Reading Comprehension on RACE (3-shot)
83.31AccuracyBNRM
Evaluation Results
| Method | Links | |
|---|---|---|
| BNRMBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 83.31 | |
| PoEBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 81.39 | |
| ALBMBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 80.69 | |
| LPBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 80.3 | |
| BaseBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 79.21 | |
| LPBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 78.9 | |
| SKBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 78.82 | |
| InfoRMBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 78.72 | |
| BNRMBase Model=OpenRLHF-Llama3-8B-SFT, Evaluation Protocol=3-shot2026.02 | 75.68 | |
| BaseBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 66.5 | |
| InfoRMBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 65.2 | |
| PoEBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 60.03 | |
| ALBMBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 59 | |
| SKBase Model=Llama3.1-8B-Instruct, Evaluation Protocol=3-shot2026.02 | 53.89 |