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

General Task on MMStar (accuracy)

76.2Accuracy

Seed1.5-VL

30.85642.62854.466.172Oct 2, 2025Nov 11, 2025Dec 21, 2025Jan 30, 2026Mar 11, 2026Apr 20, 2026May 30, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
76.2
2025.10
70.8
2025.10
69.5
2026.05
68.2
2026.05
65.9
2026.05
65
2026.05
64.1
2026.05
63.6
2026.05
63
2025.10
62.27
2025.10
62.27
2026.05
61.9
2026.05
61.9
2025.10
61.7
2025.10
61.67
2026.05
61.1
2026.05
60.7
2026.05
60.2
2026.05
60.1
2026.05
59.6
2026.05
59
2026.05
58.9
2026.05
57.8
2026.05
56.8
2026.05
56.1
2026.05
56
2025.10
55.9
2026.05
55.8
2026.05
54.6
2026.05
36.3
2026.05
35.8
2026.05
35.2
2026.05
35.1
2026.05
34.1
2026.05
33.5
2026.05
32.6