Persona-based memory dialogue on PersonaMem
65.2Normalized ScoreQwen3-Max-Thinking
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen3-Max-Thinkingformatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 65.2 | 15 | |
| DeepSeek-V3.2formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 64.52 | 15 | |
| GLM-5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 63.16 | 15 | |
| Kimi-K2.5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 55.35 | 15 | |
| MiniMax-M2.5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 42.78 | 15 |