An efficient reasoning model for everyday work, multistep agentic workflows, and coding.
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 55.7 | xhigh-effort | independent | aa | Nov 17, 2026 |
| 57.3 | — | mirror | openrouter | Nov 18, 2026 | ||
| Median output speed | speed | 97 tok/s | xhigh-effort | independent | aa | Nov 19, 2026 |
| Median time to first token | speed | 99.08s | xhigh-effort | independent | aa | Nov 18, 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 |
|---|---|---|---|---|---|---|
| Amazon Bedrock | — | 1.1M | $2 · $10 | 100.00% | — | — |
| Azure | — | 1.1M | $2 · $10 | 100.00% | — | — |
| OpenAI | — | 1.1M | $2 · $10 | 100.00% | — | — |
| OpenAI | — | 1.1M | $4 · $20 | 100.00% | — | — |
| OpenAI | — | 1.1M | $6 · $30 | 100.00% | — | — |