Up to four models
Claude 3.7 Sonnet vs DeepSeek-R1
On the index (GPT-4 = 100), Claude 3.7 Sonnet scores 135 and DeepSeek-R1 130. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude 3.7 Sonnet
135119–151
WeightsClosed
ReleasedFeb 2025
Price in / out–
Context–
Core tests taken4 of 9
Claude 3.7 Sonnet leads DeepSeek-R1 by 5 points, ahead on 2 of 2 shared core tests.
Test by testthird-party results
Claude 3.7 Sonnet
DeepSeek-R1
Every result as a table
| Test | Claude 3.7 Sonnet | DeepSeek-R1 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 79.7% | 71.7% |
| Fiction.LiveBench | 83.3% | 69.4% |
| SimpleBench | 46.4% | 30.9% |
| Maths | ||
| AIME-style maths (OTIS mock) | 57.8% | 53.3% |
| MATH (level 5) | 91.2% | 93.0% |
| Coding | ||
| Aider Polyglot | 64.9% | 56.9% |
Task length · METR36 sec
31 sec
Tests at least two of these models have taken. Bold rows are the core tests.