Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge Editing on ZsRE N = 2000
Loading...
100
Reliability
GRACE
10.56
33.78
57
80.22
May 2, 2026
Reliability
Generalization
Locality
OP Score
Updated 22d ago
Evaluation Results
Method
Method
Links
Reliability
Generalization
Locality
OP Score
GRACE
Model=Qwen2.5 7B
2026.05
100
2
100
27
HoReN
Model=Qwen2.5 7B
2026.05
100
92
100
97
GRACE
Model=DeepSeek 8B
2026.05
100
2
100
27
HoReN
Model=DeepSeek 8B
2026.05
100
95
98
98
HoReN
Model=SEA-LION 32B
2026.05
100
91
98
96
HoReN
Model=GPT-OSS 20B
2026.05
99
69
100
88
WISE
Model=SEA-LION 32B
2026.05
64
59
100
72
GRACE
Model=GPT-OSS 20B
2026.05
61
1
100
18
WISE
Model=DeepSeek 8B
2026.05
46
44
100
59
GRACE
Model=SEA-LION 32B
2026.05
43
2
100
20
WISE
Model=Qwen2.5 7B
2026.05
30
28
81
41
WISE
Model=GPT-OSS 20B
2026.05
14
14
8
12
Feedback
Search any
task
Search any
task
