Best AI models for reasoning
For the hardest problems — proofs, multi-step planning, deep research — we weigh reasoning above all else.
The podium
Top 3 picks
🥇Anthropic
Claude Opus 4.7Anthropic's flagship. Deep reasoning, long-horizon agents.
reasoning
10.0
coding
10.0
1M context$15.00 / $75.00
🥈OpenAI
GPT-5OpenAI's flagship. Omni-modal, omni-purpose.
reasoning
10.0
coding
9.0
400K context$10.00 / $40.00
Full ranking
Runners-up
| # | Model | Context | Price /M | |
|---|---|---|---|---|
| 4 | Claude Sonnet 4.6 Anthropic | 1M | $3.00 / $15.00 | View → |
| 5 | DeepSeek V3 DeepSeek | 128K | $0.27 / $1.10 | View → |
| 6 | Gemini 3 Pro Google | 2M | $3.50 / $14.00 | View → |
| 7 | Grok 4 xAI | 256K | $5.00 / $15.00 | View → |
| 8 | GPT-4.1 OpenAI | 1M | $2.00 / $8.00 | View → |
Keep learning