Strong small GPT for coding subagents, quick tool use, and high-volume work
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 30.2 | — | mirror | openrouter | Jul 23, 2026 |
| AA Coding Index | coding | 56.1 | — | mirror | openrouter | Jul 23, 2026 |
| AA Intelligence Index | intelligence | 40.0 | — | mirror | openrouter | Jul 23, 2026 |
| LMArena Text | preference | 1496 | high-effort | crowd | lmarena | Jul 21, 2026 |
| LMArena Vision | preference | 1247 | high-effort | crowd | lmarena | Jul 21, 2026 |
| LMArena WebDev | preference | 1397 | high-effort | crowd | lmarena | Jul 21, 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 | $0.75 · $4.5 | 99.99% | — | — |
| OpenAI | — | 400K | $0.75 · $4.5 | 69.97% | — | — |
| OpenAI | — | 400K | $0.375 · $2.25 | 69.97% | — | — |
| OpenAI | — | 400K | $1.5 · $9 | 69.97% | — | — |