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

General Language Evaluation on 14-Benchmark Evaluation Suite

62.05Average Score

Qwen-2.5-7B-TuluSFT

31.453239.396647.3455.2834Nov 14, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.11
62.05
2025.11
61.62
2025.11
60.48
2025.11
59.56
2025.11
58.52
2025.11
58.39
2025.11
58.11
2025.11
57.02
2025.11
56.55
2025.11
56.04
2025.11
55.36
2025.11
54.16
2025.11
53.96
2025.11
52.09
2025.11
52.04
2025.11
51.74
2025.11
51.39
2025.11
50.87
2025.11
50.55
2025.11
50.44
2025.11
50.16
2025.11
50.09
2025.11
50.02
2025.11
49.8
2025.11
49.6
2025.11
49.55
2025.11
49.17
2025.11
49.14
2025.11
48.27
2025.11
47.95
2025.11
47.66
2025.11
47.26
2025.11
47.08
2025.11
46.88
2025.11
46.66
2025.11
46.61
2025.11
46.58
2025.11
46.51
2025.11
46.51
2025.11
46.45
2025.11
45.95
2025.11
45.92
2025.11
45.78
2025.11
45.69
2025.11
45.59
2025.11
45.38
2025.11
45.06
2025.11
45.04
2025.11
44.9
2025.11
44.88
2025.11
43.94
2025.11
43.72
2025.11
43.69
2025.11
43.53
2025.11
38.74
2025.11
38.55
2025.11
37.78
2025.11
37.63
2025.11
36.57
2025.11
36.56
2025.11
36.17
2025.11
35.68
2025.11
35.31
2025.11
35.3
2025.11
35.13
2025.11
34.99
2025.11
34.78
2025.11
34.05
2025.11
34.04
2025.11
33.66
2025.11
33.29
2025.11
32.63