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

Mathematical Problem Solving on AIME (Acc, BAS, ECE, AURC)

85Accuracy

G3 Mini

-3.419.5542.565.45Apr 3, 2026Apr 8, 2026Apr 14, 2026Apr 20, 2026Apr 26, 2026May 2, 2026May 8, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.04
850.485.90.05
2026.05
81.7---
2026.05
79.2---
2026.04
750.577.20.05
2026.05
74.2---
2026.05
70.8---
2026.04
66.70.4517.60.07
2026.04
650.2424.20.1
2026.04
550.2126.80.14
2026.05
49.2---
2026.04
43.3-0.31440.26
2026.04
30-1.4254.80.5
2026.05
25---
2026.05
20---
2026.04
15-6.5284.70.8
2026.05
12.5---
2026.04
11.7-5.0673.80.77
2026.04
11.7-5.0181.40.78
2026.04
8.3-3.8152.80.82
2026.05
5.8---
2026.04
5-1.6862.50.88
2026.05
1.7---
2026.05
0---
2026.05
0---
2026.05
0---
2026.05
0---
2026.05
0---
2026.05
0---