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

Mathematical Reasoning on AIME 2025 (pass@1, pass@3)

66.67Pass@1

MINDLOOM

25.059635.862346.66557.4677May 20, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
66.6773.33
2026.05
6063.33
2026.05
6073.33
2026.05
56.6766.67
2026.05
53.3363.33
2026.05
5053.33
2026.05
46.6760
2026.05
46.6756.67
2026.05
43.3356.67
2026.05
43.3346.67
2026.05
43.3370
2026.05
4053.33
2026.05
4053.33
2026.05
4060
2026.05
36.750
2026.05
36.6746.67
2026.05
36.6740
2026.05
3033.33
2026.05
3050
2026.05
26.6636.7