Artificial Analysis Intelligence Index
We show this table for reference; we do not rank on it.
GPT-5.6 Sol has the highest reported Artificial Analysis Intelligence Index score at 58.9%, ahead of Claude Opus 5.5 (57.6%) and Claude Sonnet 5.5 (56.0%) among 216 models. We compile the table from provider self-reports and secondary reports and keep it for display only; it does not affect overall rankings.
A display-only intelligence index published by Artificial Analysis that aggregates provider-reported and benchmark-derived signals into a single model-level score.
Benchmark score on Artificial Analysis Intelligence Index — October 6, 2026
We compile the Artificial Analysis Intelligence Index rows from provider self-reports and secondary reports. GPT-5.6 Sol leads the table at 58.9%, followed by Claude Opus 5.5 (57.6%) and Claude Sonnet 5.5 (56.0%). We do not use these results to rank models overall.
GPT-5.6 Sol
OpenAI
Claude Opus 5.5
Anthropic
Claude Sonnet 5.5
Anthropic
216 modelsKnowledgeCurrentDisplay onlyUpdated October 6, 2026
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | GPT-5.6 SolOpenAI | 58.9% | Not reported | Closed |
| 2 | Claude Opus 5.5Anthropic | 57.6% | Not reported | Closed |
| 3 | Claude Sonnet 5.5Anthropic | 56.0% | Not reported | Closed |
| 4 | GPT-5.6 TerraOpenAI | 55.0% | Not reported | Closed |
| 5 | Claude Fable 5.1Anthropic | 53.4% | Not reported | Closed |
| 6 | DeepSeek V4 Pro 0813DeepSeek | 53.2% | Not reported | Open |
| 7 | GPT-6 AstraOpenAI | 52.7% | Not reported | Closed |
| 8 | Gemini 4 ArgonGoogle | 52.6% | Not reported | Closed |
| 9 | GPT-6.1 SolOpenAI | 51.8% | Not reported | Closed |
| 10 | GPT-5.6 LunaOpenAI | 51.2% | Not reported | Closed |
| 11 | Claude Opus 5Anthropic | 50.8% | Not reported | Closed |
| 12 | Gemini 3.5 FlashGoogle | 50.2% | Not reported | Closed |
| 13 | Claude Fable 5Anthropic | 49.6% | Not reported | Closed |
| 14 | Muse Spark 1.3Meta | 48.1% | Not reported | Closed |
| 15 | GPT-6 SolOpenAI | 47.6% | Not reported | Closed |
| 16 | Grok 4.7xAI | 46.5% | Not reported | Closed |
| 17 | MiMo-V2.6-ProXiaomi | 46.3% | Not reported | Open |
| 18 | Qwen3.8 Max PreviewAlibaba | 45.4% | Not reported | Closed |
| 19 | GLM-5.3Z.AI | 44.8% | Not reported | Open |
| 20 | Grok 4.6xAI | 44.3% | Not reported | Closed |
| 21 | DeepSeek V4 Pro (High)DeepSeek | 43.8% | Not reported | Open |
| 22 | Step 5 PreviewStepFun | 43.7% | Not reported | Pending |
| 23 | Kimi K3Moonshot AI | 43.6% | Not reported | Pending |
| 24 | GLM-5.3-FlashZ.AI | 41.8% | Not reported | Open |
| 25 | Claude Opus 4.8Anthropic | 41.8% | Not reported | Closed |
| 26 | Hy3 PreviewTencent | 41.2% | Not reported | Open |
| 27 | Ling 3.1 FlashInclusionAI | 41.1% | Not reported | Closed |
| 28 | Gemini 3.8 FlashGoogle | 40.9% | Not reported | Closed |
| 29 | Claude Opus 4.7 (Adaptive)Anthropic | 40.7% | Not reported | Closed |
| 30 | Qwen3.8-Flash-NextAlibaba | 39.8% | Not reported | Open |
| 31 | Muse Spark 1.2Meta | 39.6% | Not reported | Closed |
| 32 | DeepSeek V4.1 FlashDeepSeek | 39.5% | Not reported | Open |
| 33 | Gemini 3.7 FlashGoogle | 39.1% | Not reported | Closed |
| 34 | GPT-5.4OpenAI | 39.0% | Not reported | Closed |
| 35 | Grok 4.5xAI | 38.8% | Not reported | Closed |
