Qwen 3 VL 4B (Thinking) — benchmark results
Alibaba Qwen 3 VL 4B vision-language model evaluated with thinking enabled. Provider: Alibaba. Released 2025-07-01. Access: Open.
Unified ELO 1495 ± 18, rank #817 of 1776 rated models, from 85 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| OCR-Robust | 78.63 | OCR1.0 Clean (self-reported) | 86.7 |
| MedLayXPlain | 63.3 | S (self-reported) | 74.2 |
| K-MetBench | 66.1 | Accuracy (self-reported) | 62.1 |
| LLM Stats (MuirBench) | 75 | Score (%) | 60 |
| LLM Stats (MMStar) | 73.2 | Score (%) | 47.6 |
| LLM Stats (Multi-IF) | 73.6 | Score (%) | 47.4 |
| LLM Stats (Hallusion Bench) | 64.1 | Score (%) | 46.7 |
| LLM Stats (MLVU-M) | 75.7 | Score (%) | 42.9 |
| AA-LCR | 21.3 | Score (self-reported) | 41.2 |
| LLM Stats (MathVista-Mini) | 79.5 | Score (%) | 40.9 |
| LLM Stats (ScreenSpot) | 92.9 | Score (%) | 40 |
| AA Omniscience - Software Engineering (SWE) - Go | 14 | Accuracy (%) | 39.6 |
Interactive version: theaggregate.ai/model?slug=qwen-3-vl-4b-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.