Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Commonsense reasoning on WinoGrande 1.0 (test)
Loading...
0.8137
Accuracy
Mistral-7B + DSIR
0.597068
0.653309
0.70955
0.765791
Feb 12, 2024
Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Mistral-7B + DSIR
Model=Mistral-7B, Sele...
2024.02
0.8137
Mistral-7B Base
Model=Mistral-7B, Sele...
2024.02
0.8122
Mistral-7B + Uniform
Model=Mistral-7B, Sele...
2024.02
0.8019
Mistral-7B + QuRating
Model=Mistral-7B, Sele...
2024.02
0.8011
Mistral-7B + AutoDS
Model=Mistral-7B, Sele...
2024.02
0.8003
LLaMA2-7B Base
Model=LLaMA2-7B, Selec...
2024.02
0.7585
LLaMA2-7B + DSIR
Model=LLaMA2-7B, Selec...
2024.02
0.7537
LLaMA2-7B + Uniform
Model=LLaMA2-7B, Selec...
2024.02
0.753
LLaMA2-7B + QuRating
Model=LLaMA2-7B, Selec...
2024.02
0.7466
LLaMA2-7B + AutoDS
Model=LLaMA2-7B, Selec...
2024.02
0.7451
Gemma-2B + DSIR
Model=Gemma-2B, Select...
2024.02
0.6661
Gemma-2B + AutoDS
Model=Gemma-2B, Select...
2024.02
0.6661
Gemma-2B + Uniform
Model=Gemma-2B, Select...
2024.02
0.6638
Gemma-2B + QuRating
Model=Gemma-2B, Select...
2024.02
0.6638
Gemma-2B Base
Model=Gemma-2B, Select...
2024.02
0.6054
Feedback
Search any
task
Search any
task