| 36 | Mistral Large 4Mistral | 38.4% | Not reported | Pending |
| 37 | GPT-5.5OpenAI | 38.4% | Not reported | Closed |
| 38 | Claude Sonnet 5Anthropic | 38.2% | Not reported | Closed |
| 39 | GPT-6 LunaOpenAI | 38.1% | Not reported | Closed |
| 40 | MiMo-V2.6-FlashXiaomi | 37.9% | Not reported | Open |
| 41 | Grok 4.3xAI | 37.6% | Not reported | Closed |
| 42 | DeepSeek V4 Flash 0731DeepSeek | 34.3% | Not reported | Open |
| 43 | Gemini 3.6 FlashGoogle | 34.0% | Not reported | Closed |
| 44 | Muse Spark 1.1Meta | 33.7% | Not reported | Closed |
| 45 | GLM-5.2Z.AI | 33.7% | Not reported | Open |
| 46 | Qwen3.8-27BAlibaba | 33.7% | Not reported | Open |
| 47 | GPT-5.3 CodexOpenAI | 32.5% | Not reported | Closed |
| 48 | GPT-5.3-Codex-SparkOpenAI | 32.5% | Not reported | Closed |
| 49 | Claude Opus 4.6 (Adaptive)Anthropic | 31.9% | Not reported | Closed |
| 50 | Muse SparkMeta | 31.3% | Not reported | Closed |
| 51 | Claude Opus 4.7Anthropic | 30.9% | Not reported | Closed |
| 52 | GPT-5.2OpenAI | 30.4% | Not reported | Closed |
| 53 | Gemini 3.1 ProGoogle | 29.7% | Not reported | Closed |
| 54 | Qwen3.7 MaxAlibaba | 29.5% | Not reported | Closed |
| 55 | MiniMax M3MiniMax | 29.2% | Not reported | Open |
| 56 | Claude Opus 4.5 ThinkingAnthropic | 29.1% | Not reported | Closed |
| 57 | MiMo-V2-ProXiaomi | 28.6% | Not reported | Closed |
| 58 | GPT-5.2-CodexOpenAI | 28.5% | Not reported | Closed |
| 59 | Qwen 3.6 Max (preview)Alibaba | 28.4% | Not reported | Closed |
| 60 | Solar Pro 4Upstage | 28.1% | Not reported | Closed |
| 61 | Gemini 3 ProGoogle | 28.0% | Not reported | Closed |
| 62 | GLM-5Z.AI | 27.9% | Not reported | Open |
| 63 | Qwen3.6 PlusAlibaba | 27.0% | Not reported | Closed |
| 64 | Kimi K2.6Moonshot AI | 27.0% | Not reported | Open |
| 65 | Quasar 438BMultiverse Computing | 26.7% | Not reported | Closed |
| 66 | GLM-5-TurboZ.AI | 26.6% | Not reported | Closed |
| 67 | Apodex 1.1Apodex | 26.4% | Not reported | Closed |
| 68 | Apodex 1.1 MiniApodex | 26.4% | Not reported | Open |
| 69 | Claude Opus 4.6Anthropic | 26.4% | Not reported | Closed |
| 70 | GLM-5.1Z.AI | 26.1% | Not reported | Open |
| 71 | MiMo-V2.5-ProXiaomi | 26.0% | Not reported | Closed |
| 72 | Kimi K2.7 CodeMoonshot AI | 25.8% | Not reported | Open |
| 73 | Inkling-SmallThinking Machines Lab | 25.7% | Not reported | Open |
| 74 | Hy3Tencent | 25.3% | Not reported | Open |
| 75 | Qwen3.7 PlusAlibaba | 25.2% | Not reported | Closed |
| 76 | InklingThinking Machines Lab | 25.0% | Not reported | Open |
| 77 | GPT-5.1OpenAI | 24.7% | Not reported | Closed |
| 78 | Claude Sonnet 4.6Anthropic | 24.7% | Not reported | Closed |
| 79 | Ling 3.0 Flash VLInclusionAI | 24.6% | Not reported | Open |
| 80 | GPT-5.4 miniOpenAI | 24.1% | Not reported | Closed |
| 81 | MiMo-V2-OmniXiaomi | 23.9% | Not reported | Closed |
| 82 | GPT-5.1-CodexOpenAI | 23.7% | Not reported | Closed |
| 83 | GPT-5.1-Codex-MaxOpenAI | 23.7% | Not reported | Closed |
| 84 | Claude Opus 4.5Anthropic | 23.7% | Not reported | Closed |
| 85 | GLM-5V-TurboZ.AI | 23.5% | Not reported | Closed |
| 86 | Kimi K2.5Moonshot AI | 23.5% | Not reported | Open |
| 87 | Kimi K2.5 (Reasoning)Moonshot AI | 23.5% | Not reported | Closed |
| 88 | GPT-5 (high)OpenAI | 23.0% | Not reported | Closed |
