Automatic Text Evaluation on Relish
32mAPCoR
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoRBase Model=DeepSeek2025.12 | 32 | 82.6 | |
| CoRBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 31.9 | 84.9 | |
| RuAE-7BBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 30.1 | 93.4 | |
| ScoringBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 29.4 | 81.8 | |
| CoTBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 29.3 | 82.4 | |
| CoRBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 29.3 | 82.6 | |
| ScoringBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 29.1 | 82.1 | |
| CoTBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 28.7 | 82.9 | |
| QWQ-32BBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 28.5 | 80.6 | |
| CoTBase Model=DeepSeek2025.12 | 25.6 | 79.1 | |
| M-2Type=Task-Specific Baseline2025.12 | 24.1 | 87.6 | |
| SFT-7BBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 23.4 | 87.4 | |
| ScoringBase Model=DeepSeek2025.12 | 23.1 | 77 | |
| DeepSEEK-R1Base Model=DeepSeek2025.12 | 21 | 79.9 | |
| M-1Type=Task-Specific Baseline2025.12 | 10.9 | 85.3 |