Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Google |
|---|---|
| Context | 1M |
| License | |
| Cheapest hosted (out/1M) | $2.50 · Google AI |
| Released | Jul 21, 2026 |
| LiveBench | 63.94 |
| LiveBench Agentic Coding | 45.25 |
| LiveBench Coding | 76.07 |
| LiveBench Data Analysis | 53.25 |
| LiveBench Instruction Following | 67.24 |
| LiveBench Language | 71.82 |
| LiveBench Mathematics | 73.74 |
| LiveBench Reasoning | 60.19 |
| Arena Agent | 52nd of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 51st of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 55th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 51st of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 49th of 55 |
| Arena Coding | 1503 |
| Arena Creative Writing | 1435 |
| Arena Hard Prompts | 1475 |
| Arena Instruction Following | 1444 |
| Arena Maths | 1440 |
| Arena Text (overall) | 1456 |
| Arena Code (WebDev) | 1439 |
