VECTOR WIREAI INTELLIGENCE
⌘K
PKT
Refresh Models —Deals —Regulatory —Sources —

Questions this page answers

Which is better, Qwen2 VL 72B Instruct or Qwen3 VL 30B A3B Instruct?
Across 12 shared benchmarks, Qwen2 VL 72B Instruct scores higher on 6 and Qwen3 VL 30B A3B Instruct on 6. The widest gap is OCRBench, where Qwen2 VL 72B Instruct scores 877 against 90.3.

Qwen2 VL 72B Instruct vs Qwen3 VL 30B A3B Instruct

Across 12 shared benchmarks, Qwen2 VL 72B Instruct scores higher on 6 and Qwen3 VL 30B A3B Instruct on 6. The widest gap is OCRBench, where Qwen2 VL 72B Instruct scores 877 against 90.3.

AlibabavsAlibaba12 shared benchmarks6–6 head-to-head
BenchmarkQwen2 VL 72B InstructQwen3 VL 30B A3B Instruct
CC-OCR68.780.7
DocVQA_test96.595
InfoVQA_test84.582
mathvision25.960.2
MathVista70.580.1
MMMU (val) (Pass@1)64.574.2
MMMU-Pro46.262.1
MMStar68.372.1
MV-Bench73.672.3
OCRBench87790.3
RealWorldQA77.873.7
Video-MME77.874.5

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.