Automatic Text Evaluation on ASAP
0.379QWKRuAE-7B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RuAE-7BBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 0.379 | 0.326 | |
| CoRBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 0.316 | 0.325 | |
| DeepSEEK-R1Base Model=DeepSeek2025.12 | 0.315 | 0.279 | |
| CoRBase Model=DeepSeek2025.12 | 0.298 | 0.323 | |
| ScoringBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 0.286 | 0.298 | |
| CoRBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 0.163 | 0.258 | |
| ScoringBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 0.131 | 0.235 | |
| CoTBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 0.122 | 0.231 | |
| QWQ-32BBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 0.106 | 0.207 | |
| ScoringBase Model=DeepSeek2025.12 | 0.086 | 0.124 | |
| CoTBase Model=Qwen-2.5, Parameter Size=32B2025.12 | 0.071 | 0.223 | |
| CoTBase Model=DeepSeek2025.12 | 0.0553 | 0.174 | |
| SFT-7BBase Model=Qwen-2.5, Parameter Size=7B2025.12 | 0.017 | 0.089 | |
| M-1Type=Task-Specific Baseline2025.12 | 0.017 | -0.027 | |
| M-2Type=Task-Specific Baseline2025.12 | 0.0021 | -0.001 |