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
327
Real-world Visual Question AnsweringRealWorldQA
Accuracy79.35
183
Real-world Visual UnderstandingRealWorldQA
Accuracy81.4
110
Real-world QARealworldQA
Accuracy81.8
75
Vision-centric ReasoningRealWorldQA
Accuracy75.4
68
General Visual UnderstandingRealWorldQA
Accuracy71.3
64
Real-world Multimodal ReasoningRealWorldQA
Accuracy75.4
62
Real-world Question AnsweringRealWorldQA
Overall Score78.7
58
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
Perception and ReasoningRealWorldQA
Score74.2
37
Multimodal UnderstandingRealWorldQA
RWQA Score78
33
Visual Question AnsweringRealWorldQA xAI 2024 (test)
Accuracy72.81
32
General Visual Question AnsweringRealWorldQA
Score73.1
32
Real-world Visual UnderstandingRealWorldQA (test)
Final Performance77.1
30
Spatial UnderstandingRealWorldQA
RWQA Score66.01
30
Visual Question AnsweringRealWorldQA (RWQA)
Score68.5
26
General Visual Question AnsweringRealWorldQA
Accuracy71.9
25
General UtilityRealWorldQA
RealWorldQA Score72.2
21
Real-world Multimodal UnderstandingRealWorldQA
Accuracy73.99
21
General Reasoning & UnderstandingRealWorldQA
Accuracy (RealWorldQA)72.6
21
Real-world Multimodal InteractionRealWorldQA (test)
Accuracy77.8
18
Showing 25 of 56 rows