Efficient Qwen model for fast chat, extraction, and high-volume workloads
Benchmarks
| Benchmark | Category | Score | Variant | Provenance | Source | Observed |
|---|---|---|---|---|---|---|
| AA Intelligence Index | intelligence | 6.3 | — | independent | aa | Jul 24, 2026 |
| Median output speed | speed | 104 tok/s | — | independent | aa | Jul 24, 2026 |
| Median time to first token | speed | 2.15s | — | independent | aa | Jul 24, 2026 |
Includes index data from Artificial Analysis.