Claude Opus 5.5
Claude Opus 5.5 is an API-only (closed weights) language model from Anthropic, released September 22, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 168.5, rank 4 of 256 rated models. API price: $4 input / $20 output per million tokens.
Claude Opus 5.5 is our first release since we called for pacing the frontier. It was tested before release by external evaluators, including Frontier Design and METR. On our automated behavioral audit, the most comprehensive alignment test we run, Opus 5.5 is the strongest-performing model we’ve tested to date.
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 49.8 | Chess Puzzles, SimpleBench, Mystery Game Puzzles |
| Math | 80.8 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 81.8 | MirrorCode, FrontierSWE |
| Knowledge | 82.3 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| ProofBench | 100.0% |
| OTIS Mock AIME | 100.0% |
| FrontierMath (Tiers 1–3) | 96.0% |
| MirrorCode | 95.6% |
| FrontierMath-Tier-4-v2-Private | 95.0% |
| GPQA Diamond | 91.1% |
| SimpleBench | 86.1% |
| Furniture Assembly | 76.2% |
| SimpleQA Verified | 72.2% |
| EBR-bench | 71.4% |
| Mystery Game Puzzles | 68.1% |
| Chess Puzzles | 65.3% |
| FrontierSWE | 62.3% |
| Remote Labor Index | 21.3% |
| SpireClimb | 5.8% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Gemini 4 Carbon · GPT-6 Astra · GPT-6.1 Sol · GPT-6.1 Terra · Claude Fable 5.1 · Claude Sonnet 5.5 · Gemini 4 Argon · Claude Opus 5
More from Anthropic
Claude Fable 5.2 · Claude Haiku 5.5 · Claude Sonnet 5.5 · Claude Fable 5.1 · Claude Opus 5 · Claude Sonnet 5 · Claude Fable 5 · Claude Mythos 5