| 89 | Nemotron 3 UltraNVIDIA | 22.9% | Not reported | Open |
| 90 | Qwen3.5-27BAlibaba | 22.9% | Not reported | Open |
| 91 | GPT-5 (medium)OpenAI | 22.9% | Not reported | Closed |
| 92 | Claude 4.1 Opus ThinkingAnthropic | 22.9% | Not reported | Closed |
| 93 | MiniMax M2.5MiniMax | 22.8% | Not reported | Closed |
| 94 | MiniMax M2.7MiniMax | 22.8% | Not reported | Open |
| 95 | Command A+Cohere | 22.5% | Not reported | Open |
| 96 | Grok 4xAI | 22.5% | Not reported | Closed |
| 97 | GLM-4.7Z.AI | 22.2% | Not reported | Open |
| 98 | Gemini 3.5 Flash-LiteGoogle | 22.2% | Not reported | Closed |
| 99 | o3-proOpenAI | 21.9% | Not reported | Closed |
| 100 | A.X K2SK Telecom | 21.5% | Not reported | Open |
| 101 | Qwen3.5 397BAlibaba | 21.4% | Not reported | Open |
| 102 | Qwen3.5 397B (Reasoning)Alibaba | 21.4% | Not reported | Open |
| 103 | Qwen3.6-27BAlibaba | 21.4% | Not reported | Open |
| 104 | GPT-5.4 nanoOpenAI | 20.7% | Not reported | Closed |
| 105 | Grok 4.1 Fast (Reasoning)xAI | 20.4% | Not reported | Closed |
| 106 | o3OpenAI | 20.2% | Not reported | Closed |
| 107 | Ling 3.0 FlashInclusionAI | 20.1% | Not reported | Open |
| 108 | Ling 3.0 Flash FP8InclusionAI | 20.1% | Not reported | Open |
| 109 | K-EXAONE 2.0LG AI Research | 19.7% | Not reported | Open |
| 110 | Step 3.7 FlashStepFun | 19.5% | Not reported | Open |
| 111 | Qwen3.5-35B-A3BAlibaba | 19.3% | Not reported | Open |
| 112 | Claude 4.1 OpusAnthropic | 18.6% | Not reported | Closed |
| 113 | Qwen3.6-35B-A3BAlibaba | 18.2% | Not reported | Open |
| 114 | Grok 4 Fast (Reasoning)xAI | 17.9% | Not reported | Closed |
| 115 | Gemini 3 FlashGoogle | 17.9% | Not reported | Closed |
| 116 | Muse Glimmer 30BMeta | 17.5% | Not reported | Open |
| 117 | Step 3.5 FlashStepFun | 17.0% | Not reported | Open |
| 118 | GPT-5 miniOpenAI | 16.8% | Not reported | Closed |
| 119 | Gemma 4 26B A4BGoogle | 16.7% | Not reported | Open |
| 120 | Claude 4 SonnetAnthropic | 16.6% | Not reported | Closed |
| 121 | Gemini 2.5 ProGoogle | 16.1% | Not reported | Closed |
| 122 | MiMo-V2-FlashXiaomi | 16.1% | Not reported | Open |
| 123 | DeepSeek V3.2DeepSeek | 16.0% | Not reported | Open |
| 124 | Qwen3 MaxAlibaba | 15.6% | Not reported | Closed |
| 125 | Qwen3.5-122B-A10BAlibaba | 15.6% | Not reported | Open |
| 126 | o1OpenAI | 15.2% | Not reported | Closed |
| 127 | GLM-4.6Z.AI | 14.9% | Not reported | Open |
| 128 | GLM-4.7-FlashZ.AI | 14.9% | Not reported | Open |
| 129 | Granite 4.2 30BIBM | 14.8% | Not reported | Open |
| 130 | Gemma 4 31BGoogle | 14.7% | Not reported | Open |
| 131 | K-ExaoneLG AI Research | 14.4% | Not reported | Closed |
| 132 | Mistral Medium 3.5 128BMistral | 14.2% | Not reported | Open |
| 133 | Gemma 4 12BGoogle | 14.2% | Not reported | Open |
| 134 | Grok Code Fast 1xAI | 14.1% | Not reported | Closed |
| 135 | Ling 2.6 FlashInclusionAI | 14.1% | Not reported | Open |
| 136 | Mercury 2Inception | 13.8% | Not reported | Closed |
| 137 | DeepSeek V3.1DeepSeek | 13.7% | Not reported | Open |
| 138 | DeepSeek V3.1 (Reasoning)DeepSeek | 13.5% | Not reported | Open |
| 139 | DeepSeek-R1DeepSeek | 13.1% | Not reported | Open |
| 140 | GPT-5 nanoOpenAI | 13.0% | Not reported | Closed |
| 141 | Nemotron 3.5 Lightning 30B A3B NVFP4NVIDIA | 12.9% | Not reported | Open |
