Claude Sonnet 4.6
Claude Sonnet 4.6 is an API-only (closed weights) language model from Anthropic, released February 17, 2026. The context window is 1M tokens. On the Epoch Capabilities Index it scores 152.9, rank 56 of 256 rated models. API price: $3 input / $15 output per million tokens.
Check it against your own PC →
Lab
Anthropic
Released
February 17, 2026
Weights
API-only (closed weights)
Parameters
–
Context
1M
Price / M tokens
$3 / $15 in / out
Epoch ECI
152.9 #56
Strengths by category
ModelTape's 0–100 fit on Epoch AI benchmark results.
| Category | Score | Based on |
|---|---|---|
| Reasoning | 13.4 | Chess Puzzles, Mystery Game Puzzles |
| Math | 62.4 | ProofBench, OTIS Mock AIME 2024-2025, FrontierMath-2025-02-28-Private, FrontierMath-Tier-4-2025-07-01-Private |
| Coding | 44.9 | Terminal Bench, SWE-bench Verified, DeepSWE |
| Agent | 32.7 | OSWorld, OSWorld 2.0 |
| Knowledge | 70.0 | GPQA diamond, SimpleQA Verified |
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| GPQA Diamond | 86.6% |
| OTIS Mock AIME | 85.8% |
| SWE-bench Verified | 75.2% |
| OSWorld | 72.1% |
| FrontierMath-2025-02-28-Private | 56.8% |
| Terminal-Bench | 53.4% |
| ProofBench | 45.0% |
| SimpleQA Verified | 35.5% |
| DeepSWE | 29.9% |
| Chess Puzzles | 19.0% |
| FrontierMath-Tier-4-2025-07-01-Private | 13.8% |
| OSWorld 2.0 | 9.3% |
| Mystery Game Puzzles | 7.5% |
Links
Announcement · Epoch AI benchmarks
Models with a similar score
DeepSeek V4.1 Flash · GPT-5.6 Luna · GPT-6 Luna · Claude Opus 4.6 · Grok 4.7 · Gemini 3.1 Pro · Qwen3.8 Max (0902) · DeepSeek V4 Pro 0813
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