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

Mathematical Problem Solving on MATH (Latency and Performance)

3.94Average Time

CoT

0.581623.250845.9268.5892Jul 20, 2025
Updated 21d ago

Evaluation Results

MethodLinks
2025.07
3.949.91-
2025.07
4.4917.752.29
2025.07
4.9616.8-35.81
2025.07
5.3826.6611.2
2025.07
7.3216.941.48
2025.07
8.1221.81-21.57
2025.07
8.3515.46-
2025.07
8.6822.41-30.2
2025.07
9.2423.55-19.83
2025.07
9.4615.63-
2025.07
10.5737.37-15.24
2025.07
10.6934.11-60.24
2025.07
11.2634.45-8.93
2025.07
12.852.61-
2025.07
12.8438.41-20.81
2025.07
15.5243.38-
2025.07
15.6547.86-11.36
2025.07
15.9437.26-21.96
2025.07
18.5859.22-
2025.07
19.3496.382.03
2025.07
19.759.94-35.07
2025.07
20.8358.06-36.95
2025.07
21.8362.78-31.57
2025.07
27.1845.38-
2025.07
28.7591.93-3.08
2025.07
30.6178.8-0.07
2025.07
31.1294.35-
2025.07
31.3872.22-6.65
2025.07
35.1277.09-1.78
2025.07
36.4178.87-
2025.07
42.5995.01-
2025.07
43.28114.81-92.39
2025.07
46.68113.52-93.68
2025.07
51.32160.16-79.94
2025.07
55.64137.16-70.04
2025.07
58.35163.97-76.13
2025.07
59.32207.2-
2025.07
80.2207.32-32.78
2025.07
87.9240.1-