Qwen 2 VL 72B Instruct — benchmark results
Alibaba's open 72B vision-language flagship (September 2024) with dynamic-resolution image handling and 20-minute-plus video understanding. Provider: Alibaba. Released 2024-09-19. Access: Open.
Unified ELO 1539 ± 14, rank #649 of 1776 rated models, from 43 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (EgoSchema) | 77.9 | Score (%) | 100 |
| LLM Stats (TextVQA) | 85.5 | Score (%) | 100 |
| Open LLM Leaderboard - MMLU-Pro | 52.41 | Score | 99.1 |
| KOFFVQA - Object Attributes | 86.67 | Score (%) | 98.8 |
| Open LLM Leaderboard - BBH | 56.31 | Score | 98.4 |
| Open LLM Leaderboard - GPQA | 18.34 | Score | 96.8 |
| Open LLM Leaderboard - MATH Level 5 | 34.44 | Score | 84.9 |
| Open LLM Leaderboard - MuSR | 15.89 | Score | 84.2 |
| KOFFVQA - Table Understanding | 84.33 | Score (%) | 81.5 |
| LLM Stats (ChartQA) | 88.3 | Score (%) | 78.3 |
| LLM Stats (DocVQAtest) | 96.5 | Score (%) | 75 |
| KOFFVQA - Commonsense Reasoning | 83.11 | Score (%) | 74.1 |
Interactive version: theaggregate.ai/model?slug=qwen-2-vl-72b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.