Vision-Language Benchmarks
Vision Evals Explorer
25 EVAL DATASETS · REAL SAMPLES · GRADING METRICS · PROMPT TOKEN COSTS · USE ←/→ OR CLICK A CARD
General VQADocs, OCR & ChartsMath & LogicGrounding & GUIMulti-imageHallucinationInstruction Following
CountBenchQA
General VQANUM
MMBench
General VQAMCQ
MME
General VQAY/N
MMStar
General VQAMCQ
Multilingual MMBench
General VQAMCQ
RealWorldQA
General VQAMCQ
SEED-Bench
General VQAMCQ
SimpleVQA
General VQALLM
ChartQA
Docs, OCR & ChartsNUM
DocVQA
Docs, OCR & ChartsANLS
InfographicVQA
Docs, OCR & ChartsANLS
OCRBench v1
Docs, OCR & ChartsSTR
OCRBench v2
Docs, OCR & ChartsSTR
TextVQA
Docs, OCR & ChartsVQA
LogicVista
Math & LogicMCQ
MMMU
Math & LogicMCQ
MMMU-Pro
Math & LogicMCQ
MathVista (mini)
Math & LogicEXT
RefCOCO-avg
Grounding & GUIIoU
ScreenSpot-v2
Grounding & GUIACC
BLINK
Multi-imageMCQ
MuirBench
Multi-imageMCQ
HallusionBench
HallucinationY/N
POPE
HallucinationY/N
MM-IFEval
Instruction FollowingACC