Best AI Language Models
See how the top language models compare, when each launched, and which labs are ahead.
See how the top language models compare, when each launched, and which labs are ahead.
Composite index aggregating multiple benchmarks to measure overall general intelligence and reasoning. Data from Artificial Analysis
| # | ||
|---|---|---|
| 1 | Anthropic | 56.8 |
| 2 | 56.2 | |
| 3 | OpenAI | 54.7 |
| 4 | 54.5 | |
| 5 | OpenAI | 54.3 |
| 6 | Anthropic | 54.1 |
| 7 | OpenAI | 53.4 |
| 8 | 53.4 | |
| 9 | Anthropic | 53.2 |
| 10 | 53.0 | |
| 11 | 52.8 | |
| 12 | OpenAI | 52.2 |
| 13 | 52.0 | |
| 14 | 51.6 | |
| 15 | OpenAI | 51.3 |
| 16 | 50.9 | |
| 17 | SpaceXAI | 50.6 |
| 18 | Kimi | 50.2 |
| 19 | SpaceXAI | 49.9 |
| 20 | OpenAI | 49.8 |
| 21 | 49.5 | |
| 22 | OpenAI | 49.3 |
| 23 | SpaceXAI | 48.8 |
| 24 | Z AI | 48.6 |
| 25 | OpenAI | 48.3 |
| 26 | 47.8 | |
| 27 | Anthropic | 47.8 |
| 28 | Google | 47.1 |
| 29 | Alibaba | 46.9 |
| 30 | 46.8 | |
| 31 | 46.8 | |
| 32 | OpenAI | 46.8 |
| 33 | Alibaba | 46.7 |
| 34 | Z AI | 46.2 |
| 35 | OpenAI | 46.0 |
| 36 | Alibaba | 45.6 |
| 37 | OpenAI | 45.6 |
| 38 | SpaceXAI | 45.5 |
| 39 | Google | 45.2 |
| 40 | Anthropic | 45.1 |
| 41 | OpenAI | 44.4 |
| 42 | Anthropic | 44.3 |
| 43 | OpenAI | 44.1 |
| 44 | 43.8 | |
| 45 | 43.4 | |
| 46 | OpenAI | 43.4 |
| 47 | OpenAI | 42.8 |
| 48 | Z AI | 42.1 |
| 49 | 42.1 | |
| 50 | SpaceXAI | 41.6 |
AA Intelligence Index data from Artificial Analysis· updated Sep 7, 2026