Efficient Qwen thinking model for local reasoning, math, and coding agents
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Agentic Index | agentic | 2.1 | thinking | mirror | openrouter | Jul 23, 2026 |
| AA Coding Index | coding | 17.4 | thinking | mirror | openrouter | Jul 23, 2026 |
| AA Intelligence Index | intelligence | 16.9 | thinking | mirror | openrouter | Aug 7, 2026 |
| LMArena Text | preference | 1368 | thinking | crowd | lmarena | Sep 13, 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 |
|---|---|---|---|---|---|---|
| Alibaba | — | 131K | $0.15 · $1.2 | 99.86% | — | — |
| — | 262K | $0.15 · $1.2 | 100.00% | — | — |