InternVL-3-8B vs Qwen2.5 VL 72B
26 SHARED BENCHMARKSAcross 26 shared benchmarks, InternVL-3-8B scores higher on 5 and Qwen2.5 VL 72B on 21. The widest gap is OCRVQA_TEST, where Qwen2.5 VL 72B scores 66.8 against 39.
OPENGVLABVSALIBABA26 SHARED5–21 HEAD-TO-HEAD
A-Bench_VAL75.979.2
CCBench77.873.7
InHouse Dataset A40.657.2
InHouse Dataset B36.359.7
Mathverse43.755.2
MMT-Bench_VAL65.269.5
MTVQA_TEST30.331.5
OCRVQA_TEST3966.8
Q-Bench1_VAL7679.9
ScienceQA_TEST9892.5
ScienceQA_VAL97.891.3
SEEDBench_IMG7778.3
SEEDBench2_Plus69.573.3
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.