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

Symbolic Reasoning on Last Letter Concatenation

90.4Accuracy

Zero-Shot CoT

-3.61620.79245.269.608Oct 7, 2022May 14, 2023Dec 19, 2023Jul 25, 2024Mar 1, 2025Oct 6, 2025May 13, 2026
Updated 20d ago

Evaluation Results

MethodLinks
2023.10
90.4
2026.01
84.2
2026.01
82.8
2026.03
79.33
2026.01
78
2026.01
77.47
2026.03
77.33
2026.01
75.4
2023.06
74.5
2026.01
74.2
2026.03
74
2023.06
73
2026.01
72.8
2026.03
72.67
2026.01
72.2
2026.03
71.33
2026.05
71.2
2023.06
69.7
2026.05
69
2023.06
68.3
2026.01
66.8
2026.01
66.8
2026.05
65.7
2026.01
65.4
2023.06
65.4
2023.06
63.1
2026.01
62.53
2023.06
61.1
2026.01
61
2026.05
61
2026.05
60.1
2022.10
59.7
2023.06
59.7
2023.06
59.4
2022.10
59
2023.06
59
2023.10
58.2
2026.05
58.2
2026.03
58
2022.10
57.6
2023.06
57.6
2026.05
56.1
2026.01
56
2026.01
55.2
2026.05
55.2
2026.01
54.8
2026.05
51.3
2023.10
50.8
2026.05
49.6
2026.03
46
2026.03
40
2026.03
37.86
2026.03
35.33
2026.03
33.33
2026.03
24
2026.01
13.6
2026.01
11
2026.01
7.86
2026.01
6.2
2026.01
6
2026.01
5.4
2026.01
5.2
2026.01
4.8
2023.10
3.2
2022.10
0.2
2022.10
0.2
2023.06
0.2
2023.06
0