Instruction Following Evaluation on SELF-INSTRUCT seed data
72.01ScoreGPT-4 Turbo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4 Turboevaluation_scale=percentage-based2024.09 | 72.01 | — | — | |
| GLM-4evaluation_scale=percentage-based2024.09 | 71.86 | — | — | |
| Claude3evaluation_scale=percentage-based2024.09 | 71.71 | — | — | |
| Qwenevaluation_scale=percentage-based2024.09 | 71.11 | — | — | |
| GPT-4evaluation_scale=percentage-based2024.09 | 70.06 | — | — | |
| Aggregate Statistics2024.09 | — | 71.35 | 0.51 |