Automated Essay Scoring analytic feedback on AES Analytic Aspects Dataset (Negative Feedback)
44.68IntGPT4.1
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT4.1Model Version=GPT-4.12026.05 | 44.68 | 49.2 | 24.68 | 22.52 | 37.71 | 45.45 | 20.52 | 38.2 | 16.37 | 37.75 | 33.71 | |
| Llama3.1Model Size=70B2026.05 | 40.92 | 34 | 24.66 | 20.51 | 25.55 | 28.18 | 20.2 | 51.43 | 20.11 | 42.93 | 30.85 | |
| ORDescription=Operational Rater2026.05 | 40.77 | 30.76 | 26.1 | 22.37 | 34.1 | 23.67 | 23.83 | 33.25 | 32.79 | 45.87 | 31.35 | |
| Qwen2.5Model Size=72B2026.05 | 31.96 | 37.2 | 16.75 | 17.7 | 15.71 | 36.52 | 27.71 | 46.13 | 12.72 | 40.51 | 28.29 |