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) | $0.38 · DeepInfra |
| Released | Aug 26, 2026 |
| LiveBench | 76.19 |
| LiveBench Agentic Coding | 61.62 |
| LiveBench Coding | 72.55 |
| LiveBench Data Analysis | 74.24 |
| LiveBench Instruction Following | 77.11 |
| LiveBench Language | 74.64 |
| LiveBench Mathematics | 85.82 |
| LiveBench Reasoning | 87.38 |
| Arena Agent | 29th of 55 |
| Arena Agent · Recoverygets back on track after a command fails | 35th of 55 |
| Arena Agent · Steerabilitydoes what it was asked, and changes course when told | 37th of 55 |
| Arena Agent · Task outcomefinishes what the session set out to do | 12th of 55 |
| Arena Agent · Tool usereaches for the right one, and does not invent one | 45th of 55 |
| Arena Code (WebDev) | 1636 |
