Qwen 3 VL 30B A3B (Thinking): benchmark results
Alibaba Qwen 3 VL 30B A3B vision-language model evaluated with thinking enabled. Provider: Alibaba. Released 2025-07-01. Access: Open.
Unified ELO 1516 ± 1, rank #764 of 1761 rated models, from 135 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Medmarks - PubMedQA | 78.53 | Score (%) | 95.7 |
| SnakeBench | 32.5 | TrueSkill Rating | 92.1 |
| MedLayXPlain | 64.8 | S (self-reported) | 90.3 |
| Medmarks - SuperGPQA Medicine Easy | 58.82 | Score (%) | 84.3 |
| FlagEval EmbodiedVerse - RoboSpatial-Home | 58.93 | Score | 82.6 |
| LLM Stats (MuirBench) | 77.6 | Score (%) | 81.8 |
| SWE-Arena | 1002 | Elo Score | 80.6 |
| Medmarks - HEAD-QA v2 | 87.5 | Score (%) | 80 |
| Medmarks - CareQA EN | 90.11 | Score (%) | 78.6 |
| Medmarks - Med-HALT Reasoning NOTA | 66.97 | Score (%) | 78.6 |
| K-MetBench | 74.9 | Accuracy (self-reported) | 78.4 |
| FlagEval EmbodiedVerse - CV-Bench (test) | 86.7 | Score | 78.3 |
Interactive version: theaggregate.ai/model?slug=qwen-3-vl-30b-a3b-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.