Artificial Analysis Intelligence Index
Indexes
The Artificial Analysis Intelligence Index is a versioned composite of agentic, coding, general, and scientific-reasoning evaluations. Higher index values indicate stronger aggregate performance.
Top models (higher is better)
| Model | Score |
|---|---|
| Claude Opus 5 | 60.7 |
| GPT-5.6 Sol | 57.7 |
| Kimi K3 | 57.1 |
| Grok 4.5 | 53.8 |
| Opus 4.7 | 53.5 |
| Sonnet 5 | 53.4 |
| GPT-5.6 Terra | 51.6 |
| GPT-5.4 | 51.4 |
| GLM-5.2 | 51.1 |
| Muse Spark 1.1 | 50.6 |
| Gemini 3.6 Flash | 50.1 |
| DeepSeek-V4-Flash-0731 | 49.9 |
| Sonnet 4.6 | 47.2 |
| Qwen3.7-Max (source unspecified) | 46.0 |
| MiniMax M3 | 44.4 |
| DeepSeek-V4-Pro | 44.3 |
| Kimi K2.6 | 44.2 |
| Motif-3-Beta | 44.1 |
| Muse Spark | 43.1 |
| MiMo-V2.5-Pro | 42.2 |
| Kimi K2.7 Code | 41.9 |
| Hy3 | 41.2 |
| Nex-N2-Pro | 41.0 |
| Inkling | 40.7 |
| DeepSeek-V4-Flash | 40.3 |
| Inkling-Small | 40.2 |
| GLM-5.1 | 40.2 |
| GPT-5.4 Mini | 40.0 |
| Grok Build 0.1 | 39.8 |
| Qwen3.6 Plus (2026-04-02) | 39.6 |
| Qwen3.7-Plus (source unspecified) | 39.0 |
| JT-4.1 Flash 236B A21B | 38.8 |
| Agnes 2.5 Pro Alpha | 38.8 |
| GPT-5.4 Nano | 38.2 |
| MiniMax M2.7 | 38.1 |
| Nemotron 3 Ultra 550B A55B | 37.8 |
| Grok 4.3 | 37.6 |
| MiMo-V2.5 | 37.2 |
| Qwen3.6 27B | 37.1 |
| GPT-5.1 | 36.9 |