Claude Sonnet 4.6 vs Claude Sonnet 5
| model Claude Sonnet 4.6 Anthropic | model Claude Sonnet 5 Anthropic | |
|---|---|---|
| Context | 1M | 1M |
| Input $/M | $3.00 | — |
| Output $/M | $15.00 | — |
| Knowledge cutoff | 2025-08 | 2026-01 |
| Available via | Anthropic API, OpenRouter | Anthropic API |
| SWE-Atlas Codebase QnA (score) | 31.2 | — |
| SWE-Atlas Refactoring (score) | 32.21 | — |
| SWE-Atlas Test Writing (score) | 31.76 | — |
| Artificial Analysis Coding Agent Index (average pass@1) | 49.4 | — |
| SWE-Atlas Codebase QnA (pass@1) | 70.3 | — |
| SWE-bench Pro (pass@1) | 14.9 | — |
| SWE-bench Verified (resolved) | — | 85.2 |
| SWE-bench Pro | — | 63.2% |
| SWE-bench Multilingual | — | 78.3% |
| Terminal-Bench (success rate) | — | 80.4 |
| OSWorld-Verified (success rate) | — | 81.2 |
| BrowseComp (accuracy) | — | 84.7 |