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) | $50.00 · Anthropic |
| Released | Jun 9, 2026 |
| LiveBench | 82.97 |
| LiveBench Agentic Coding | 62.17 |
| LiveBench Coding | 85.99 |
| LiveBench Data Analysis | 80.54 |
| LiveBench Instruction Following | 75.77 |
| LiveBench Language | 90.68 |
| LiveBench Mathematics | 95.99 |
| LiveBench Reasoning | 89.65 |
| Arena Agent | 4th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 5th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 2nd of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 17th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 9th of 55 |
| Arena Coding | 1552 |
| Arena Creative Writing | 1504 |
| Arena Hard Prompts | 1532 |
| Arena Instruction Following | 1511 |
| Arena Maths | 1526 |
| Arena Text (overall) | 1506 |
| Arena Code (WebDev) | 1628 |
