Claude Opus 5
Claude Opus 5 is an API-only (closed weights) language model from Anthropic, released July 24, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 164.7, rank 10 of 256 rated models. API price: $5 input / $25 output per million tokens.
Claude Opus 5 is available today. It’s a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price. On coding and knowledge work evaluations like Frontier-Bench and GDPval-AA, Opus 5 is the new state-of-the-art, though it remains behind Mythos 5 on cybersecurity …
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 35.7 | Chess Puzzles, SimpleBench, Mystery Game Puzzles |
| Math | 76.5 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 77.5 | MirrorCode, FrontierSWE, DeepSWE |
| Agent | 38.4 | Balrog, OSWorld 2.0 |
| Knowledge | 80.0 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| ProofBench | 99.0% |
| OTIS Mock AIME | 98.9% |
| GPQA Diamond | 95.7% |
| FrontierMath (Tiers 1–3) | 90.1% |
| MirrorCode | 87.8% |
| SimpleBench | 76.7% |
| DeepSWE | 73.6% |
| FrontierMath-Tier-4-v2-Private | 73.2% |
| Balrog | 63.4% |
| SimpleQA Verified | 59.9% |
| Mystery Game Puzzles | 54.8% |
| FrontierSWE | 52.0% |
| EBR-bench | 45.7% |
| Furniture Assembly | 44.0% |
| Chess Puzzles | 40.0% |
| OSWorld 2.0 | 31.4% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Claude Opus 5.5 · GPT-6.1 Sol · GPT-6.1 Terra · Claude Fable 5.1 · Claude Sonnet 5.5 · Gemini 4 Argon · Claude Fable 5 · GPT-6 Sol
More from Anthropic
Claude Fable 5.2 · Claude Haiku 5.5 · Claude Sonnet 5.5 · Claude Opus 5.5 · Claude Fable 5.1 · Claude Sonnet 5 · Claude Fable 5 · Claude Mythos 5