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) | $3.75 · Google AI |
| Released | Aug 13, 2026 |
| LiveBench | 78.83 |
| LiveBench Agentic Coding | 58.28 |
| LiveBench Coding | 78.89 |
| LiveBench Data Analysis | 67.96 |
| LiveBench Instruction Following | 79.93 |
| LiveBench Language | 85.46 |
| LiveBench Mathematics | 93.47 |
| LiveBench Reasoning | 87.8 |
| Arena Agent | 32nd of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 36th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 24th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 25th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 37th of 55 |
| Arena Coding | 1519 |
| Arena Creative Writing | 1492 |
| Arena Hard Prompts | 1509 |
| Arena Instruction Following | 1487 |
| Arena Maths | 1507 |
| Arena Text (overall) | 1488 |
| Arena Code (WebDev) | 1593 |
