← AI Model Ranking
Best Reasoning AI Models
Transparent, explainable model scores based on benchmark results, capabilities, price and context.
| Rank | Model | Provider | Score |
|---|---|---|---|
| 1 | DeepSeek R1 | DeepSeek | 71.5 |
| 2 | Claude 3.5 Sonnet | Anthropic | 59.4 |
| 3 | GPT-4o | OpenAI | 53.6 |
| 4 | Llama 3.1 405B | Meta | 51.1 |
| 5 | Claude 3 Opus | Anthropic | 50.4 |
| 6 | Gemini 1.5 Pro | 46.5 | |
| 7 | GPT-4o mini | OpenAI | 40.2 |
| 8 | Claude 3 Haiku | Anthropic | 33.3 |