Sentence Completion
Papers
Showing 81–90 of 91 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CompassMTL 567M with Tailor | Accuracy | 96.1 | — | Unverified |
| 2 | CompassMTL 567M | Accuracy | 95.6 | — | Unverified |
| 3 | DeBERTa-Large 304M (classification-based) | Accuracy | 95.6 | — | Unverified |
| 4 | GPT-4 (10-shot) | Accuracy | 95.3 | — | Unverified |
| 5 | LLaMA3+MoSLoRA | Accuracy | 95 | — | Unverified |
| 6 | LLaMA-2 13B + MixLoRA | Accuracy | 94.7 | — | Unverified |
| 7 | DeBERTa-Large 304M | Accuracy | 94.7 | — | Unverified |
| 8 | Unicorn 11B (fine-tuned) | Accuracy | 93.9 | — | Unverified |
| 9 | LLaMA-3 8B + MixLoRA | Accuracy | 93.3 | — | Unverified |
| 10 | LLaMA-2 7B + MixLoRA | Accuracy | 93.1 | — | Unverified |