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

Mathematical Reasoning on AIME24 Math (Performance %)

50Performance (%)

RLKV

-211.52538.5Oct 9, 2025
Updated 6d ago

Evaluation Results

MethodLinks
2025.10
50
2025.10
50
2025.10
46.7
2025.10
46.7
2025.10
43.3
2025.10
43.3
2025.10
40
2025.10
40
2025.10
36.7
2025.10
36.7
2025.10
33.3
2025.10
33.3
2025.10
30
2025.10
30
2025.10
30
2025.10
26.7
2025.10
26.7
2025.10
26.7
2025.10
26.7
2025.10
26.7
2025.10
20
2025.10
20
2025.10
20
2025.10
20
2025.10
20
2025.10
13.3
2025.10
13.3
2025.10
13.3
2025.10
13.3
2025.10
10
2025.10
10
2025.10
6.7
2025.10
6.7
2025.10
6.7
2025.10
6.7
2025.10
3.3
2025.10
3.3
2025.10
3.3
2025.10
3.3
2025.10
3.3
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0
2025.10
0