BenchmarkActivecategory · compositefamily · artificial-analysis-intelligence-index · variant index
Artificial Analysis Intelligence Index
composite of several evaluations run by Artificial Analysis
data quality57
Updated 2 h ago · first seen 11 Sept 2026
- Metric
- index ↑
- Current results
- 1,272
- Models
- 477
- Current leader
- Claude Fable 5.1 53.4
Score history · gpt-5.4 6 rows
- gpt-5.4
- 18.16aa_slug=gpt-5-4-non-reasoning · version=4.3 · estimated=true · reasoning=off12 Sept 2026
- 27.58aa_slug=gpt-5-4-low · version=4.3 · estimated=true · reasoning_effort=low12 Sept 2026
- 38.98aa_slug=gpt-5-4 · version=4.3 · estimated=true · reasoning_effort=xhigh12 Sept 2026
- 18.16aa_slug=gpt-5-4-non-reasoning · version=4.3 · estimated=true · reasoning=off11 Sept 2026
- 27.58aa_slug=gpt-5-4-low · version=4.3 · estimated=true · aa_variant_slug=gpt-5-4-low11 Sept 2026
- 38.98aa_slug=gpt-5-4 · version=4.3 · estimated=true11 Sept 2026
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.
- 53.4Claude Fable 5.1 Anthropic Independent11 Sept 2026
- 53.2Claude Fable 5.1 Anthropic Independent11 Sept 2026
- 51.2Claude Fable 5.1 Anthropic Independent11 Sept 2026
- 51.0gpt-6-astra OpenAI Independent11 Sept 2026
- 49.7gpt-6-astra OpenAI Independent11 Sept 2026
- 45.1Claude Opus 5 Anthropic Independent11 Sept 2026
- 14.6grok-3-mini-reasoning SpaceXAI Independent11 Sept 2026
- 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 · trust independent-evaluator
Select models with +, then Compare.
| # | Model | Score | Trust | Configuration | vs leader | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|---|---|
| 101 | grok-4ClosedSpaceXAI · Grok 4 · best of 2 rows | 22.5 | Independent | reasoningonversion4.3 | Partially comparable0.00 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 102 | mimo-v2-0206Open weightsXiaomi · best of 2 rows | 22.4 | Independent | reasoningonversion4.3 | Partially comparable-0.05 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 103 | MiMo-V2.5Open weightsXiaomi · best of 2 rows | 22.3 | Independent | reasoningonversion4.3 | Partially comparable-0.19 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 104 | GLM 4.7Open weightsZ.ai (Zhipu AI) · GLM4.7 · best of 4 rows | 22.2 | Independent | reasoningonversion4.3 | Partially comparable-0.25 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 105 | Kimi K2 ThinkingOpen weightsMoonshot AI · Kimi · best of 2 rows | 22.0 | Independent | reasoningonversion4.3 | Partially comparable-0.47 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 106 | Qwen3.6 27BOpen weightsQwen · Qwen3.6 · best of 4 rows | 21.9 | Independent | reasoningonversion4.3 | Partially comparable-0.58 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 107 | o3-proClosedOpenAI · OpenAI o-series · best of 2 rows | 21.9 | Independent | reasoningonversion4.3 | Partially comparable-0.62 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 108 | g9v3-39a5bOpen weightsAI9Stars · best of 2 rows | 21.8 | Independent | reasoningonversion4.3 | Partially comparable-0.66 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 109 | KAT-Coder-Pro V2ClosedKwaipilot · best of 2 rows | 21.7 | Independent | reasoningoffversion4.3 | Partially comparable-0.79 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 110 | DeepSeek V3Open weightsDeepSeek · DeepSeek · best of 5 rows | 21.5 | Independent | reasoningonversion4.3 | Partially comparable-1.00 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 110 | DeepSeek V3.2Open weightsDeepSeek · DeepSeek-V3 | 21.5 | Independent | version4.3 | Partially comparable-1.00 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 112 | Qwen3.5 397B A17BOpen weightsQwen · Qwen3.5 · best of 4 rows | 21.4 | Independent | reasoningoffversion4.3 | Partially comparable-1.05 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 113 | Qwen3 MaxClosedQwen · Qwen3 · best of 4 rows | 21.3 | Independent | reasoningonversion4.3 | Partially comparable-1.23 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 114 | gpt-5.4-nanoClosedOpenAI · GPT 5.4 · best of 6 rows | 21.2 | Independent | reasoning_effortxhighversion4.3 | Partially comparable-1.25 