Memory-Driven Role-Play on MRBench
8.43MA ScoreQwen3-8B
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Qwen3-8BCondition=MRPrompt2026.03 | 8.43 | 8.44 | 7.85 | 7.76 | 8.12 | |
| GLM-4.7Condition=MRPrompt2026.03 | 8.34 | 8.54 | 7.91 | 7.75 | 8.13 | |
| Qwen3-MaxCondition=MRPrompt2026.03 | 8.33 | 8.22 | 8.02 | 7.73 | 8.07 | |
| GLM-4-9B-ChatCondition=MRPrompt2026.03 | 8.32 | 8.47 | 7.8 | 7.65 | 8.06 | |
| Qwen3-MaxCondition=Base2026.03 | 8.31 | 8.41 | 7.89 | 7.73 | 8.08 | |
| GLM-4.7Condition=Base2026.03 | 8.31 | 8.6 | 7.87 | 7.65 | 8.11 | |
| Qwen3-8BCondition=Base2026.03 | 8.07 | 8.42 | 7.84 | 7.45 | 7.95 | |
| GLM-4-9B-ChatCondition=Base2026.03 | 8.06 | 8.35 | 7.67 | 7.36 | 7.86 |