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

Multimodal Multi-choice on MMStar (Accuracy)

65.1Accuracy

Claude3.7-Sonnet

45.75650.77855.860.822Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
65.1
2025.12
64.8
2025.12
64.5
2025.12
61.9
2025.12
61.6
2025.12
61.4
2025.12
61.3
2025.12
60.7
2025.12
60.3
2025.12
59.6
2025.12
56
54.8
2025.12
53.9
2025.12
47.1
2025.12
46.5