Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Meta |
|---|---|
| Context | 1M |
| License | |
| Cheapest hosted (out/1M) | $4.25 · Meta |
| Released | Sep 2, 2026 |
| LiveBench | 81.59 |
| LiveBench Agentic Coding | 64.09 |
| LiveBench Coding | 81.06 |
| LiveBench Data Analysis | 79.57 |
| LiveBench Instruction Following | 78 |
| LiveBench Language | 82.79 |
| LiveBench Mathematics | 95.95 |
| LiveBench Reasoning | 89.65 |
| Arena Agent | 15th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 18th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 22nd of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 9th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 9th of 55 |
| Arena Coding | 1539 |
| Arena Creative Writing | 1450 |
| Arena Hard Prompts | 1516 |
| Arena Instruction Following | 1486 |
| Arena Maths | 1505 |
| Arena Text (overall) | 1494 |
| Arena Code (WebDev) | 1656 |
