Tools
Compare models
Add up to four models via ?models=slug-a,slug-b — or pick from any model page.
| Spec | OpenAI |
|---|---|
| Context | 1.1M |
| Weights | |
| License | — |
| — | |
| Cheapest hosted (out/1M) | $1.32 · Amazon Bedrock |
| Released | Jul 9, 2026 |
| LiveBench | 73.6via Max |
| LiveBench Agentic Coding | 48.4via Max |
| LiveBench Coding | 82.9via Max |
| LiveBench Data Analysis | 78via Max |
| LiveBench Instruction Following | 60.1via Max |
| LiveBench Language | 72.6via Max |
| LiveBench Mathematics | 87.2via Max |
| LiveBench Reasoning | 85.6via Max |
| Arena Agent (IPS) | 0.035via xHigh |
| Arena Coding | 1501.4via xHigh |
| Arena Creative Writing | 1417.9via xHigh |
| Arena Hard Prompts | 1474.5via xHigh |
| Arena Instruction Following | 1448via xHigh |
| Arena Maths | 1476via xHigh |
| Arena Text (overall) | 1450.4via xHigh |
| Arena Code (WebDev) | 1522.9via codex-harness |