Claude Opus 4.6
Claude Opus 4.6 is an API-only (closed weights) language model from Anthropic, released February 5, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 156.3, rank 37 of 256 rated models. API price: $5 input / $25 output per million tokens.
Check it against your own PC →
Lab
Anthropic
Released
February 5, 2026
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$5 / $25 in / out
Epoch ECI
156.3 #37
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 19.7 | Chess Puzzles, SimpleBench, Mystery Game Puzzles, Humanity's Last Exam |
| Math | 51.8 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-Tiers-1-3-v2-Private, FrontierMath-Tier-4-v2-Private |
| Coding | 60.2 | GSO-Bench, MirrorCode, Terminal Bench, SWE-bench Verified |
| Knowledge | 75.0 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 94.4% |
| GPQA Diamond | 91.0% |
| Terminal-Bench | 79.8% |
| SWE-bench Verified | 78.7% |
| FrontierMath (Tiers 1–3) | 69.4% |
| SimpleBench | 61.1% |
| ProofBench | 50.0% |
| SimpleQA Verified | 47.0% |
| GSO-Bench | 41.2% |
| Humanity's Last Exam | 34.4% |
| MirrorCode | 33.3% |
| FrontierMath-Tier-4-v2-Private | 26.8% |
| Mystery Game Puzzles | 17.4% |
| Chess Puzzles | 16.9% |
| EBR-bench | 12.7% |
| Remote Labor Index | 4.2% |
| Furniture Assembly | 0.0% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
GPT-5.4 Pro · GPT-5.5 · Claude Opus 4.8 · DeepSeek V4.1 Flash 1017 · Gemini 3.8 Flash · Kimi K3 · Gemini 3.7 Flash · Muse Spark 1.3
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