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

Multimodal Understanding on MMBench (test)

90.9Accuracy

Counting

20.28438.61756.9575.283Oct 13, 2023Mar 27, 2024Sep 9, 2024Feb 22, 2025Aug 7, 2025Jan 20, 2026Jul 5, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
90.9----
2026.07
90.8----
2026.07
90.8----
2026.07
90.5----
2024.05
84.2----
2024.05
80.6----
2024.05
80.21----
2024.05
79.3----
2024.02
78.1----
2024.05
77----
2024.02
77----
2024.05
76.8----
2024.05
76.7----
2024.02
75.7----
2024.05
75.1----
2025.01
74.5----
2025.01
74.4----
2024.05
73.6----
2024.05
73.2----
2025.01
72.3----
2024.05
72.3----
2025.01
72.1----
2024.05
70----
2026.04
70----
2024.02
69.7----
2023.12
69.5----
2025.01
69.3----
2025.01
69.3----
2023.10
69.2----
2024.02
69.1----
2024.02
69.1----
2025.01
68.5----
2024.02
68.45----
2024.02
68.4----
2025.01
68.2----
2025.01
68----
2024.05
67.8----
2023.10
67.8----
2025.01
67.7----
2025.01
67.5----
2025.01
67----
2023.12
67----
2025.01
66.5----
2025.01
66.5----
2025.01
66.4----
2024.02
66.19----
2023.10
66.1----
2023.12
66----
2024.02
66----
2023.10
65.2----
2025.01
64.5----
2025.01
64.3----
2023.10
63.9----
2024.05
63.3----
2026.04
63.2----
2026.04
62.8----
2026.04
62----
2023.12
61.8----
2025.01
60.9----
2026.04
60.8----
2024.05
60.7----
2025.01
60.2----
2024.02
60.2----
2026.04
59.8----
2025.01
57.9----
2026.04
56.5----
2025.01
39.8----
2025.01
38.3----
2023.10
33.9----
2024.02
33.9----
2023.10
23----
2023.11
-23---
2023.11
-36.2---
2023.11
-46.6---
2023.11
-36---
2023.11
-39.5---
2023.11
-48.3---
2023.11
-60.6---
2023.11
-64.3---
2023.11
-64.5---
2023.12
-46.6---
2023.12
-36---
2023.12
-39.5---
2023.12
-48.3---
2023.12
-60.6---
2023.12
-36.2---
2023.12
-37.8---
2023.12
-23---
2023.12
-24.5---
2023.12
-64.3---
2023.12
-64.5---
2023.12
--38.7--
2023.12
--24.3--
2023.12
--41--
2023.12
--49.4--
2023.12
--36--
2023.12
--48.2--
2023.12
--58.8--
2023.12
--38.2--
2023.12
--60.6--
Showing 100 of 163 rows