Instruction Following Evaluation on SELF-INSTRUCT Ours
74.29ScoreGPT-4 Turbo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4 Turboevaluation_scale=percentage-based2024.09 | 74.29 | — | — | |
| GLM-4evaluation_scale=percentage-based2024.09 | 70.51 | — | — | |
| GPT-4evaluation_scale=percentage-based2024.09 | 68.7 | — | — | |
| Qwenevaluation_scale=percentage-based2024.09 | 67.48 | — | — | |
| Claude3evaluation_scale=percentage-based2024.09 | 66.87 | — | — | |
| Aggregate Statistics2024.09 | — | 69.57 | 7.12 |