Claude 3.7 Sonnet
Claude 3.7 Sonnet is an API-only (closed weights) language model from Anthropic, released February 24, 2025. On the Epoch Capabilities Index it scores 141.0, rank 118 of 256 rated models.
Check it against your own PC →
Lab
Anthropic
Released
February 24, 2025
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
141.0 #118
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 12.7 | SimpleBench, Humanity's Last Exam |
| Math | 30.2 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private |
| Coding | 39.5 | Aider polyglot, GSO-Bench, SWE-bench Verified |
| Agent | 22.1 | The Agent Company, OSWorld |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 91.2% |
| GPQA Diamond | 76.0% |
| Aider Polyglot | 64.9% |
| SWE-bench Verified | 61.0% |
| OTIS Mock AIME | 57.7% |
| OSWorld | 35.8% |
| SimpleBench | 35.7% |
| The Agent Company | 30.9% |
| Humanity's Last Exam | 8.0% |
| FrontierMath-2025-02-28-Private | 7.3% |
| GSO-Bench | 3.8% |
Links
Models with a similar score
Gemini 2.5 Pro (Jun 2025) · Claude Opus 4.1 · DeepSeek-V3.2-Exp · Grok 4 Fast · Gemma 4 31B IT · Qwen 3.6 35B-A3B · Qwen3.5-35B-A3B · Gemini 2.5 Pro (Mar 2025)
More from Anthropic
Claude Fable 5.2 · Claude Haiku 5.5 · Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Fable 5.1 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5