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

Mathematical Reasoning on Olympiad (P@1, ASRt, RAS)

40.86P@1

BaseRL

6.872815.696424.5233.3436Sep 30, 2025
Updated 12d ago

Evaluation Results

MethodLinks
2025.09
40.86--
2025.09
40.596.8392.17
2025.09
36.5298.7896.67
2025.09
35.1765.160.93
2025.09
34.6465.10
2025.09
34.1665.330
2025.09
32.75--
2025.09
32.75--
2025.09
31.8568.711.77
2025.09
31.8296.0287.49
2025.09
31.7667.320
2025.09
29.6970.611
2025.09
26.5873.540.45
2025.09
13.4887.769.23
2025.09
12.59--
2025.09
12.1290.6122.49
2025.09
10.9198.1983.38
2025.09
10.7992.5631.04
2025.09
8.6292.158.94
2025.09
8.1891.820