Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Anthropic |
|---|---|
| Context | 200K |
| Weights | |
| License | — |
| — | |
| Cheapest hosted (out/1M) | $25.00 · OpenRouter |
| Released | Nov 24, 2025 |
| LiveBench | 72.6via Thinking 64k High effort |
| LiveBench Agentic Coding | 39.7via Thinking 64k High effort |
| LiveBench Coding | 79.7via Thinking 64k High effort |
| LiveBench Data Analysis | 74.4via Thinking 64k High effort |
| LiveBench Instruction Following | 62.6via Thinking 64k High effort |
| LiveBench Language | 81.3via Thinking 64k High effort |
| LiveBench Mathematics | 90.4via Thinking 64k High effort |
| LiveBench Reasoning | 80.1via Thinking 64k High effort |
| Arena Coding | 1523 |
| Arena Creative Writing | 1460 |
| Arena Hard Prompts | 1497.6 |
| Arena Instruction Following | 1474.3 |
| Arena Maths | 1465 |
| Arena Text (overall) | 1468.9 |
| Arena Code (WebDev) | 1467 |
| SWE-bench Verified | 79.2via live-SWE-agent |
