Claude Opus 4
Claude Opus 4 is an API-only (closed weights) language model from Anthropic, released May 22, 2025. On the Epoch Capabilities Index it scores 142.9, rank 108 of 256 rated models.
Check it against your own PC →
Lab
Anthropic
Released
May 22, 2025
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
142.9 #108
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 17.2 | SimpleBench, Humanity's Last Exam |
| Math | 31.2 | MATH level 5, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private, FrontierMath-Tier-4-2025-07-01-Private |
| Coding | 44.8 | Aider polyglot, GSO-Bench, SWE-bench Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MATH level 5 | 85.0% |
| Aider Polyglot | 72.0% |
| GPQA Diamond | 71.2% |
| SWE-bench Verified | 70.7% |
| OTIS Mock AIME | 64.4% |
| SimpleBench | 50.6% |
| Humanity's Last Exam | 10.7% |
| FrontierMath-2025-02-28-Private | 7.9% |
| FrontierMath-Tier-4-2025-07-01-Private | 6.9% |
| GSO-Bench | 6.9% |
Links
Models with a similar score
Grok 4 · DeepSeek-V4-Flash · Qwen3.6 27B · GLM-5 · GPT-5.4 Nano · DeepSeek-V3.2 · GPT-5 mini · Gemini 3.5 Flash-Lite
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