Code-specialist GPT for repository edits, reviews, and long-running software agents
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 28.5 | — | independent | aa | Sep 9, 2026 |
| Design Arena — androidnative | preference | 1176 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — fullstack | preference | 1002 | — | mirror | openrouter | Sep 15, 2026 |
| Design Arena — godotgamedev | preference | 1142 | — | mirror | openrouter | Jul 23, 2026 |
| Design Arena — mobileapps | preference | 1119 | — | mirror | openrouter | Sep 19, 2026 |
| Design Arena — webapps | preference | 1066 | — | mirror | openrouter | Sep 19, 2026 |
| LMArena WebDev | preference | 1339 | — | crowd | lmarena | Sep 11, 2026 |
| Median output speed | speed | 152 tok/s | — | independent | aa | Jul 25, 2026 |
| Median time to first token | speed | 47.86s | — | 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 | $1.75 · $14 | 100.00% | — | — |