Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MM-Vet

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal UnderstandingMM-Vet
MM-Vet Score82.2
531
Multimodal ReasoningMM-Vet
MM-Vet Score86.2
431
Multimodal Capability EvaluationMM-Vet
Score85.6
345
Multimodal EvaluationMM-Vet
Score64
180
Visual UnderstandingMM-Vet
MM-Vet Score76.9
142
Multimodal UnderstandingMM-VET (test)
Total Score67.6
120
Large Multimodal Model EvaluationMM-Vet
Average Score54.5
61
Vision-Language UnderstandingMM-Vet
Total Score72.16
43
Visual ReasoningMM-Vet
Score82.7
40
Visual Question AnsweringMM-Vet
MM-Vet ASR Accuracy75.8
33
Multimodal Question AnsweringMM-Vet
Total Score68.3
24
Multimodal UnderstandingMM-Vet v2
MM-Vet v2 Score71.8
23
Visual Reasoning and Instruction FollowingMM-Vet
Overall Score75.2
23
Multi-modal Reasoning and UnderstandingMM-Vet
Accuracy74.6
20
Multi-modal understandingMM-Vet
Rec46.9
19
Multimodal ReasoningMM-Vet
Pass@1 Accuracy76.2
16
Multimodal UnderstandingMM-Vet OOD
Accuracy96.33
14
Malicious Prompt DetectionMM-Vet OOD
FPR3.67
14
Multimodal UnderstandingMM-Vet
Relative Speed (RelSpd)193.2
13
Multimodal Reasoning and Tool-useMM-Vet
MM-Vet Tool-use Score44.7
13
Multimodal Capability EvaluationMM-Vet 58
Score38.2
13
Multimodal UnderstandingMM-Vet benign queries
Recognition Score54.5
12
General EvaluationMM-VET
REC39.5
12
Multimodal UnderstandingMM-Vet (5% Forget Set)
Average Score43.9
12
Multimodal EvaluationMM-Vet v2
Score81.6
10
Showing 25 of 44 rows