5.32obs. 11 Sept 2026artificialanalysis.aiT2History
160mimo-v2-0206Open weightsXiaomi22.4Independentversion4.3Comparable-5.37obs. 11 Sept 2026artificialanalysis.aiT2History
161glm-5-2-non-reasoningOpen weightsZ.ai (Zhipu AI)22.4Independentversion4.3Comparable-5.38obs. 11 Sept 2026artificialanalysis.aiT2History
162qwen3-8-27b-non-reasoningOpen weightsAlibaba Group22.4Independentversion4.3Comparable-5.39obs. 11 Sept 2026artificialanalysis.aiT2History
163gemini-3-pro-lowClosedGoogle22.3Independentversion4.3Comparable-5.49obs. 11 Sept 2026artificialanalysis.aiT2History
164MiMo-V2.5Open weightsXiaomi22.3Independentversion4.3Comparable-5.51obs. 11 Sept 2026artificialanalysis.aiT2History
164gpt-5-6-terra-non-reasoningClosedOpenAI22.3Independentversion4.3Comparable-5.51obs. 11 Sept 2026artificialanalysis.aiT2History
166GLM 4.7Open weightsZ.ai (Zhipu AI)22.2Independentversion4.3Comparable-5.57obs. 11 Sept 2026artificialanalysis.aiT2History
167Kimi K2 ThinkingOpen weightsMoonshot AI22.0Independentversion4.3Comparable-5.79obs. 11 Sept 2026artificialanalysis.aiT2History
168Qwen3.6 27BOpen weightsQwen21.9Independentversion4.3Comparable-5.90obs. 11 Sept 2026artificialanalysis.aiT2History
169o3-proClosedOpenAI21.9Independentversion4.3Comparable-5.94obs. 11 Sept 2026artificialanalysis.aiT2History
170g9v3-39a5bOpen weightsAI9Stars21.8Independentversion4.3Comparable-5.98obs. 11 Sept 2026artificialanalysis.aiT2History
171glm-5-non-reasoningOpen weightsZ.ai (Zhipu AI)21.8Independentversion4.3Comparable-6.03obs. 11 Sept 2026artificialanalysis.aiT2History
172KAT-Coder-Pro V2ClosedKwaipilot21.7Independentversion4.3Comparable-6.11obs. 11 Sept 2026artificialanalysis.aiT2History
173gpt-5-6-luna-lowClosedOpenAI21.6Independentversion4.3Comparable-6.26obs. 11 Sept 2026artificialanalysis.aiT2History
174DeepSeek V3.2Open weightsDeepSeek · DeepSeek-V321.5Independentversion4.3Comparable-6.32obs. 11 Sept 2026artificialanalysis.aiT2History
175qwen3-5-397b-a17b-non-reasoningOpen weightsAlibaba Group21.4Independentversion4.3Comparable-6.37obs. 11 Sept 2026artificialanalysis.aiT2History
176Qwen3 Max ThinkingClosedQwen21.3Independentversion4.3Comparable-6.55obs. 11 Sept 2026artificialanalysis.aiT2History
177gpt-5.4-nanoClosedOpenAI21.2Independentversion4.3Comparable-6.57obs. 11 Sept 2026artificialanalysis.aiT2History
178claude-4-5-sonnet-thinkingClosedAnthropic21.2Independentversion4.3Comparable-6.63obs. 11 Sept 2026artificialanalysis.aiT2History
179MiniMax M2.1Open weightsMiniMax20.9Independentversion4.3Comparable-6.86obs. 11 Sept 2026artificialanalysis.aiT2History
180deepseek-v4-pro-0424-non-reasoningOpen weightsDeepSeek20.8Independentversion4.3Comparable-6.98obs. 11 Sept 2026artificialanalysis.aiT2History
181mimo-v2-flash-reasoningOpen weightsXiaomi20.8Independentversion4.3Comparable-6.99obs. 11 Sept 2026artificialanalysis.aiT2History
182gpt-5 (low)ClosedOpenAI20.8Independentversion4.3Comparable-7.02obs. 11 Sept 2026artificialanalysis.aiT2History
183Claude Opus 4ClosedAnthropic · Claude20.6Independentversion4.3Comparable-7.17obs. 11 Sept 2026artificialanalysis.aiT2History
184gpt-5-mini-mediumClosedOpenAI20.6Independentversion4.3Comparable-7.21obs. 11 Sept 2026artificialanalysis.aiT2History
185GPT-5.1-Codex MiniClosedOpenAI20.4Independentversion4.3Comparable-7.43obs. 11 Sept 2026artificialanalysis.aiT2History
185qwen3-5-omni-plusClosedAlibaba Group20.4Independentversion4.3Comparable-7.43obs. 11 Sept 2026artificialanalysis.aiT2History
187grok-4-1-fast-reasoningClosedSpaceXAI20.4Independentversion4.3Comparable-7.44obs. 11 Sept 2026artificialanalysis.aiT2History
188o3ClosedOpenAI20.2Independentversion4.3Comparable-7.61obs. 11 Sept 2026artificialanalysis.aiT2History
189gpt-5-4-nano-mediumClosedOpenAI20.0Independentversion4.3Comparable-7.80obs. 11 Sept 2026artificialanalysis.aiT2History
190qwen3-6-27b-non-reasoningOpen weightsAlibaba Group19.8Independentversion4.3Comparable-7.98obs. 11 Sept 2026artificialanalysis.aiT2History
191gpt-5-4-mini-mediumClosedOpenAI19.8Independentversion4.3Comparable-8.06obs. 11 Sept 2026artificialanalysis.aiT2History
192LongCat 2.0Open weightsMeituan19.7Independentversion4.3Comparable-8.12obs. 11 Sept 2026artificialanalysis.aiT2History
192k-exaone-2-0-0803Open weightsLG AI Research19.7Independentversion4.3Comparable-8.12obs. 11 Sept 2026artificialanalysis.aiT2History
194Step 3.7 FlashOpen weightsStepFun19.5Independentversion4.3Comparable-8.33obs. 11 Sept 2026artificialanalysis.aiT2History
195kimi-k2-5-non-reasoningOpen weightsMoonshot AI19.4Independentversion4.3Comparable-8.38obs. 11 Sept 2026artificialanalysis.aiT2History
196qwen3-5-27b-non-reasoningOpen weightsAlibaba Group19.4Independentversion4.3Comparable-8.44obs. 11 Sept 2026artificialanalysis.aiT2History
197Claude Sonnet 4.5ClosedAnthropic · Claude19.3Independentversion4.3Comparable-8.47obs. 11 Sept 2026artificialanalysis.aiT2History
198Qwen3.5-35B-A3BOpen weightsQwen19.3Independentversion4.3Comparable-8.48obs. 11 Sept 2026artificialanalysis.aiT2History
199Qwen3.5 397B A17BOpen weightsQwen19.1Independentversion4.3Comparable-8.70obs. 11 Sept 2026artificialanalysis.aiT2History
200claude-4-sonnet-thinkingClosedAnthropic18.9Independentversion4.3Comparable-8.89obs. 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 →