Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prosocial Alignment on NicheHazardQA (test)
Loading...
78.2
MIP
PROSOCIALALIGN
42.84
52.02
61.2
70.38
Dec 6, 2025
MIP
Updated 4d ago
Evaluation Results
Method
Method
Links
MIP
PROSOCIALALIGN
Backbone=llama
2025.12
78.2
PP
Backbone=llama
2025.12
70.1
PROATTR-GEN-PCA
Backbone=mistral
2025.12
68.8
PROSOCIALALIGN
Backbone=mistral
2025.12
68.1
DIREG
Backbone=llama
2025.12
67.4
PV-ARM-SUM
Backbone=llama
2025.12
64.1
PROATTR-GEN-PCA
Backbone=llama
2025.12
63.9
DIREG
Backbone=mistral
2025.12
59.4
PP
Backbone=mistral
2025.12
58.6
SAFE-ARITH
Backbone=llama
2025.12
53.9
CTRL-GEN
Backbone=llama
2025.12
51.8
CTRL-GEN
Backbone=mistral
2025.12
51.8
SAFE-ARITH
Backbone=mistral
2025.12
45.3
PV-ARM-SUM
Backbone=mistral
2025.12
44.2
Feedback
Search any
task
Search any
task