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

Multi-modal Understanding on MuirBench

59.6Score

Vanilla

52.73654.51856.358.082Dec 9, 2024
Updated 25d ago

Evaluation Results

MethodLinks
2024.12
59.6
2024.12
59.1
2024.12
58.7
2024.12
58.2
2024.12
58.1
2024.12
57.8
2024.12
57.6
2024.12
57.2
2024.12
56.4
2024.12
56.3
2024.12
56.3
2024.12
55.3
2024.12
55.2
2024.12
54.8
2024.12
54.6
2024.12
53