Interactive Text Editing (Continuation) on CoAuthor (test)
4.48Quality ScoreGPT4
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT4Constraint=None2024.06 | 4.48 | — | — | |
| GPT3.5Constraint=L2024.06 | 4.44 | 6,200 | 62 | |
| GPT4Constraint=K2024.06 | 4.44 | 5,600 | 56 | |
| GPT4Constraint=L2024.06 | 4.44 | 5,500 | 55 | |
| GPT3.5Constraint=None2024.06 | 4.4 | — | — | |
| GPT4Constraint=Avg.2024.06 | 4.4 | 5,700 | 56 | |
| GPT3.5Constraint=Avg.2024.06 | 4.38 | 4,300 | 43 | |
| GPT3.5Constraint=K&L2024.06 | 4.36 | 3,100 | 31 | |
| GPT3.5Constraint=K2024.06 | 4.32 | 3,600 | 36 | |
| Ctrl-GConstraint=L2024.06 | 4.27 | 10,000 | 97 | |
| GPT4Constraint=K&L2024.06 | 4.26 | 5,900 | 57 | |
| Ctrl-GConstraint=None2024.06 | 4.13 | — | — | |
| Ctrl-GConstraint=Avg.2024.06 | 4.08 | 10,000 | 92 | |
| Ctrl-GConstraint=K2024.06 | 3.98 | 10,000 | 89 | |
| Ctrl-GConstraint=K&L2024.06 | 3.96 | 10,000 | 90 | |
| TULU2Constraint=K&L2024.06 | 3.88 | 100 | 1 | |
| TULU2Constraint=L2024.06 | 3.87 | 3,300 | 31 | |
| TULU2Constraint=Avg.2024.06 | 3.83 | 2,300 | 21 | |
| TULU2Constraint=None2024.06 | 3.8 | — | — | |
| TULU2Constraint=K2024.06 | 3.77 | 3,500 | 30 |