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

RealworldQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringRealworldQA
Accuracy80.2
259
Real-world Visual Question AnsweringRealWorldQA
Accuracy79.35
173
Real-world Visual UnderstandingRealWorldQA
Accuracy81.4
110
Vision-centric ReasoningRealWorldQA
Accuracy75.4
66
General Visual UnderstandingRealWorldQA
Accuracy71.3
62
Real-world QARealworldQA
Accuracy75.7
62
Real-world Question AnsweringRealWorldQA
Overall Score78.7
58
Real-world Multimodal ReasoningRealWorldQA
Accuracy75.4
57
Spatial ReasoningRealWorldQA
Accuracy69.67
52
Visual Question AnsweringRealWorldQA (test)
Accuracy79
47
Multimodal ReasoningRealWorldQA
Accuracy81.39
40
Multimodal ReasoningRealWorldQA
Mean@8 Accuracy70.46
40
Real-world Visual UnderstandingRealWorldQA
Score72.29
39
Multimodal UnderstandingRealWorldQA
RWQA Score78
33
Perception and ReasoningRealWorldQA
Score74.2
31
Spatial UnderstandingRealWorldQA
RWQA Score66.01
30
General UtilityRealWorldQA
RealWorldQA Score72.2
21
Real-world Multimodal UnderstandingRealWorldQA
Accuracy73.99
21
General Reasoning & UnderstandingRealWorldQA
Accuracy (RealWorldQA)72.6
21
Real-world Visual UnderstandingRealWorldQA (test)
Final Performance77.1
20
General Visual Question AnsweringRealWorldQA
Score73.1
20
Real-world Multimodal InteractionRealWorldQA (test)
Accuracy77.8
18
Vision UnderstandingRealworldQA
Overall Score75.4
17
Vision-Centric PerceptionRealWorldQA
Accuracy69.3
16
Real-world PerceptionRealWorldQA
Accuracy65.1
16
Showing 25 of 48 rows