Qwen 3 VL 32B (Thinking) — benchmark results
Alibaba Qwen 3 VL 32B vision-language model evaluated with thinking enabled. Provider: Alibaba. Released 2025-07-01. Access: Open.
Unified ELO 1593 ± 21, rank #492 of 1776 rated models, from 83 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (MuirBench) | 80.3 | Score (%) | 100 |
| LLM Stats (OCRBench-V2 (en)) | 68.4 | Score (%) | 100 |
| MedLayXPlain | 65.4 | S (self-reported) | 93.5 |
| LLM Stats (ScreenSpot) | 95.7 | Score (%) | 93.3 |
| LLM Stats (OCRBench-V2 (zh)) | 62.1 | Score (%) | 90 |
| K-MetBench | 78.6 | Accuracy (self-reported) | 89.7 |
| AA LiveCodeBench | 73.76 | Pass@1 (%) | 85.1 |
| LLM Stats (Multi-IF) | 78 | Score (%) | 84.2 |
| AA AIME 2025 | 84.67 | Accuracy (%) | 81.9 |
| LLM Stats (CharXiv-D) | 90.2 | Score (%) | 80 |
| LLM Stats (WritingBench) | 86.2 | Score (%) | 78.6 |
| LLM Stats (InfoVQAtest) | 89.2 | Score (%) | 77.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-vl-32b-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.