| 142 | Nemotron 3 Super 100BNVIDIA | 12.8% | Not reported | Open |
| 143 | Nemotron 3 Super 120B A12BNVIDIA | 12.8% | Not reported | Open |
| 144 | Kimi K2Moonshot AI | 12.7% | Not reported | Closed |
| 145 | GPT-4.1OpenAI | 12.7% | Not reported | Closed |
| 146 | o3-miniOpenAI | 12.5% | Not reported | Closed |
| 147 | MiniCPM5-2BOpenBMB | 12.5% | Not reported | Open |
| 148 | o1-proOpenAI | 12.4% | Not reported | Closed |
| 149 | Mercury 2.5Inception | 12.3% | Not reported | Closed |
| 150 | MiniMax M1 80kMiniMax | 11.7% | Not reported | Closed |
| 151 | GPT-OSS 120BOpenAI | 11.6% | Not reported | Open |
| 152 | o1-previewOpenAI | 11.4% | Not reported | Closed |
| 153 | Grok 4.1 FastxAI | 11.3% | Not reported | Closed |
| 154 | Mistral Small 4Mistral | 11.3% | Not reported | Open |
| 155 | Mistral Small 4 (Reasoning)Mistral | 11.3% | Not reported | Open |
| 156 | GLM-4.5-AirZ.AI | 11.1% | Not reported | Closed |
| 157 | Granite 4.2 8BIBM | 11.1% | Not reported | Open |
| 158 | Ling 3.0 TinyInclusionAI | 11.1% | Not reported | Open |
| 159 | Trinity-Large-ThinkingArcee AI | 10.8% | Not reported | Open |
| 160 | Trinity-Large-PreviewArcee AI | 10.8% | Not reported | Open |
| 161 | Nemotron 3 Nano Omni 30B A3BNVIDIA | 10.3% | Not reported | Open |
| 162 | GPT-4.1 miniOpenAI | 10.2% | Not reported | Closed |
| 163 | Llama 4 MaverickMeta | 10.0% | Not reported | Open |
| 164 | North Mini CodeCohere | 9.9% | Not reported | Open |
| 165 | Gemini 2.5 FlashGoogle | 9.8% | Not reported | Closed |
| 166 | DeepSeek V3 0324DeepSeek | 9.7% | Not reported | Open |
| 167 | Mistral Large 3Mistral | 9.3% | Not reported | Closed |
| 168 | Granite 4.2 3BIBM | 9.1% | Not reported | Open |
| 169 | Mistral Medium 3Mistral | 9.1% | Not reported | Closed |
| 170 | GPT-OSS 20BOpenAI | 9.0% | Not reported | Open |
| 171 | Gemma 4 E4BGoogle | 8.9% | Not reported | Open |
| 172 | Nemotron 3 Nano 30BNVIDIA | 8.9% | Not reported | Open |
| 173 | Sarvam 105BSarvam | 8.8% | Not reported | Open |
| 174 | Claude 3 OpusAnthropic | 8.7% | Not reported | Closed |
| 175 | DeepSeek V3DeepSeek | 8.5% | Not reported | Open |
| 176 | GPT-4oOpenAI | 8.4% | Not reported | Closed |
| 177 | LFM2.5-2.6BLiquidAI | 8.4% | Not reported | Open |
| 178 | DeepSeek R1 Distill Qwen 32BDeepSeek | 8.4% | Not reported | Open |
| 179 | Llama 4 ScoutMeta | 8.1% | Not reported | Open |
| 180 | Gemini 1.5 ProGoogle | 7.9% | Not reported | Closed |
| 181 | Solar Pro 3Upstage | 7.8% | Not reported | Closed |
| 182 | GPT-4.1 nanoOpenAI | 7.8% | Not reported | Closed |
| 183 | Gemma 4 E2BGoogle | 7.8% | Not reported | Open |
| 184 | Qwen3-Omni-30B-A3B-ThinkingAlibaba | 7.8% | Not reported | Open |
| 185 | Ultravox v0.6 Llama 3.3 70BFixie AI | 7.7% | Not reported | Open |
| 186 | Mistral Large 2Mistral | 7.6% | Not reported | Closed |
| 187 | Nemotron Ultra 253BNVIDIA | 7.5% | Not reported | Open |
| 188 | Llama 3.1 405BMeta | 7.3% | Not reported | Open |
| 189 | LFM2.5-8B-A1BLiquidAI | 7.2% | Not reported | Open |
| 190 | GPT-4 TurboOpenAI | 7.0% | Not reported | Closed |
| 191 | Nova ProAmazon | 7.0% | Not reported | Closed |
| 192 | Qwen2.5 Coder 32B InstructAlibaba | 6.7% | Not reported | Open |
| 193 | GPT-4o miniOpenAI | 6.7% | Not reported | Closed |
