Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | OpenAI |
|---|---|
| Context | 1.1M |
| License | |
| Cheapest hosted (out/1M) | $10.00 · OpenAI |
| Released | Jul 9, 2026 |
| LiveBench | 81.05 |
| LiveBench Agentic Coding | 56.21 |
| LiveBench Coding | 83.94 |
| LiveBench Data Analysis | 79.84 |
| LiveBench Instruction Following | 71.85 |
| LiveBench Language | 87.68 |
| LiveBench Mathematics | 96.2 |
| LiveBench Reasoning | 91.65 |
| Arena Agent | 6th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 23rd of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 9th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 19th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 9th of 55 |
| Arena Coding | 1531 |
| Arena Creative Writing | 1470 |
| Arena Hard Prompts | 1509 |
| Arena Instruction Following | 1489 |
| Arena Maths | 1494 |
| Arena Text (overall) | 1483 |
| Arena Code (WebDev) | 1617 |
