QwQ-32B 16K: benchmark results
Provider: Alibaba. Released 2025-03-05.
Aggregate Rating 1638 ± 28, rank #711 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Step Game (Lechmazur) | 3.21 | TrueSkill μ | 76.4 |
| NYT Connections Older Models | 17.8 | Score (%) | 56.2 |
| Generalization V1 (Lechmazur) | 1.93 | Avg Rank (lower is better) | 51.2 |
| Confabulation Leaderboard (Lechmazur) | 25.25 | Confabulation rate % (lower is better) | 41.5 |
| PGG-Bench (Lechmazur) | 8.63 | TrueSkill μ | 22.2 |
| Elimination Game (Lechmazur) | 2.05 | TrueSkill μ | 5.1 |
Interactive version: theaggregate.ai/model?slug=qwq-32b-16k · How It Works · Data refreshed daily, snapshot 2026-11-08.