Automated Evaluation of Tutor Responses on Kochmar 2025 (demonstration set)
68AccuracyLoMTL
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LoMTL2025.12 | 68 | 55 | |
| GPT-52025.12 | 66 | 58 | |
| Prometheus22025.12 | 41 | 33 |
| Method | Links | ||
|---|---|---|---|
| LoMTL2025.12 | 68 | 55 | |
| GPT-52025.12 | 66 | 58 | |
| Prometheus22025.12 | 41 | 33 |