Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MM-Vet

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal UnderstandingMM-Vet
MM-Vet Score82.2
418
Multimodal Capability EvaluationMM-Vet
Score85.6
282
Multimodal ReasoningMM-Vet
MM-Vet Score80.8
281
Multimodal EvaluationMM-Vet
Accuracy85.6
122
Multimodal UnderstandingMM-VET (test)
Total Score67.6
114
Visual UnderstandingMM-Vet
MM-Vet Score76.9
102
Large Multimodal Model EvaluationMM-Vet
Average Score54.5
58
Vision-Language UnderstandingMM-Vet
Total Score72.16
43
Visual ReasoningMM-Vet
Score82.7
34
Visual Question AnsweringMM-Vet
MM-Vet ASR Accuracy73.1
27
Multimodal Question AnsweringMM-Vet
Total Score68.3
24
Visual Reasoning and Instruction FollowingMM-Vet
Overall Score75.2
23
Multimodal Reasoning and Tool-useMM-Vet
MM-Vet Tool-use Score44.7
13
Multimodal Capability EvaluationMM-Vet 58
Score38.2
13
General EvaluationMM-VET
REC39.5
12
Multi-modal Reasoning and UnderstandingMM-Vet
Accuracy53.4
12
Multimodal UnderstandingMM-Vet (5% Forget Set)
Average Score43.9
12
Multi-modal understandingMM-Vet
Rec46.9
11
Multimodal UnderstandingMM-Vet v2
MM-Vet v2 Score71.8
11
Multimodal UnderstandingMM-Vet
Average Accepted Length (tau)3.82
10
Conversational Visual QAMM-Vet (test)
MM-Vet Score52.8
10
General Visual Question AnsweringMM-Vet
Accuracy69.1
10
3D Multimodal Comprehension3D MM-Vet (test)
Recognition Accuracy65.1
9
Multimodal Utility EvaluationMM-Vet benign
FRR3.21
8
Multimodal ReasoningMM-Vet
Accuracy36.2
8
Showing 25 of 31 rows