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

Multi-modal Question Answering on MMStar (test)

72.7Accuracy

Proprietary API SOTA (SenseTime, 2024)

11.13227.11643.159.084Jan 21, 2025Apr 6, 2025Jun 20, 2025Sep 4, 2025Nov 18, 2025Feb 1, 2026Apr 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.01
72.7
2025.01
63.2
2025.01
59.9
2025.01
59.6
2026.04
27.5
2026.04
27.3
2026.04
26.7
2026.04
26.5
2026.04
25.7
2026.04
25.7
2026.04
25.1
2026.04
23.9
2026.04
23.7
2026.04
23.3
2026.04
22.9
2026.04
20
2026.04
13.5