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 115 | Claude Sonnet 4.5ClosedAnthropic · Claude · best of 4 rows | 21.2 | Independent | reasoningonversion4.3 | Partially comparable-1.31 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 116 | MiniMax M2.1Open weightsMiniMax · MiniMax · best of 2 rows | 20.9 | Independent | reasoningonversion4.3 | Partially comparable-1.54 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 117 | deepseek-v4-pro-0424-non-reasoningOpen weightsDeepSeek · DeepSeek | 20.8 | Independent | version4.3 | Partially comparable-1.66 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 118 | mimo-v2-flashOpen weightsXiaomi · best of 4 rows | 20.8 | Independent | reasoningonversion4.3 | Partially comparable-1.67 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 119 | Claude Opus 4ClosedAnthropic · Claude | 20.6 | Independent | version4.3 | Partially comparable-1.85 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 119 | claude-4-opusClosedAnthropic · Claude 4 · best of 3 rows | 20.6 | Independent | reasoningonversion4.3 | Partially comparable-1.85 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 121 | gpt-5-miniClosedOpenAI · GPT 5 · best of 6 rows | 20.6 | Independent | reasoning_effortmediumversion4.3 | Partially comparable-1.89 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 122 | GPT-5.1-Codex MiniClosedOpenAI · GPT 5.1 · best of 2 rows | 20.4 | Independent | reasoning_efforthighversion4.3 | Partially comparable-2.11 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 122 | qwen3-5-omni-plusClosedAlibaba Group · Qwen3.5 · best of 2 rows | 20.4 | Independent | reasoningoffversion4.3 | Partially comparable-2.11 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 124 | grok-4-1-fastClosedSpaceXAI · Grok 4.1 · best of 4 rows | 20.4 | Independent | reasoningonversion4.3 | Partially comparable-2.12 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 125 | o3ClosedOpenAI · OpenAI o-series · best of 2 rows | 20.2 | Independent | reasoningonversion4.3 | Partially comparable-2.29 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 126 | LongCat 2.0Open weightsMeituan · best of 2 rows | 19.7 | Independent | reasoningonversion4.3 | Partially comparable-2.80 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 126 | k-exaone-2-0-0803Open weightsLG AI Research · EXAONE 2.0 · best of 2 rows | 19.7 | Independent | reasoningonversion4.3 | Partially comparable-2.80 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 128 | Step 3.7 FlashOpen weightsStepFun · Step3.7 · best of 2 rows | 19.5 | Independent | reasoningonversion4.3 | Partially comparable-3.01 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 129 | Qwen3.5-35B-A3BOpen weightsQwen · Qwen3.5 · best of 4 rows | 19.3 | Independent | reasoningonversion4.3 | Partially comparable-3.16 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 130 | Claude Sonnet 4ClosedAnthropic · Claude · best of 4 rows | 18.9 | Independent | reasoningonversion4.3 | Partially comparable-3.57 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 131 | deepseek-v4-flash-0420-non-reasoningOpen weightsDeepSeek · DeepSeek | 18.9 | Independent | version4.3 | Partially comparable-3.61 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 132 | Qwen3.6 35B A3BOpen weightsQwen · Qwen3.6 · best of 4 rows | 18.8 | Independent | reasoningonversion4.3 | Partially comparable-3.68 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 133 | jt-35b-flashClosedChina Mobile · best of 2 rows | 18.7 | Independent | reasoningoffversion4.3 | Partially comparable-3.83 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 134 | MiniMax M2Open weightsMiniMax · MiniMax · best of 2 rows | 18.6 | Independent | reasoningonversion4.3 | Partially comparable-3.86 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 135 | kat-coder-pro-v1ClosedKwaiKAT · best of 2 rows | 18.6 | Independent | reasoningoffversion4.3 | Partially comparable-3.90 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 136 | GLM 4.6Open weightsZ.ai (Zhipu AI) · GLM4.6 · best of 4 rows | 18.5 | Independent | reasoningonversion4.3 | Partially comparable-3.96 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 137 | Muse Glimmer 30BOpen weightsMeta AI · best of 2 rows | 18.1 | Independent | reasoning_efforthighversion4.3 | Partially comparable-4.42 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 138 | grok-4-fastClosedSpaceXAI · Grok 4 · best of 4 rows | 17.9 | Independent | reasoningonversion4.3 | Partially comparable-4.55 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 139 | Qwen3.5-122B-A10BOpen weightsQwen · Qwen3.5 · best of 4 rows | 17.8 | Independent | reasoningoffversion4.3 | Partially comparable-4.74 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 140 | Claude 3.7 SonnetClosedAnthropic · Claude · best of 4 rows | 17.7 | Independent | reasoningonversion4.3 | Partially comparable-4.78 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 141 | Claude Haiku 4.5ClosedAnthropic · Claude · best of 4 rows | 17.6 | Independent | reasoningonversion4.3 | Partially comparable-4.90 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 142 | ring-2-6-1tOpen weightsinclusionAI · best of 2 rows | 17.3 | Independent | reasoningonversion4.3 | Partially comparable-5.21 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 143 | ling-2-6-1tOpen weightsinclusionAI · best of 2 rows | 17 | Independent | reasoningoffversion4.3 | Partially comparable-5.49 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 144 | Step 3.5 FlashOpen weightsStepFun · Step3.5 · best of 4 rows | 17.0 | Independent | reasoningonversion4.3 | Partially comparable-5.53 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 145 | doubao-seed-codeClosedByteDance · Seed · best of 2 rows | 16.9 | Independent | reasoningonversion4.3 | Partially comparable-5.54 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 146 | Gemma 4 26B A4BOpen weightsGoogle · Gemma 4 · best of 4 rows | 16.7 | Independent | reasoningonversion4.3 | Partially comparable-5.82 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 147 | Gemini 2.5 ProClosedGoogle · Gemini 2.5 · best of 2 rows | 16.7 | Independent | reasoningonversion4.3 | Partially comparable-5.83 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 148 | o4-miniClosedOpenAI · OpenAI o-series · best of 2 rows | 16.6 | Independent | reasoning_efforthighversion4.3 | Partially comparable-5.84 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 149 | DeepSeek V3.2 ExpOpen weightsDeepSeek · DeepSeek-V3 · best of 3 rows | 16.6 | Independent | reasoningonversion4.3 | Partially comparable-5.91 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 150 | qwen3-max-thinking-previewClosedAlibaba Group · Qwen3 · best of 2 rows | 16.3 | Independent | reasoningonversion4.3 | Partially comparable-6.20 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 151 | Gemini 3.1 Flash-Lite PreviewClosedGoogle · Gemini 3.1 · best of 2 rows | 16.0 | Independent | reasoningonversion4.3 | Partially comparable-6.46 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 152 | gemini-2-5-flash-preview-09-2025ClosedGoogle · Gemini 2.5 · best of 6 rows | 15.5 | Independent | reasoningonversion4.3 | Partially comparable-7.02 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 153 | Gemma 4 31BOpen weightsGoogle · Gemma 4 · best of 4 rows | 15.4 | Independent | reasoningonversion4.3 | Partially comparable-7.07 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 154 | DeepSeek V3.1 TerminusOpen weightsDeepSeek · DeepSeek · best of 4 rows | 15.4 | Independent | reasoningonversion4.3 | Partially comparable-7.09 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 155 | Kimi K2 0905Open weightsMoonshot AI · Kimi · best of 2 rows | 15.3 | Independent | reasoningoffversion4.3 | Partially comparable-7.20 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 156 | o1ClosedOpenAI · OpenAI o-series · best of 2 rows | 15.2 | Independent | reasoningonversion4.3 | Partially comparable-7.26 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 157 | gemini-2-5-pro-03-25ClosedGoogle · Gemini 2.5 · best of 2 rows | 15.0 | Independent | reasoningonversion4.3 | Partially comparable-7.53 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 158 | Mistral Medium 3.5Open weightsMistral AI · Mistral · best of 2 rows | 14.9 | Independent | reasoningonversion4.3 | Partially comparable-7.60 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 159 | GLM 4.7 FlashOpen weightsZ.ai (Zhipu AI) · GLM4.7 · best of 4 rows | 14.9 | Independent | reasoningonversion4.3 | Partially comparable-7.62 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 160 | granite-4.2-30bOpen weightsIBM · Granite 4.2 · best of 2 rows | 14.8 | Independent | reasoningonversion4.3 | Partially comparable-7.66 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 161 | grok-3-mini-reasoningClosedSpaceXAI · Grok 3 · best of 2 rows | 14.6 | Independent | reasoningonreasoning_efforthighversion4.3 | Partially comparable-7.87 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 162 | gemini-2-5-pro-05-06ClosedGoogle · Gemini 2.5 · best of 2 rows | 14.5 | Independent | reasoningonversion4.3 | Partially comparable-7.97 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 163 | deepseek-v3-2-specialeOpen weightsDeepSeek · DeepSeek · best of 2 rows | 14.5 | Independent | reasoningonversion4.3 | Partially comparable-8.03 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 164 | k-exaoneOpen weightsLG AI Research · EXAONE · best of 4 rows | 14.4 | Independent | reasoningonversion4.3 | Partially comparable-8.12 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 165 | ernie-5-0-thinking-previewClosedBaidu · ERNIE 5.0 · best of 2 rows | 14.3 | Independent | reasoningonversion4.3 | Partially comparable-8.23 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 166 | grok-4.20-0309-non-reasoningClosedxAI · Grok | 14.2 | Independent | version4.3 | Partially comparable-8.29 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 167 | gemma-4-12BOpen weightsGoogle · Gemma 4 · best of 4 rows | 14.2 | Independent | reasoningonversion4.3 | Partially comparable-8.31 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 168 | nova-2-0-proClosedAmazon Web Services · Nova 2.0 · best of 6 rows | 14.2 | Independent | reasoningonreasoning_effortmediumversion4.3 | Partially comparable-8.33 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 169 | Grok Build 0.1ClosedxAI · Grok · best of 2 rows | 14.1 | Independent | reasoningonversion4.3 | Partially comparable-8.43 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 170 | command-a-plusOpen weightsCohere · Command · best of 2 rows | 13.9 | Independent | reasoningonversion4.3 | Partially comparable-8.57 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 171 | deepseek-v3-2-0925Open weightsDeepSeek · DeepSeek | 13.9 | Independent | version4.3 | Partially comparable-8.61 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 172 | apriel-v1-5-15b-thinkerOpen weightsServiceNow · best of 2 rows | 13.8 | Independent | reasoningonversion4.3 | Partially comparable-8.67 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 173 | DeepSeek V3.1Open weightsDeepSeek · DeepSeek-V3 · best of 4 rows | 13.7 | Independent | reasoningoffversion4.3 | Partially comparable-8.78 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 174 | Qwen3.5-9BOpen weightsQwen · Qwen3.5 · best of 4 rows | 13.7 | Independent | reasoningonversion4.3 | Partially comparable-8.84 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 174 | nova-2-0-omniClosedAmazon Web Services · Nova 2.0 · best of 6 rows | 13.7 | Independent | reasoningonreasoning_effortmediumversion4.3 | Partially comparable-8.84 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 176 | NVIDIA Nemotron 3.5 Lightning 30B A3BOpen weightsNVIDIA · Nemotron 3.5 · best of 2 rows | 13.6 | Independent | reasoningonversion4.3 | Partially comparable-8.85 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 177 | Nemotron 3 SuperOpen weightsNVIDIA · Nemotron 3 · best of 2 rows | 13.6 | Independent | reasoningonversion4.3 | Partially comparable-8.94 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 178 | Qwen3 VL 235B A22B InstructOpen weightsQwen · Qwen3 · best of 4 rows | 13.4 | Independent | reasoningonversion4.3 | Partially comparable-9.05 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 179 | apriel-v1-6-15b-thinkerOpen weightsServiceNow · best of 2 rows | 13.4 | Independent | reasoningonversion4.3 | Partially comparable-9.09 