Instruction Following Evaluation on Ours hard seed data
56.73ScoreGPT-4 Turbo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-4 Turboevaluation_scale=percentage-based2024.09 | 56.73 | — | — | |
| Claude3evaluation_scale=percentage-based2024.09 | 53.75 | — | — | |
| GLM-4evaluation_scale=percentage-based2024.09 | 51.75 | — | — | |
| Qwenevaluation_scale=percentage-based2024.09 | 49.85 | — | — | |
| GPT-4evaluation_scale=percentage-based2024.09 | 47.51 | — | — | |
| Aggregate Statistics2024.09 | — | 51.92 | 10.06 |