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) | $1.20 · OpenRouter |
| Released | Jul 9, 2026 |
| LiveBench | 73.56 |
| LiveBench Agentic Coding | 48.43 |
| LiveBench Coding | 82.92 |
| LiveBench Data Analysis | 78.03 |
| LiveBench Instruction Following | 60.12 |
| LiveBench Language | 72.57 |
| LiveBench Mathematics | 87.2 |
| LiveBench Reasoning | 85.64 |
| Arena Agent | 30th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 26th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 21st of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 36th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 9th of 55 |
| Arena Coding | 1501 |
| Arena Creative Writing | 1412 |
| Arena Hard Prompts | 1475 |
| Arena Instruction Following | 1446 |
| Arena Maths | 1474 |
| Arena Text (overall) | 1454 |
| Arena Code (WebDev) | 1520 |
