Codex GPT for repository edits, code review, and practical software agents
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 34.7 | — | independent | aa | Jul 24, 2026 |
| Design Arena — codecategories | preference | 1183 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — dataviz | preference | 1206 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — fullstack | preference | 1086 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — gamedev | preference | 1197 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — mobileapps | preference | 1198 | — | mirror | openrouter | Jul 24, 2026 |
| Design Arena — webapps | preference | 1076 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — website | preference | 1188 | — | mirror | openrouter | Jul 23, 2026 |
| LMArena WebDev | preference | 1330 | — | crowd | lmarena | Jul 21, 2026 |
| Median output speed | speed | 196 tok/s | — | independent | aa | Jul 24, 2026 |
| Median time to first token | speed | 5.25s | — | independent | aa | Jul 24, 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% | — | — |
| OpenAI | — | 400K | $1.25 · $10 | 93.69% | — | — |
| OpenAI | — | 400K | $2.5 · $20 | 93.69% | — | — |