Qwen 3 VL 32B Instruct — benchmark results
Alibaba's open Qwen 3 VL 32B instruct vision-language model. Provider: Alibaba. Released 2025-07-01. Access: Open.
Unified ELO 1546 ± 21, rank #634 of 1776 rated models, from 102 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| FIND | 77.8 | Zero shot en (self-reported) | 100 |
| LLM Stats (MLVU-M) | 82.1 | Score (%) | 100 |
| LLM Stats (ScreenSpot) | 95.8 | Score (%) | 100 |
| LLM Stats (OCRBench-V2 (en)) | 67.4 | Score (%) | 90.9 |
| LLM Stats (DocVQAtest) | 96.9 | Score (%) | 90 |
| LLM Stats (CharXiv-D) | 90.5 | Score (%) | 86.7 |
| CulMind | 46.6 | S (self-reported) | 84.6 |
| VANTAGE-Bench - Video QA | 71.3 | Video QA (%) | 84.6 |
| TriViewBench | 61.38 | Overall (self-reported) | 83.3 |
| MechVQA | 76.5 | Total (self-reported) | 81.2 |
| Physical AI Bench - Understanding Overall | 62 | Overall Score (%) | 79.2 |
| VANTAGE-Bench | 55.05 | Overall (%) | 76.9 |
Interactive version: theaggregate.ai/model?slug=qwen-3-vl-32b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.