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

Multimodal Reasoning on LogicVista

84.78Accuracy

InternVL2.5-38B + VRPRM

44.032854.611465.1975.7686Jun 5, 2025Aug 3, 2025Oct 1, 2025Nov 29, 2025Jan 27, 2026Mar 27, 2026May 25, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2025.08
84.78--
2025.08
83--
2025.08
79.46--
2025.08
70.02--
2025.08
68.9--
2025.08
64.43--
2026.02
61.750.5-
2025.09
61.1--
2025.06
60.9--
2025.06
60.4--
2025.06
60.4--
2025.08
60.4--
2025.06
60.1--
2025.06
59.6--
2025.06
59.1--
2026.02
58.534.7-
2025.06
58.4--
2025.06
58.2--
2025.06
58.2--
2025.06
58.2--
2025.09
58.2--
2025.06
57.7--
2025.06
56.6--
2025.06
56.4--
2025.06
56.2--
2026.02
5632.1-
2025.06
55.9--
2025.06
55.7--
2025.06
55.7--
2025.06
55.7--
2025.06
55--
2026.02
54.815.1-
2026.02
54.6--
2026.02
54.67.9-
2026.02
54.127.6-
2026.02
53.7--
2025.08
53.7--
2026.02
53.414.1-
2025.06
53--
2025.12
52.8--
2025.06
52.8--
2025.08
52.8--
2025.06
52.3--
2025.08
52.3--
2026.05
52.3--
2026.02
51.834.5-
2026.05
51.3--
2025.06
51.3--
2025.06
51.2--
2025.06
51.2--
2025.08
51--
2026.05
50--
2026.05
50--
2025.06
49.9--
2026.02
49.830.8-
2026.05
49.8--
2026.05
49.7--
2026.03
49.66--
2025.06
49.5--
2026.03
49.44--
2026.02
49.331.7-
2026.05
49.1--
2025.11
49--
2025.09
49--
2026.05
48.8--
2026.03
48.76--
2025.11
48.7--
2026.05
48.7--
2025.06
48.6--
2026.03
48.54--
2025.09
48.4--
2026.03
48.32--
2026.03
48.32--
2025.06
48.3--
2025.06
48.3--
2025.09
48.1--
2026.03
48.09--
2026.02
47.9--
2025.08
47.9--
2025.06
47.9--
2026.03
47.87--
2026.03
47.87--
2026.02
47.7--
2025.11
47.7--
2025.06
47.7--
2025.09
47.7--
2025.06
47.4--
2025.12
47.3--
2025.06
47.3--
2026.03
47.2--
2026.02
46.5--
2026.02
46.4--
2026.02
46.421.2-
2025.11
46.3--
2025.06
46.1--
2026.03
46.08--
2026.05
46--
2025.11
45.9--
2025.11
45.9--
2026.02
45.6--
Showing 100 of 173 rows