VECTOR WIREAI INTELLIGENCE
PKT
Refresh Models Deals Regulatory Sources

Questions this page answers

Which is better, GPT-4o mini or InternVL-2-4B?
Across 10 shared benchmarks, GPT-4o mini scores higher on 7 and InternVL-2-4B on 3. The widest gap is Video-MME Overall, where GPT-4o mini scores 61.2 against 49.9.

GPT-4o mini vs InternVL-2-4B

Across 10 shared benchmarks, GPT-4o mini scores higher on 7 and InternVL-2-4B on 3. The widest gap is Video-MME Overall, where GPT-4o mini scores 61.2 against 49.9.

OpenAIvsOpenGVLab10 shared benchmarks73 head-to-head
BenchmarkGPT-4o miniInternVL-2-4B
AI2D75.277.3
BLINK51.945.9
InterGPS (test)39.945.6
MathVista56.753.7
MMBench (dev-en)83.883.4
MMMU (val) (Pass@1)52.144.2
POPE (test)83.683.3
ScienceQA (img-test)8494.9
TextVQA (val)70.966.2
Video-MME Overall61.249.9

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.