Science Reasoning on AI2ARC
92.92AccuracyD-RPC
Evaluation Results
| Method | Links | |
|---|---|---|
| D-RPCStudent Model=Llama 3.1 8B Instruct2026.05 | 92.92 | |
| FreeformStudent Model=Llama 3.1 8B Instruct2026.05 | 92.41 | |
| D-RPCStudent Model=Qwen 3 1.7B2026.05 | 88.82 | |
| CoTStudent Model=Qwen 3 1.7B2026.05 | 88.78 | |
| FreeformStudent Model=Qwen 3 1.7B2026.05 | 88.7 | |
| CoTStudent Model=Llama 3.1 8B Instruct2026.05 | 87.92 | |
| SGFTStudent Model=Llama 3.1 8B Instruct2026.05 | 86.71 | |
| DCoTStudent Model=Qwen 3 1.7B2026.05 | 85.74 | |
| DCoTStudent Model=Llama 3.1 8B Instruct2026.05 | 80.78 | |
| SGFTStudent Model=Qwen 3 1.7B2026.05 | 75.99 |