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

Multimodal Multi-choice on BLINK

60Accuracy

GPT-4o

37.84843.59949.3555.101Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
60
2025.12
58.3
2025.12
56.7
2025.12
56.7
56.6
2025.12
56.1
2025.12
55.1
53.6
2025.12
53.5
2025.12
53
2025.12
52.5
2025.12
51
2025.12
45.3
2025.12
43.1
2025.12
38.7