Claude 3.5 Sonnet (October 2024)
Claude 3.5 Sonnet (October 2024) is an API-only (closed weights) language model from Anthropic, released October 22, 2024. On the Epoch Capabilities Index it scores 133.4, rank 149 of 256 rated models.
Check it against your own PC →
Lab
Anthropic
Released
October 22, 2024
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
133.4 #149
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 11.1 | SimpleBench, Humanity's Last Exam |
| Math | 14.2 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private, FrontierMath-Tier-4-2025-07-01-Private |
| Coding | 35.8 | Aider polyglot, GSO-Bench |
| Agent | 21.8 | Balrog, The Agent Company |
| Knowledge | 40.1 | GPQA diamond, MMLU |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 83.1% |
| MATH level 5 | 56.9% |
| Aider Polyglot | 51.6% |
| GPQA Diamond | 42.1% |
| Balrog | 32.6% |
| SimpleBench | 29.7% |
| The Agent Company | 24.0% |
| OTIS Mock AIME | 8.4% |
| GSO-Bench | 4.6% |
| Humanity's Last Exam | 4.1% |
| FrontierMath-2025-02-28-Private | 3.6% |
| FrontierMath-Tier-4-2025-07-01-Private | 0.0% |
Links
Models with a similar score
Qwen3-32B · QwQ-32B · GPT-4.5 · GPT-4.1 · Qwen3-14B · Gemini 2.0 Pro · o1-mini · DeepSeek-V3 (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