Best reasoning model
- models ranked
- 106
- lead over #2
- +2.4
Overall index · read October 21
As of October 21, 2026, Anthropic Claude Opus 5.5 leads 106 models that qualify, with 87.1 on the overall index, ahead of Anthropic Claude Fable 5.1 (84.7) and Google Gemini 4 Argon (84.0).
| Rank | Model | Overall index | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 Anthropic | 87.1 | 88.8 | $20.00 | |
| 2 | Claude Fable 5.1 Anthropic | 84.7 | 84.2 | $50.00 | |
| 3 | Gemini 4 Argon Google | 84.0 | 81.0 | $10.00 | |
| 4 | GPT-6 Astra OpenAI | 83.0 | 85.1 | $50.00 | |
| 5 | Claude Sonnet 5.5 Anthropic | 82.8 | 87.3 | $10.00 | |
| 6 | Claude Opus 5 Anthropic | 81.6 | 83.0 | $25.00 | |
| 7 | GPT-6.1 Sol OpenAI | 81.4 | 82.4 | $10.00 | |
| 8 | Claude Fable 5 Anthropic | 79.0 | 79.3 | $50.00 | |
| 9 | GPT-5.6 Sol OpenAI | 74.7 | 73.5 | $20.00 | |
| 10 | GPT-6 Sol OpenAI | 74.6 | 76.0 | $10.00 | |
| 11 | Claude Opus 4.7 Anthropic | 71.6 | 67.5 | $25.00 | |
| 12 | Claude Opus 4.8 Anthropic | 69.8 | 65.0 | $25.00 | |
| 13 | GPT-5.4 OpenAI | 69.6 | 64.4 | $15.00 | |
| 14 | GPT-5.5 OpenAI | 69.2 | 71.3 | $30.00 | |
| 15 | Gemini 3.8 Flash Google | 69.0 | 61.6 | $3.75 | |
| 16 | Qwen3.8 Max (0902) Qwen | 68.9 | 62.4 | $6.00 | |
| 17 | Muse Spark 1.3 Meta | 68.6 | 57.4 | $4.25 | |
| 18 | MiMo-V2.6-Pro Xiaomi | 68.4 | 65.4 | $0.87 | |
| 19 | Gemini 3.6 Flash Google | 68.3 | 62.5 | $3.75 | |
| 20 | GPT-5.6 Terra OpenAI | 68.1 | 63.9 | $12.00 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models whose OpenRouter listing has a reasoning mode, ordered by the LLMBenchmark Index, highest first. The index is our own 0 to 100 composite of our five skill indexes, the Artificial Analysis Intelligence Index and the LMArena text Elo, with a 90% margin.
- OpenRouter, fetched
- Artificial Analysis (via OpenRouter), fetched
- LMArena WebDev, fetched