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

Model Merging on Average of 8 benchmarks

52.79Average Accuracy

Pico

26.904433.624740.34547.0653Apr 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
52.79
2026.04
52.21
2026.04
50.43
2026.04
50.29
2026.04
50.08
2026.04
50.05
2026.04
49.97
2026.04
49.41
2026.04
48.9
2026.04
48.78
2026.04
48.7
2026.04
48.58
2026.04
48.57
2026.04
48.47
2026.04
48.27
2026.04
48.23
2026.04
48.16
2026.04
48.02
2026.04
48.01
2026.04
47.54
2026.04
47.49
2026.04
47.48
2026.04
46.79
2026.04
46.62
2026.04
46.4
2026.04
46.33
2026.04
46.21
2026.04
45.05
2026.04
45.04
2026.04
44.73
2026.04
44.3
2026.04
44.12
2026.04
44.04
2026.04
44
2026.04
43.95
2026.04
43.53
2026.04
43.28
2026.04
43.05
2026.04
42.85
2026.04
42.7
2026.04
42.57
2026.04
42.07
2026.04
41.86
2026.04
40.93
2026.04
40.89
2026.04
40.88
2026.04
40.65
2026.04
39.76
2026.04
38.59
2026.04
37.22
2026.04
36.6
2026.04
35.77
2026.04
35.23
2026.04
35.17
2026.04
34.73
2026.04
32.06
2026.04
31.73
2026.04
31.05
2026.04
31.03
2026.04
30.96
2026.04
30.52
2026.04
30.31
2026.04
30.11
2026.04
29.77
2026.04
29.57
2026.04
29.45
2026.04
29.26
2026.04
29.19
2026.04
29.09
2026.04
28.11
2026.04
28.07
2026.04
27.9