| 194 | Sarvam 30BSarvam | 6.6% | Not reported | Open |
| 195 | Celeris-1Celeris | 6.3% | Not reported | Closed |
| 196 | Exaone 4.0 32BLG AI Research | 6.3% | Not reported | Open |
| 197 | Ministral 3 14B (Reasoning)Mistral | 6.0% | Not reported | Open |
| 198 | Ministral 3 14BMistral | 6.0% | Not reported | Open |
| 199 | Qwen3-Omni-30B-A3B-InstructAlibaba | 6.0% | Not reported | Open |
| 200 | LFM2-24B-A2BLiquidAI | 6.0% | Not reported | Closed |
| 201 | Phi-4Microsoft | 5.9% | Not reported | Open |
| 202 | Phi-4 Multimodal InstructMicrosoft | 5.8% | Not reported | Open |
| 203 | Claude 3 HaikuAnthropic | 5.6% | Not reported | Closed |
| 204 | Ministral 3 8B (Reasoning)Mistral | 5.5% | Not reported | Open |
| 205 | Ministral 3 8BMistral | 5.5% | Not reported | Open |
| 206 | Gemini 1.0 ProGoogle | 5.3% | Not reported | Closed |
| 207 | Exaone 4.0 1.2BLG AI Research | 5.2% | Not reported | Open |
| 208 | LFM2.5-1.2B-ThinkingLiquidAI | 5.2% | Not reported | Closed |
| 209 | LFM2.5-1.2B-InstructLiquidAI | 5.2% | Not reported | Closed |
| 210 | Granite-4.0-H-1BIBM | 5.2% | Not reported | Open |
| 211 | Gemma 3 27BGoogle | 4.8% | Not reported | Open |
| 212 | Ministral 3 3B (Reasoning)Mistral | 4.8% | Not reported | Open |
| 213 | Ministral 3 3BMistral | 4.8% | Not reported | Open |
| 214 | Granite-4.0-350MIBM | 4.8% | Not reported | Open |
| 215 | Granite-4.0-H-350MIBM | 4.8% | Not reported | Open |
| 216 | LFM2.5-VL-1.6B-ExtractLiquidAI | 4.8% | Not reported | Open |
Among the reported Artificial Analysis Intelligence Index rows, GPT-5.6 Sol is first at 58.9%. The third row is 2.9 points behind. The broader top-10 range is 7.6 points, so many of the published results sit in a relatively narrow band.
216 models have been evaluated on Artificial Analysis Intelligence Index. The benchmark falls in the Knowledge category. Artificial Analysis Intelligence Index is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Artificial Analysis Intelligence Index
Year
2026
Tasks
Cross-benchmark intelligence index
Format
Aggregated model score
Difficulty
Display-only external reference
BenchLM tracks Artificial Analysis as a display-only external reference rather than a weighted benchmark. It is useful as a market snapshot, but it is not a benchmark-native row with a single public task set, scoring harness, or exact-source methodology aligned to BenchLM's core benchmark pages.
Freshness and provenance
Version
Artificial Analysis Intelligence Index 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Artificial Analysis Intelligence Index measure?
A display-only intelligence index published by Artificial Analysis that aggregates provider-reported and benchmark-derived signals into a single model-level score.
Which model scores highest on Artificial Analysis Intelligence Index?
GPT-5.6 Sol by OpenAI currently leads with a score of 58.9% on Artificial Analysis Intelligence Index.
How many models are evaluated on Artificial Analysis Intelligence Index?
216 AI models have published results on Artificial Analysis Intelligence Index in the BenchLM catalog.
Compare top models on Artificial Analysis Intelligence Index
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 5,500+ readers.
One email each week. Unsubscribe anytime.