Debate on ARC-C
78.8AccuracyOPTIMA-iSFT-DPO SC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| OPTIMA-iSFT-DPO SCoptimization_strategy=iSFT-DPO, self_consistency=true2024.10 | 78.8 | 1,036.1 | |
| DITS-iSFT-DPO2025.02 | 77.6 | — | |
| OPTIMA-iSFT SCoptimization_strategy=iSFT, self_consistency=true2024.10 | 77.2 | 1,148.7 | |
| OPTIMA-iSFT-DPOoptimization_strategy=iSFT-DPO2024.10 | 77.1 | 88 | |
| Optima-iSFT-DPO2025.02 | 77.1 | — | |
| OPTIMA-iDPO SCoptimization_strategy=iDPO, self_consistency=true2024.10 | 77 | 1,091.2 | |
| SCn=82024.10 | 75.6 | 1,116.7 | |
| OPTIMA-iDPOoptimization_strategy=iDPO2024.10 | 74.5 | 97.8 | |
| Optima-iDPO2025.02 | 74.5 | — | |
| OPTIMA-iSFToptimization_strategy=iSFT2024.10 | 74.1 | 92.2 | |
| Optima-iSFT2025.02 | 74.1 | — | |
| MAD2024.10 | 71.4 | 478 | |
| MAD2025.02 | 71.4 | — | |
| CoT2024.10 | 65.2 | 138.9 | |
| CoT2025.02 | 65.2 | — | |
| AutoForm2024.10 | 60.2 | 221.2 | |
| AutoForm2025.02 | 60.2 | — |