Claude Opus 4.5
Claude Opus 4.5 is an API-only (closed weights) language model from Anthropic, released November 24, 2025. The context window is 195K tokens. On the Epoch Capabilities Index it scores 151.9, rank 61 of 256 rated models. API price: $5 input / $25 output per million tokens.
Our newest model, Claude Opus 4.5, is available today. It’s intelligent, efficient, and the best model in the world for coding, agents, and computer use. It’s also meaningfully better at everyday tasks like deep research and working with slides and spreadsheets.
Check it against your own PC →
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 15.7 | Chess Puzzles, SimpleBench, Mystery Game Puzzles, Humanity's Last Exam |
| Math | 36.1 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 54.1 | GSO-Bench, Terminal Bench, SWE-bench Verified |
| Agent | 30.4 | Balrog, OSWorld, Remote Labor Index |
| Knowledge | 72.4 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 86.1% |
| GPQA Diamond | 84.8% |
| SWE-bench Verified | 76.7% |
| OSWorld | 66.3% |
| Terminal-Bench | 63.1% |
| SimpleBench | 54.4% |
| SimpleQA Verified | 45.7% |
| Balrog | 43.5% |
| FrontierMath (Tiers 1–3) | 36.2% |
| ProofBench | 36.0% |
| GSO-Bench | 26.5% |
| Humanity's Last Exam | 25.2% |
| EBR-bench | 14.3% |
| Mystery Game Puzzles | 14.1% |
| Chess Puzzles | 9.5% |
| FrontierMath-Tier-4-v2-Private | 4.9% |
| Remote Labor Index | 3.8% |
| Furniture Assembly | 0.0% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
Muse Spark Open · Gemini 3.5 Flash · Gemini 3.6 Flash · Muse Spark 1.2 · Grok 4.5 · Muse Spark 1.1 · Mistral Large 4 · Qwen3.7-Max
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