Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | Qwen |
|---|---|
| Context | 1M |
| License | |
| Cheapest hosted (out/1M) | $6.00 · Novita AI |
| Released | Aug 3, 2026 |
| LiveBench | 78.46 |
| LiveBench Agentic Coding | 64.65 |
| LiveBench Coding | 72.87 |
| LiveBench Data Analysis | 78.41 |
| LiveBench Instruction Following | 74.08 |
| LiveBench Language | 79.69 |
| LiveBench Mathematics | 91.31 |
| LiveBench Reasoning | 88.21 |
| Arena Agent | 18th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 22nd of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 18th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 15th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 48th of 55 |
| Arena Coding | 1520 |
| Arena Creative Writing | 1467 |
| Arena Hard Prompts | 1501 |
| Arena Instruction Following | 1472 |
| Arena Maths | 1495 |
| Arena Text (overall) | 1479 |
| Arena Code (WebDev) | 1672 |