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

Mathematical Reasoning on AMC 23 (Accuracy, Avg, Speedup)

95Accuracy

GRPO

-1.223.77548.7573.725Mar 25, 2026Apr 6, 2026Apr 19, 2026May 1, 2026May 14, 2026May 26, 2026Jun 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
9556.66-
2026.03
9559.531.62
2026.03
92.553.541.63
2026.05
92.34--
2026.05
91.79--
2026.03
87.551.01-
2026.03
82.537.091.61
2026.05
77.03--
2026.05
75.78--
2026.05
75.39--
2026.05
75.23--
2026.03
7534.79-
2026.05
73.82--
2026.05
73.35--
2026.05
71.01--
2026.05
70.93--
2026.05
65--
2026.05
63.9--
2026.05
61.56--
2026.05
60--
2026.05
55--
2026.05
50--
2026.03
47.517.491.67
2026.03
4514.63-
2026.05
45--
2026.05
37.5--
2026.05
32.5--
2026.05
32.5--
2026.05
30--
2026.05
30--
2026.05
30--
2026.05
30--
2026.05
30--
2026.05
22.5--
2026.06
22.5--
2026.06
22.5--
2026.06
22.5--
2026.06
22.5--
2026.06
22.5--
2026.05
20--
2026.05
20--
2026.05
20--
2026.06
20--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.05
17.5--
2026.06
17.5--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
15--
2026.05
12.5--
2026.05
12.5--
2026.05
12.5--
2026.05
12.5--
2026.06
12.5--
2026.05
10--
2026.05
10--
2026.05
10--
2026.05
10--
2026.06
10--
2026.06
10--
2026.05
7.5--
2026.05
7.5--
2026.06
7.5--
2026.05
5--
2026.06
5--
2026.06
5--
2026.06
2.5--