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) | $10.00 · Anthropic |
| Released | Jun 30, 2026 |
| LiveBench | 76.04 |
| LiveBench Agentic Coding | 59.39 |
| LiveBench Coding | 80.68 |
| LiveBench Data Analysis | 71.74 |
| LiveBench Instruction Following | 63.86 |
| LiveBench Language | 74.97 |
| LiveBench Mathematics | 92.94 |
| LiveBench Reasoning | 88.69 |
| Arena Agent | 8th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 9th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 8th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 24th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 34th of 55 |
| Arena Coding | 1436 |
| Arena Creative Writing | 1370 |
| Arena Hard Prompts | 1399 |
| Arena Instruction Following | 1374 |
| Arena Maths | 1351 |
| Arena Text (overall) | 1374 |
| Arena Code (WebDev) | 1539 |
