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

Mathematical Reasoning on AIME 2025 (Accuracy, Avg, Speedup)

99.2Accuracy

TRICE-30B

36.38452.6926985.308Oct 8, 2025Nov 20, 2025Jan 2, 2026Feb 14, 2026Mar 29, 2026May 11, 2026Jun 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.05
99.2--
2026.05
98.3--
2026.05
96.7--
2026.05
96.7--
2026.06
96.7--
2026.06
96.7--
2026.06
96.1--
2026.06
96--
2026.05
95--
2026.06
94.6--
2026.05
94.2--
2026.06
94.1--
2026.06
93.3--
2026.06
93.1--
2026.06
92.8--
2026.06
92.5--
2026.06
91.7--
2026.06
91.4--
2026.05
90--
2026.06
90--
2026.05
89.2--
2026.06
88.9--
2026.05
88.8--
2026.06
87.5--
2026.05
86.7--
2026.06
86.7--
2026.06
86.67--
2026.05
86.4--
2026.05
85.8--
2026.05
84.7--
2026.06
83.33--
2026.06
83.33--
2026.05
82.5--
2026.06
80--
2026.05
79.2--
2026.05
75.8--
2026.05
74.1--
2026.06
73.33--
2026.06
73.33--
2026.06
72--
2025.10
70--
2025.10
69--
2026.05
67.5--
2026.05
67.0876.49-
2026.05
67.08--
2025.10
67--
2026.05
66.8--
2026.06
66.7--
2025.10
66--
2026.05
65.8375.4-
2026.05
65.83--
2026.05
64.9--
2026.05
63.3--
2026.06
63.3--
2026.06
63.3--
2025.10
63--
2025.10
63--
2026.05
60.6--
2026.05
60.2--
2025.10
60--
2025.10
60--
2026.05
6073.18-
2026.05
60--
2026.06
60--
2026.05
58.9--
2026.06
56.7--
2026.06
56.7--
2026.06
53.33--
2026.06
53.3--
2026.06
53.3--
2025.10
53--
2025.10
52--
2026.06
50--
2026.05
49.1--
2026.05
49.1--
2026.05
48.8--
2025.10
48--
2025.10
48--
2025.10
48--
2026.06
46.7--
2026.03
46.6753.541.63
2026.03
46.6759.531.62
2026.04
43.9--
2025.10
43.7--
2026.06
43.3--
2026.06
43.3--
2025.10
42.6--
2025.10
42.6--
2025.10
42.3--
2025.10
41.7--
2025.10
41.7--
2025.10
41.5--
2026.06
41.5--
2026.06
40.5--
2026.03
4051.01-
2026.03
4056.66-
2025.10
40--
2026.06
40--
2025.10
39--
2026.06
38.8--
Showing 100 of 378 rows