Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Chain-of-Thought Generation on e-SNLI (test)
Loading...
3.49
GPT-4 Score
Gold
2.3772
2.6661
2.955
3.2439
Mar 5, 2024
GPT-4 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
GPT-4 Score
Gold
Self-consistency=true
2024.03
3.49
DSS
Self-consistency=false
2024.03
3.24
DSS
Self-consistency=true
2024.03
3.18
MI-based distillation
Self-consistency=true
2024.03
3.17
MI-based distillation
Self-consistency=false
2024.03
3.03
Gold
Self-consistency=false
2024.03
2.42
Feedback
Search any
task
Search any
task