Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Counterfactual Faithfulness on SNLI
Loading...
0.243
Faithfulness Score
Tulu-2 13B
0.06932
0.11441
0.1595
0.20459
Dec 8, 2025
Faithfulness Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Faithfulness Score
Tulu-2 13B
Training Setup=No-Trai...
2025.12
0.243
Tulu-2 13B
Training Setup=w/ Pred...
2025.12
0.216
Tulu-2 13B
Training Setup=w/ Expl...
2025.12
0.192
Tulu-2 7B
Training Setup=w/ Expl...
2025.12
0.17
Tulu-2 7B
Training Setup=w/ Pred...
2025.12
0.079
Tulu-2 7B
Training Setup=No-Trai...
2025.12
0.076
Feedback
Search any
task
Search any
task