MMBench

Benchmarks

Task Name	Dataset Name	SOTA Result
Multimodal Understanding	MMBench	Accuracy88.8	367
Multimodal Model Evaluation	MMBench	Accuracy87.8	180
Multimodal Understanding	MMBench CN	Accuracy88.5	162
Multimodal Model Evaluation	MMBench Chinese	Accuracy82.6	121
Multimodal Evaluation	MMBench	MMB Score79.7	118
Vision Understanding	MMBench	Accuracy85	104
Multimodal Benchmarking	MMBench-CN	Score92.39	73
Multimodal Benchmark	MMBench (MMB)	Accuracy81.8	70
Multimodal Understanding	MMBench Chinese	MMB Benchmark (CN)89.5	70
Multimodal Understanding	MMBench (MMB)	Accuracy86.3	69
Multimodal Understanding	MMBench (test)	Overall Score81.2	65
Multimodal Benchmarking	MMBench	Score83.4	62
Multimodal Benchmarking	MMBench English	Accuracy70.4	61
Multimodal Understanding	MMBench (dev)	Accuracy80.41	58
Multimodal Evaluation	MMBench CN	Accuracy74.3	57
Multimodal Understanding	MMBench English	MMB Score90.8	55
Multimodal Reasoning	MMBench	Accuracy87	50
Multimodal Understanding (Chinese)	MMBench Chinese	Accuracy91	47
Multimodal Reasoning	MMBench (dev)	Accuracy87.6	47
GUI Grounding	MMBench-GUI L2 (test)	Error (Windows, Basic)1.5	46
Multi-modal Benchmark	MMBench	Accuracy83.3	40
Visual Question Answering	MMBench-CN	Accuracy93.13	40
Multi-modal Understanding	MMBench (dev)	Overall Score80.6	40
Multi-modal Understanding	MMBench EN	Overall Score86.3	39
Multimodal Understanding	MMBench en (dev)	Score84.2	38

Showing 25 of 116 rows