Claude 3 Opus
Claude 3 Opus is an API-only (closed weights) language model from Anthropic, released February 29, 2024. On the Epoch Capabilities Index it scores 125.5, rank 172 of 256 rated models.
Check it against your own PC →
Lab
Anthropic
Released
February 29, 2024
Weights
API-only (closed weights)
Parameters
–
Context
–
Price / M tokens
–
Epoch ECI
125.5 #172
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 8.4 | Chess Puzzles, SimpleBench |
| Math | 11.6 | MATH level 5, OTIS Mock AIME 2024-2025 |
| Knowledge | 33.3 | GPQA diamond, SimpleQA Verified, MMLU |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| MMLU | 79.5% |
| MATH level 5 | 37.5% |
| GPQA Diamond | 30.8% |
| SimpleQA Verified | 12.6% |
| SimpleBench | 8.2% |
| OTIS Mock AIME | 4.6% |
| Chess Puzzles | 0.0% |
Links
Models with a similar score
Phi-4 · GPT-4o (Nov 2024) · GPT-4o (May 2024) · Llama 3.1-405B · Llama 4 Scout · Gemma 3 27B · Qwen2.5-72B · GPT-4o (Aug 2024)
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