Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | OpenAI |
|---|---|
| Context | 128K |
| Weights | |
| License | — |
| — | |
| Cheapest hosted (out/1M) | $14.00 · OpenRouter |
| Released | Dec 10, 2025 |
| LiveBench | 74.6via High |
| LiveBench Agentic Coding | 50.3via High |
| LiveBench Coding | 76.1via High |
| LiveBench Data Analysis | 78.2via High |
| LiveBench Instruction Following | 61.8via High |
| LiveBench Language | 79.8via High |
| LiveBench Mathematics | 93.2via High |
| LiveBench Reasoning | 83.2via High |
| Arena Coding | 1515.2 |
| Arena Creative Writing | 1433.2 |
| Arena Hard Prompts | 1496.9 |
| Arena Instruction Following | 1457 |
| Arena Maths | 1453.7 |
| Arena Text (overall) | 1476.1 |
| Arena Code (WebDev) | 1419.2 |
| SWE-bench Verified | 72.8via mini-SWE-agent |