AI models compared
The leading models by intelligence index, context window and price – live.
Compare two models
vs
| # | Models | Intelligence Index | Price per request | |
|---|---|---|---|---|
| 1 | Claude Opus 5.5 | 57.6 | — | Try in Playground |
| 2 | Claude Fable 5.1 | 53.4 | — | Try in Playground |
| 3 | GPT-6 Astra | 52.7 | — | Try in Playground |
| 4 | Claude Opus 5 | 49.7 | — | Try in Playground |
| 5 | MiMo-V2.6-Pro | 46.3 | — | Try in Playground |
| 6 | Grok 4.7 | 46.3 | — | Try in Playground |
| 7 | Grok 4.6 | 42.8 | — | Try in Playground |
| 8 | GLM 5.3 Flash | 41.8 | — | Try in Playground |
| 9 | Muse Spark 1.2 | 39.6 | — | Try in Playground |
| 10 | GPT-5.5 | 38.4 | — | Try in Playground |
| 11 | Claude Sonnet 5 | 38.2 | — | Try in Playground |
| 12 | GPT-5.6 Luna | 37.3 | — | Try in Playground |
| 13 | GPT-6 Sol | 33.9 | — | Try in Playground |
| 14 | GPT-6 Luna | 33.9 | — | Try in Playground |
| 15 | GPT-5.6 Sol | 33.5 | — | Try in Playground |
| 16 | Gemini 3.5 Flash | 32.6 | — | Try in Playground |
| 17 | Claude Opus 4.7 | 30.9 | — | Try in Playground |
| 18 | GPT-5.6 Terra | 30.1 | — | Try in Playground |
| 19 | MiniMax M3 | 29.2 | — | Try in Playground |
| 20 | Claude Opus 4.5 | 29.1 | — | Try in Playground |
| 21 | GPT-5.2-Codex | 28.5 | — | Try in Playground |
| 22 | Solar Pro 4 | 28.2 | — | Try in Playground |
| 23 | GLM 5 | 27.9 | — | Try in Playground |
| 24 | Kimi K2.6 | 27 | — | Try in Playground |
Popular comparisons
Claude Opus 5.5 vs GPT-6 AstraClaude Opus 5.5 vs MiMo-V2.6-ProClaude Opus 5.5 vs Grok 4.7Claude Opus 5.5 vs GLM 5.3 FlashGPT-6 Astra vs MiMo-V2.6-ProGPT-6 Astra vs Grok 4.7GPT-6 Astra vs GLM 5.3 FlashMiMo-V2.6-Pro vs Grok 4.7MiMo-V2.6-Pro vs GLM 5.3 FlashGrok 4.7 vs GLM 5.3 Flash
Source: Artificial Analysis Intelligence Index (artificialanalysis.ai). Prices: our own catalogue.