Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Evaluation on HaluBench
Loading...
44.6
Score
NEO-2B
31.912
35.206
38.5
41.794
Jun 30, 2026
Score
Updated 24d ago
Evaluation Results
Method
Method
Links
Score
NEO-2B
Backbone=NEO-2B, Token...
2026.06
44.6
FastV
Backbone=NEO-2B, Token...
2026.06
43.4
ERA
Backbone=NEO-2B, Token...
2026.06
42.1
DivPrune
Backbone=NEO-2B, Token...
2026.06
42
CDPruner
Backbone=NEO-2B, Token...
2026.06
41.6
FastV
Backbone=NEO-2B, Token...
2026.06
38.4
ERA
Backbone=NEO-2B, Token...
2026.06
37.6
CDPruner
Backbone=NEO-2B, Token...
2026.06
36.9
FastV
Backbone=NEO-2B, Token...
2026.06
36.6
CDPruner
Backbone=NEO-2B, Token...
2026.06
35.3
ERA
Backbone=NEO-2B, Token...
2026.06
35.2
DivPrune
Backbone=NEO-2B, Token...
2026.06
34
DivPrune
Backbone=NEO-2B, Token...
2026.06
32.4
Feedback
Search any
task
Search any
task