Qwen instruction model for multilingual chat, reasoning, and tool use
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 9.6 | — | independent | aa | Sep 9, 2026 |
| 9.6 | — | mirror | openrouter | Oct 5, 2026 | ||
| LMArena Text | preference | 1417 | — | crowd | lmarena | Nov 9, 2026 |
| Median output speed | speed | 151 tok/s | — | independent | aa | Nov 19, 2026 |
| Median time to first token | speed | 0.80s | — | 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 |
|---|---|---|---|---|---|---|
| DeepInfra | fp8 | 262K | $0.09 · $1.1 | 98.37% | — | — |
| — | 262K | $0.15 · $1.2 | 97.34% | — | — | |
| Parasail | fp8 | 262K | $0.1 · $1.1 | 100.00% | — | — |