Qwen 3 VL 235B A22B — benchmark results
Alibaba Qwen 3 VL 235B A22B vision-language model row. Provider: Alibaba. Released 2025-09-22. Access: Open.
Unified ELO 1660 ± 28, rank #346 of 1776 rated models, from 40 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SciEval - Physics | 49.93 | Physics (%) | 100 |
| MMMU Benchmark | 78.7 | Validation Score | 94.2 |
| GeoSym-Bench | 77.34 | Overall (self-reported) | 90.5 |
| VeriTrip | 68.26 | DR (Simple) (self-reported) | 90 |
| SGI-Bench Wet Experiment | 30.3 | Wet Experiment Score | 77.8 |
| SciEval - Chemistry | 77.39 | Chemistry (%) | 77.8 |
| SciEval - Life Sciences | 56.69 | Life Sciences (%) | 77.8 |
| SciEval - Overall | 60.58 | Overall (%) | 77.8 |
| IDP Leaderboard | 76.8 | Avg Score (%) | 72 |
| Perception or Prejudice | 12.8 | HR (self-reported) | 69.2 |
| SciEval - Materials Science | 81.85 | Materials Science (%) | 66.7 |
| OmniDocBench 1.5 | 89.15 | Overall (self-reported) | 63.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-vl-235b-a22b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.