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

Mathematical Reasoning on LogicVista

73.8Accuracy

Gemini-2.5-Pro*

36.8846.46556.0565.635Sep 30, 2025
Updated 17d ago

Evaluation Results

MethodLinks
2025.09
73.8--
2025.09
70--
2025.09
50.9--
2025.09
49.7--
2025.09
48.5--
2025.09
45.6--
2025.09
42.6--
2025.09
39.7--
2025.09
38.3--
2026.04
-7081.5
2026.04
-73.876.4
2026.04
-42.659.3
2026.04
-38.344.7
2026.04
-45.652.5
2026.04
-48.554.5
2026.04
-49.753.8
2026.04
-42.850.3
2026.04
-50.661.5