Instruction Following Evaluation on SELF-INSTRUCT
69.48ScoreGPT-4 Turbo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4 Turboevaluation_scale=percentage-based2024.09 | 69.48 | — | — | |
| GLM-4evaluation_scale=percentage-based2024.09 | 67.73 | — | — | |
| Qwenevaluation_scale=percentage-based2024.09 | 67.15 | — | — | |
| GPT-4evaluation_scale=percentage-based2024.09 | 66.86 | — | — | |
| Claude3evaluation_scale=percentage-based2024.09 | 63.95 | — | — | |
| Aggregate Statistics2024.09 | — | 67.03 | 3.2 |