Long-context Benchmark Evaluation on CL-Bench (unfiltered)
6.49DK ScoreNo Memory
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| No MemoryModel=Qwen3-4B2026.06 | 6.49 | 1.51 | 3.82 | 4.24 | 4.63 | |
| No MemoryModel=Qwen3-8B2026.06 | 6.49 | 1.01 | 5.31 | 4.06 | 4.9 | |
| TMEMModel=Qwen3-4B2026.06 | 6.49 | 2.51 | 5.1 | 4.06 | 5 | |
| TMEMModel=Qwen3-8B2026.06 | 6.33 | 1.51 | 6.37 | 4.06 | 5.16 | |
| MemAgentModel=Qwen3-8B2026.06 | 6.18 | 1.01 | 5.73 | 4.06 | 4.9 | |
| AMEMModel=Qwen3-8B2026.06 | 5.88 | 1.51 | 4.46 | 3.53 | 4.37 | |
| AMEMModel=Qwen3-4B2026.06 | 5.28 | 1.51 | 3.82 | 3.89 | 4.11 | |
| MemAgentModel=Qwen3-4B2026.06 | 4.83 | 1.51 | 4.46 | 3.89 | 4.11 |