Codex GPT for repository edits, code review, and practical software agents
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 23.7 | — | independent | aa | Sep 9, 2026 |
| Design Arena — codecategories | preference | 1166 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — dataviz | preference | 1228 | — | mirror | openrouter | Sep 17, 2026 |
| Design Arena — fullstack | preference | 1086 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — gamedev | preference | 1162 | — | mirror | openrouter | Sep 21, 2026 |
| Design Arena — mobileapps | preference | 1191 | — | mirror | openrouter | Aug 4, 2026 |
| Design Arena — uicomponent | preference | 1253 | — | mirror | openrouter | Sep 20, 2026 |
| Design Arena — webapps | preference | 1033 | — | mirror | openrouter | Sep 16, 2026 |
| Design Arena — website | preference | 1174 | — | mirror | openrouter | Sep 11, 2026 |
| LMArena WebDev | preference | 1336 | — | crowd | lmarena | Sep 11, 2026 |
| Median output speed | speed | 196 tok/s | — | independent | aa | Jul 25, 2026 |
| Median time to first token | speed | 8.92s | — | independent | aa | Jul 25, 2026 |
Includes index data from Artificial Analysis.
Providers
Live operational stats per hosting endpoint, via OpenRouter.
| Provider | Quant | Context | $/1M in · out | Uptime 24h | Latency | Throughput |
|---|---|---|---|---|---|---|
| Azure | — | 400K | $1.25 · $10 | 100.00% | — | — |