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) | $12.00 · Google AI |
| Released | Feb 25, 2026 |
| Arena Agent | 44th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 48th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 38th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 42nd of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 43rd of 55 |
| Arena Coding | 1521 |
| Arena Creative Writing | 1480 |
| Arena Hard Prompts | 1507 |
| Arena Instruction Following | 1479 |
| Arena Maths | 1488 |
| Arena Text (overall) | 1487 |
| Arena Code (WebDev) | 1446 |
