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

Mathematical Reasoning on Math500 (Accuracy, Avg, Speedup)

87.18Accuracy

STRIDE

21.680838.685455.6972.6946Mar 25, 2026Apr 7, 2026Apr 21, 2026May 4, 2026May 18, 2026May 31, 2026Jun 14, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
87.1849.24-
2026.06
86.9647.27-
2026.06
86.4846.63-
2026.06
86.4347.09-
2026.06
83.7545.28-
2026.03
81.4559.531.62
2026.03
81.2556.66-
2026.06
80.1744.71-
2026.03
80.0453.541.63
2026.03
79.6451.01-
2026.06
78.5542.18-
2026.06
78.2541.8-
2026.06
78.0741.61-
2026.06
77.5842.01-
2026.06
63.829.4-
2026.06
62.434.1-
2026.03
62.337.091.61
2026.03
60.8934.79-
2026.06
57.1925.87-
2026.06
55.4823.97-
2026.06
55.2523.3-
2026.06
55.1523.41-
2026.06
54.2222.92-
2026.06
50.217.78-
2026.03
29.0317.491.67
2026.03
24.214.63-