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

RealworldQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringRealworldQA
Accuracy80.2
98
Real-world Visual Question AnsweringRealWorldQA
Accuracy77.8
91
Real-world Multimodal ReasoningRealWorldQA
Accuracy75.4
40
Visual Question AnsweringRealWorldQA (test)
Accuracy79
36
Real-world QARealworldQA
Accuracy73.1
33
Spatial ReasoningRealWorldQA
Accuracy69.67
32
Spatial UnderstandingRealWorldQA
RWQA Score66.01
30
General Visual UnderstandingRealWorldQA
Accuracy67.58
28
Real-world Question AnsweringRealWorldQA
Accuracy79
27
Real-world Visual UnderstandingRealWorldQA
Accuracy65.5
24
Multimodal UnderstandingRealWorldQA
RWQA Score78
24
Vision-centric ReasoningRealWorldQA
Accuracy73.3
18
Real-world Multimodal InteractionRealWorldQA (test)
Accuracy77.8
18
Vision UnderstandingRealworldQA
Overall Score75.4
17
Real-world Multimodal InteractionRealWorldQA
RealWorldQA Score76.5
15
Visual Question AnsweringRealWorldQA 1.0 (test)
Accuracy0.6353
15
Visual UnderstandingRealWorldQA
Accuracy (Clean)68.23
7
Visual Question AnsweringRealWorldQA 2024
Score64.8
7
General visual question answeringRealWorldQA
Pass@178.4
7
General Visual Question AnsweringRealWorldQA (avg)
Score0.787
7
Spatial UnderstandingRealWorldQA
Accuracy79.61
6
General Visual Question AnsweringRealWorldQA 2024
Accuracy71.9
6
Real-World UnderstandingReal-world Understanding (RealWorldQA, MME-RW, R-Bench)
RealWorld QA Score68.2
5
GeneralRealWorldQA
Score0.779
4
Multimodal Hallucination and Real-world EvaluationRealWorldQA
Accuracy74.6
3
Showing 25 of 27 rows