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

Instruction Following on Vicuna (Rouge-L)

20.93Rouge-L

Teacher (Qwen1.5)

0.16125.553110.94516.3369Oct 13, 2025Nov 10, 2025Dec 9, 2025Jan 7, 2026Feb 4, 2026Mar 5, 2026Apr 3, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.03
20.93
2026.03
19.96
2026.03
19.51
2026.03
18.94
2026.03
18.89
2026.03
18.82
2026.03
18.72
2026.03
18.36
2026.03
18.18
2026.03
18.16
2025.10
18.14
2026.04
18.01
2026.03
17.85
2026.02
17.8
2025.10
17.69
2025.10
17.69
2025.10
17.62
2025.10
17.58
2025.10
17.45
2025.10
17.43
2025.10
17.36
2025.10
17.14
2026.02
17.1
2025.10
17.09
2025.10
17.02
2025.10
17.02
2025.10
16.94
2025.10
16.91
2026.02
16.9
2025.10
16.85
2025.10
16.76
2025.10
16.76
2025.10
16.64
2025.10
16.62
2025.10
16.62
2025.10
16.51
2025.10
16.43
2025.10
16.42
2025.10
16.39
2025.10
16.35
2025.10
16.34
2026.03
16.24
2026.03
16.21
2025.10
16.12
2025.10
16.12
2025.10
16.1
2026.03
16.08
2025.10
16
2025.10
15.98
2026.03
15.95
2025.10
15.85
2026.03
15.84
2025.10
15.82
2026.02
15.8
2025.10
15.71
2026.02
15.7
2026.04
15.62
2025.10
15.59
2026.03
15.59
2025.10
15.56
2026.03
15.54
2025.10
15.32
2026.03
15.28
2026.03
15.2
2025.10
14.94
2025.10
14.93
2026.03
14.93
2026.03
14.85
2025.10
14.79
2026.02
14.7
2026.03
14.66
2025.10
14.6
2026.04
13.99
2026.04
13.77
2026.04
12.62
2026.04
12.54
2026.04
12.24
2026.04
12.14
2026.04
11.82
2026.04
11.38
2026.03
10.18
2026.04
9.51
2026.04
0.96