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) | $25.00 · Anthropic |
| Released | May 27, 2026 |
| LiveBench | 76.22 |
| LiveBench Agentic Coding | 50.51 |
| LiveBench Coding | 81.83 |
| LiveBench Data Analysis | 66.03 |
| LiveBench Instruction Following | 72.03 |
| LiveBench Language | 79.66 |
| LiveBench Mathematics | 94.32 |
| LiveBench Reasoning | 89.19 |
| Arena Agent | 19th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 3rd of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 4th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 14th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 54th of 55 |
| Arena Coding | 1530 |
| Arena Creative Writing | 1462 |
| Arena Hard Prompts | 1504 |
| Arena Instruction Following | 1478 |
| Arena Maths | 1477 |
| Arena Text (overall) | 1474 |
| Arena Code (WebDev) | 1535 |
