The best AI models right now
Ranked by independent tests, with what each one costs. Compare two of them side by side.
| # | Model | Maker | Intelligence index | Speed (tokens/s) | Input (1M tokens) | Output (1M tokens) |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 (Max, Default Fallback) | Anthropic | 57.6 | 97 | $4 | $20 |
| 2 | Claude Sonnet 5.5 (Max, Default Fallback) | Anthropic | 56 | 142 | $2 | $10 |
| 3 | Claude Opus 5.5 (Xhigh, Default Fallback) | Anthropic | 56 | 86 | $4 | $20 |
| 4 | Muse Wonder Full (Max) | Meta | 55.8 | – | free | free |
| 5 | Claude Opus 5.5 (High, Default Fallback) | Anthropic | 53.6 | 79 | $4 | $20 |
| 6 | Claude Fable 5.1 (Max, Default Fallback) | Anthropic | 53.4 | 73 | $10 | $50 |
| 7 | Claude Fable 5.1 (Xhigh, Default Fallback) | Anthropic | 53.2 | 62 | $10 | $50 |
| 8 | GPT-6 Astra (Max) | OpenAI | 52.7 | 69 | $10 | $50 |
| 9 | Gemini 4 Argon (High) | 52.6 | – | $2 | $10 | |
| 10 | Muse Wonder (Max) | Meta | 52.4 | 173 | $4 | $20 |
| 11 | GPT-6 Astra (Xhigh) | OpenAI | 52.4 | 63 | $10 | $50 |
| 12 | Claude Sonnet 5.5 (Xhigh, Default Fallback) | Anthropic | 51.9 | 108 | $2 | $10 |
| 13 | GPT-6.1 Sol (Max) | OpenAI | 51.8 | 59 | $2 | $10 |
| 14 | Claude Opus 5.5 (Medium, Default Fallback) | Anthropic | 51.2 | 82 | $4 | $20 |
| 15 | Claude Fable 5.1 (High, Default Fallback) | Anthropic | 51.2 | 58 | $10 | $50 |
| 16 | GPT-6.1 Sol (Xhigh) | OpenAI | 51 | 56 | $2 | $10 |
| 17 | GPT-6 Astra (High) | OpenAI | 50.9 | 58 | $10 | $50 |
| 18 | Claude Opus 5 (Max) | Anthropic | 50.8 | – | $5 | $25 |
| 19 | GPT-6.1 Sol (High) | OpenAI | 50.2 | 54 | $2 | $10 |
| 20 | Claude Opus 5 (Xhigh) | Anthropic | 49.7 | – | $5 | $25 |
| 21 | Claude Fable 5 (Max, Opus 4.8 Fallback) | Anthropic | 49.6 | – | $10 | $50 |
| 22 | GPT-6 Astra (Medium) | OpenAI | 49.6 | 58 | $10 | $50 |
| 23 | Claude Fable 5.1 (Medium, Default Fallback) | Anthropic | 48.9 | 57 | $10 | $50 |
| 24 | Claude Opus 5 (High) | Anthropic | 48.1 | – | $5 | $25 |
| 25 | Muse Spark 1.3 (Max) | Meta | 48.1 | 111 | $1.25 | $4.25 |
| 26 | GPT-6.1 Sol (Medium) | OpenAI | 47.8 | 54 | $2 | $10 |
| 27 | GPT-6 Sol (Max) | OpenAI | 47.6 | – | $2 | $10 |
| 28 | GPT-5.6 Sol (Max) | OpenAI | 47 | – | $4 | $20 |
| 29 | Claude Fable 5.1 (Low, Default Fallback) | Anthropic | 46.8 | 59 | $10 | $50 |
| 30 | Claude Sonnet 5.5 (High, Default Fallback) | Anthropic | 46.8 | 109 | $2 | $10 |
| 31 | Grok 4.7 (Xhigh) | SpaceXAI | 46.4 | 83 | $2 | $6 |
| 32 | Grok 4.7 (High) | SpaceXAI | 46.3 | 78 | $2 | $6 |
| 33 | MiMo-V2.6-Pro | Xiaomi | 46.3 | 46 | $0.43 | $0.87 |
| 34 | GPT-6 Astra (Low) | OpenAI | 45.8 | 57 | $10 | $50 |
| 35 | Qwen3.8 Max (0902) | Alibaba | 45.4 | 37 | $2 | $6 |
| 36 | Muse Spark 1.3 (Xhigh) | Meta | 45.1 | 263 | $1.25 | $4.25 |
| 37 | Claude Opus 5 (Medium) | Anthropic | 44.8 | – | $5 | $25 |
| 38 | GLM-5.3 (Max) | Z AI | 44.8 | 83 | $1.40 | $4.40 |
| 39 | Grok 4.6 (High) | SpaceXAI | 44.3 | – | $2 | $6 |
| 40 | GPT-6 Sol (Xhigh) | OpenAI | 44.2 | – | $2 | $10 |
Data from Artificial Analysis, updated every few hours. The intelligence index combines several independent tests. Prices are in US dollars for one million tokens: input is the text you send the model, output is the text it writes back. A token is a small piece of text, roughly three quarters of a word.