Qwen 3 VL 30B A3B Instruct — benchmark results

Alibaba's open 30B A3B MoE vision-language model with 256K context, OCR in 32 languages, and GUI-agent skills. Provider: Alibaba. Released 2025-07-01. Access: Open.

Unified ELO 1547 ± 17, rank #630 of 1776 rated models, from 87 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Konkur 1404 - Experimental Sciences50.31Accuracy (%, text-only)100
LLM Stats (CharadesSTA)63.5Score (%)86.4
LLM Stats (MLVU-M)81.3Score (%)85.7
Konkur 1404 - Mathematics46.96Accuracy (%, text-only)84.2
LLM Stats (OCRBench)90.3Score (%)81
Konkur 1404 - Overall43.64Accuracy (%, text-only)78.9
LLM Stats (ScreenSpot)94.7Score (%)70
AA Omniscience - Software Engineering (SWE) - Swift48Accuracy (%)69.5
LLM Stats (ODinW)47.5Score (%)66.7
Physical AI Bench - Understanding Overall59.5Overall Score (%)66.7
AA AIME 202572.33Accuracy (%)66.5
Konkur 1404 - Foreign Language37.5Accuracy (%, text-only)65.8

Interactive version: theaggregate.ai/model?slug=qwen-3-vl-30b-a3b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.