Code-related memory dialogue on MemoryCode
44.91Normalized ScoreGLM-5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GLM-5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 44.91 | 18 | |
| MiniMax-M2.5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 34.13 | 18 | |
| Qwen3-Max-Thinkingformatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 34.06 | 18 | |
| Kimi-K2.5formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 31.88 | 18 | |
| DeepSeek-V3.2formatting=multi-turn, score_aggregation=stricter, setup=normalized2026.03 | 25.99 | 18 |