Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Preference Alignment on DeepPref
Loading...
84.7
AccPF
CDRA
20.532
37.191
53.85
70.509
Oct 13, 2025
AccPF
AccDA
AccMis
mth
mdm
mie
Updated 1mo ago
Evaluation Results
Method
Method
Links
AccPF
AccDA
AccMis
mth
mdm
mie
CDRA
2025.10
84.7
76.3
32.3
47
65
42.7
GRPO
2025.10
83.7
70.3
30.7
46.3
58.7
34
SFT
2025.10
83.3
75
34.7
46.7
63.7
40.3
CoT
2025.10
59.7
49.3
50.3
39
25.3
0.7
TPO
2025.10
55.3
36.3
56.3
29.7
15.7
0
Few-shot
Mode=Few-shot
2025.10
49.7
32.7
61.3
29
10.7
0.3
Zero-shot
Mode=Zero-shot
2025.10
23
6.7
76
4.7
3
0
Feedback
Search any
task
Search any
task