Up to four models
Claude 3.7 Sonnet vs Claude 3.5 Sonnet
On the index (GPT-4 = 100), Claude 3.7 Sonnet scores 135 and Claude 3.5 Sonnet 122. 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 3.5 Sonnet
122107–138
WeightsClosed
ReleasedOct 2024
Price in / out–
Context–
Core tests taken3 of 9
Claude 3.7 Sonnet leads Claude 3.5 Sonnet by 13 points, ahead on 3 of 3 shared core tests.
Test by testthird-party results
Claude 3.7 SonnetClaude 3.5 Sonnet
Every result as a table
| Test | Claude 3.7 Sonnet | Claude 3.5 Sonnet |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 79.7% | 55.3% |
| Humanity's Last Exam | 8.0% | 4.1% |
| GeoBench | 68.0% | 62.0% |
| SimpleBench | 46.4% | 41.4% |
| VPCT | 39.0% | 33.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 57.8% | 8.5% |
| MATH (level 5) | 91.2% | 57.0% |
| FrontierMath (2025 set) | 4.1% | 2.1% |
| Coding | ||
| Aider Polyglot | 64.9% | 51.6% |
| CadEval | 54.0% | 48.0% |
| GSO-Bench | 3.8% | 4.6% |
Task length · METR36 sec27 sec
Tests at least two of these models have taken. Bold rows are the core tests.