Natural Language Inference on AX-g
51.97AccuracyQuRating
Evaluation Results
| Method | Links | |
|---|---|---|
| QuRatingModel Backbone=GPT-2 XL2026.02 | 51.97 | |
| DCLM-FastTextModel Backbone=GPT-2 XL2026.02 | 51.97 | |
| PPLModel Backbone=GPT-2 XL2026.02 | 51.12 | |
| GREATSModel Backbone=GPT-2 XL2026.02 | 50.84 | |
| OPUSModel Backbone=GPT-2 XL2026.02 | 50.56 | |
| RandomModel Backbone=GPT-2 XL2026.02 | 50 | |
| FineWeb-EduModel Backbone=GPT-2 XL2026.02 | 50 | |
| DSIRModel Backbone=GPT-2 XL2026.02 | 49.44 | |
| UltraFinewebModel Backbone=GPT-2 XL2026.02 | 48.31 |