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 | Jul 16, 2026 |
| LiveBench | 75.3 |
| LiveBench Agentic Coding | 58.54 |
| LiveBench Coding | 77.16 |
| LiveBench Data Analysis | 72.55 |
| LiveBench Instruction Following | 69.64 |
| LiveBench Language | 74.34 |
| LiveBench Mathematics | 87.14 |
| LiveBench Reasoning | 87.73 |
| Arena Agent | 39th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 33rd of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 42nd of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 30th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 25th of 55 |
| Arena Coding | 1532 |
| Arena Creative Writing | 1465 |
| Arena Hard Prompts | 1511 |
| Arena Instruction Following | 1473 |
| Arena Maths | 1489 |
| Arena Text (overall) | 1491 |
| Arena Code (WebDev) | 1541 |