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 180 | nova-2-0-liteClosedAmazon Web Services · Nova 2.0 · best of 8 rows | 13.4 | Independent | reasoningonreasoning_efforthighversion4.3 | Partially comparable-9.12 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 181 | exaone-4-5-33bOpen weightsLG AI Research · EXAONE 4.5 · best of 2 rows | 13.2 | Independent | reasoningonversion4.3 | Partially comparable-9.28 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 182 | minicpm5-2bOpen weightsOpenBMB · best of 2 rows | 13.1 | Independent | reasoningonversion4.3 | Partially comparable-9.35 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 183 | Qwen3.5-4BOpen weightsQwen · Qwen3.5 · best of 4 rows | 13.1 | Independent | reasoningonversion4.3 | Partially comparable-9.37 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 183 | deepseek-r1Open weightsDeepSeek · DeepSeek-R1 · best of 2 rows | 13.1 | Independent | reasoningonversion4.3 | Partially comparable-9.37 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 185 | Gemini 2.5 FlashClosedGoogle · Gemini 2.5 · best of 2 rows | 13.1 | Independent | reasoningonversion4.3 | Partially comparable-9.38 | obs. 11 Sept 2026 | artificialanalysis.aiT2 | History |
| 186 | gpt-5-nanoClosedOpenAI · GPT 5 · best of 6 rows | 13.0 | Independent | reasoning_efforthighversion4.3 | Partially comparable-9.50 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 187 | North Mini Code (free)Open weightsCohere · best of 2 rows | 12.8 | Independent | reasoningonversion4.3 | Partially comparable-9.65 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 188 | GLM 4.5Open weightsZ.ai (Zhipu AI) · GLM4.5 · best of 2 rows | 12.8 | Independent | reasoningonversion4.3 | Partially comparable-9.72 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 189 | Kimi K2 0711Open weightsMoonshot AI · Kimi · best of 2 rows | 12.7 | Independent | reasoningoffversion4.3 | Partially comparable-9.77 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 190 | Qwen3 235B A22B Instruct 2507Open weightsQwen · Qwen3 · best of 4 rows | 12.7 | Independent | reasoningonversion4.3 | Partially comparable-9.78 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 191 | gpt-4.1ClosedOpenAI · GPT 4.1 · best of 2 rows | 12.7 | Independent | reasoningoffversion4.3 | Partially comparable-9.80 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 192 | qwen3-max-previewClosedAlibaba Group · Qwen3 · best of 2 rows | 12.6 | Independent | reasoningoffversion4.3 | Partially comparable-9.90 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 193 | o3-miniClosedOpenAI · OpenAI o-series · best of 4 rows | 12.5 | Independent | reasoningonversion4.3 | Partially comparable-10.0 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 193 | qwen3-5-omni-flashClosedAlibaba Group · Qwen3.5 · best of 2 rows | 12.5 | Independent | reasoningoffversion4.3 | Partially comparable-10.0 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 195 | o1-proClosedOpenAI · OpenAI o-series · best of 2 rows | 12.4 | Independent | reasoningonversion4.3 | Partially comparable-10.1 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 196 | gpt-oss-120bOpen weightsOpenAI · gpt-oss · best of 4 rows | 12.3 | Independent | reasoning_efforthighversion4.3 | Partially comparable-10.1 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 197 | jt-miniClosedChina Mobile · best of 2 rows | 12.2 | Independent | reasoningoffversion4.3 | Partially comparable-10.3 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 198 | grok-3ClosedSpaceXAI · Grok 3 · best of 4 rows | 12.1 | Independent | reasoningoffversion4.3 | Partially comparable-10.4 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 199 | Seed-OSS-36B-InstructOpen weightsByteDance · Seed · best of 2 rows | 12.1 | Independent | reasoningonversion4.3 | Partially comparable-10.4 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
| 200 | qwen3-coder-480b-a35b-instructOpen weightsAlibaba Group · Qwen3-Coder · best of 2 rows | 11.9 | Independent | reasoningoffversion4.3 | Partially comparable-10.6 | obs. 12 Sept 2026 | artificialanalysis.aiT2 | History |
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 →