HyperAI
Command Palette
Search for a command to run...
Performance results of various models on this benchmark
Metrics
ALL (Qwen2-VL)
GVQA (Qwen2-VL)
MVQA (Qwen2-VL)
ALL (MM-Reasoner)
GVQA (MM-Reasoner)
MVQA (MM-Reasoner)
ALL (LLaMA-3.2-11B-Vision)
GVQA (LLaMA-3.2-11B-Vision)
MVQA (LLaMA-3.2-11B-Vision)
ALL
FQA
GPS
MWP
TQA
VQA
Method
Avg
MathVerse
MathVista
MathVision
6 rows total