Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Anthropic |
|---|---|
| Context | 1M |
| License | |
| Cheapest hosted (out/1M) | $15.00 · Anthropic |
| Released | Feb 17, 2026 |
| LiveBench | 72.99 |
| LiveBench Agentic Coding | 42.63 |
| LiveBench Coding | 79.27 |
| LiveBench Data Analysis | 77.95 |
| LiveBench Instruction Following | 63.22 |
| LiveBench Language | 76.1 |
| LiveBench Mathematics | 86.99 |
| LiveBench Reasoning | 84.77 |
| Arena Agent | 34th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 19th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 41st of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 39th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 28th of 55 |
| Arena Coding | 1529 |
| Arena Creative Writing | 1449 |
| Arena Hard Prompts | 1503 |
| Arena Instruction Following | 1475 |
| Arena Maths | 1463 |
| Arena Text (overall) | 1472 |
| Arena Code (WebDev) | 1521 |
