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

Mathematical Reasoning on Countdown (test)

85Accuracy

RandOpt

-3.29619.62742.5565.473Jul 7, 2025Aug 30, 2025Oct 23, 2025Dec 17, 2025Feb 9, 2026Apr 4, 2026May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.05
85-
2026.05
78.9-
2026.05
74.4-
2025.10
73.7-
2026.05
69-
2026.05
68.5-
2025.10
68.2-
2025.10
67.8-
2026.05
64.8-
2026.05
63.6-
2025.10
60.6-
2026.05
58.4-
2026.05
52.7-
2025.10
52-
2025.07
51.2-
2025.10
51.1-
2025.12
46.883.7
2025.12
46.13.71
2025.07
46.1-
2026.05
42.3-
2025.07
42.2-
2025.10
41.3-
2025.10
41.1-
2025.12
40.624.15
2025.12
40.623.73
2025.12
40.234.03
2025.12
38.673.95
2025.07
37.1-
2026.05
36.9-
2026.05
35.3-
2025.07
35.2-
2025.07
34-
2026.05
32.6-
2025.07
32-
2025.10
31.9-
2025.07
31.3-
2026.05
27.5-
2025.07
27-
2026.05
27-
2026.05
26.2-
2025.07
25.8-
2025.12
255.28
2026.05
23.7-
2025.12
23.435.25
2026.05
22.5-
2025.12
21.886.48
2025.12
21.096.11
2026.05
20.9-
2025.12
20.78.62
2025.12
20.3110.92
2025.12
20.3110.39
2025.07
19.5-
2025.12
19.1410.89
2025.12
19.148.21
2025.12
18.7511.19
2025.12
18.4410.39
2025.12
17.584.97
2026.05
17.1-
2026.05
17-
2026.05
16.8-
2025.12
16.46.1
2025.12
16.0211.2
2025.07
16-
2026.05
14.8-
2025.12
14.6110.84
2026.05
14.5-
2025.12
14.458.13
2026.05
13.8-
2026.05
13-
2026.05
12.1-
2026.05
10.8-
2026.05
10.7-
2026.05
10.4-
2026.05
10-
2026.05
10-
2026.05
9.9-
2026.05
9.1-
2026.05
8.4-
2025.12
7.0310.31
2026.05
6.7-
2026.05
5.6-
2026.05
4.8-
2025.12
4.6911.15
2026.05
0.1-