Qwen 3 235B A22B (25-07) Instruct: benchmark results
Provider: Alibaba. Released 2025-04-29.
Aggregate Rating 1634 ± 30, rank #733 of 10916 rated models, from 4 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Elimination Game (Lechmazur) | 4.41 | TrueSkill μ | 59.3 |
| Step Game (Lechmazur) | 2.45 | TrueSkill μ | 56.8 |
| Generalization V1 (Lechmazur) | 1.97 | Avg Rank (lower is better) | 43.1 |
| NYT Connections Older Models | 8.6 | Score (%) | 28.1 |
Interactive version: theaggregate.ai/model?slug=qwen-3-235b-a22b-25-07-instruct · How It Works · Data refreshed daily, snapshot 2026-11-08.