Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Alignment on Harmlessness
Loading...
87.85
WR
AlignX
22.902
39.7635
56.625
73.4865
Feb 7, 2026
WR
SS
TI
Avg
Updated 1mo ago
Evaluation Results
Method
Method
Links
WR
SS
TI
Avg
AlignX
Backbone=DeepSeek-7B
2026.02
87.85
33.15
80.65
45.12
AlignX
Backbone=Mistral-7B
2026.02
86.05
33.9
78.9
43.68
AlignX
Backbone=Gemma-7B
2026.02
83.18
34.6
76.05
41.54
TrinityX
Backbone=LLaMA-2-7B
2026.02
81.5
23.1
80.17
46.19
AlignX
Backbone=LLaMA-2-7B
2026.02
80.2
23.25
76.85
44.6
H3Fusion
2026.02
59.86
33
32.03
19.63
Aligner
2026.02
25.4
7.2
-
6.06
Feedback
Search any
task
Search any
task