Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | xAI |
|---|---|
| Context | 500K |
| License | |
| Cheapest hosted (out/1M) | $6.00 · xAI |
| Released | Aug 12, 2026 |
| LiveBench | 78.04 |
| LiveBench Agentic Coding | 57.02 |
| LiveBench Coding | 76.78 |
| LiveBench Data Analysis | 73.86 |
| LiveBench Instruction Following | 71.87 |
| LiveBench Language | 83.7 |
| LiveBench Mathematics | 92.57 |
| LiveBench Reasoning | 90.51 |
| Arena Agent | 23rd of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 14th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 16th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 31st of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 9th of 55 |
| Arena Coding | 1507 |
| Arena Creative Writing | 1445 |
| Arena Hard Prompts | 1478 |
| Arena Instruction Following | 1451 |
| Arena Maths | 1443 |
| Arena Text (overall) | 1453 |
| Arena Code (WebDev) | 1621 |
