Framework Usability Evaluation on Participant Ratings User Study (11 participants) 1.0 (test)
4.27Setup & Config RatingEKA-EVAL
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| EKA-EVAL2025.07 | 4.27 | 4.55 | 4.64 | 4.55 | 4.64 | 4.73 | |
| lm-eval-harness2025.07 | 3.73 | 3.91 | 1 | 3.64 | 4.18 | 1.64 | |
| indic-eval2025.07 | 2.55 | 3.18 | 1 | 2.55 | 2.55 | 4.55 | |
| FreeEval2025.07 | 2.55 | 2.45 | 2.73 | 2.64 | 2.36 | 1.45 | |
| OpenCompass2025.07 | 2.18 | 2.36 | 3.09 | 3.09 | 2.8 | 2.09 | |
| HELM2025.07 | 1.91 | 2.64 | 2.36 | 2.55 | 2.09 | 1.36 |