Smaller o-series reasoner for economical coding, math, and planning tasks
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 0.9 | high-effort | independent | aa | Sep 7, 2026 |
| 0.9 | high-effort | mirror | openrouter | Sep 8, 2026 | ||
| AA Coding Index | coding | 16.3 | high-effort | mirror | openrouter | Jul 23, 2026 |
| 16.3 | high-effort | independent | aa | Jul 24, 2026 | ||
| AA Intelligence Index | intelligence | 11.0 | high-effort | mirror | openrouter | Sep 8, 2026 |
| 11.0 | high-effort | independent | aa | Sep 9, 2026 | ||
| 12.5 | — | independent | aa | Sep 9, 2026 | ||
| LMArena Text | preference | 1337 | high-effort | crowd | lmarena | Sep 13, 2026 |
| 1319 | — | crowd | lmarena | Sep 13, 2026 | ||
| Median output speed | speed | 224 tok/s | high-effort | independent | aa | Sep 21, 2026 |
| 199 tok/s | — | independent | aa | Sep 21, 2026 | ||
| Median time to first token | speed | 34.94s | high-effort | independent | aa | Sep 21, 2026 |
| 6.03s | — | independent | aa | Sep 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 |
|---|---|---|---|---|---|---|
| OpenAI | — | 200K | $1.1 · $4.4 | 100.00% | — | — |