Multi-party Dialogue Question Answering on LongDialQA
12.55F1 ScoreGAM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GAMModel=Qwen 2.5-7B2026.04 | 12.55 | 12.43 | |
| GAMModel=Qwen 2.5-14B2026.04 | 11.86 | 11.66 | |
| Mem0Model=Qwen 2.5-14B2026.04 | 11.48 | 10.94 | |
| GAMModel=GPT-4o-mini2026.04 | 11.18 | 10.14 | |
| Mem0Model=GPT-4o-mini2026.04 | 10.9 | 9.84 | |
| MemoryOSModel=GPT-4o-mini2026.04 | 10.61 | 9.31 | |
| Mem0Model=Qwen 2.5-7B2026.04 | 10.27 | 9.91 | |
| MemorybankModel=Qwen 2.5-14B2026.04 | 9.86 | 10.24 | |
| MemoryOSModel=Qwen 2.5-14B2026.04 | 9.07 | 8.39 | |
| ReadAgentModel=Qwen 2.5-14B2026.04 | 8.71 | 8.85 | |
| A-MemModel=Qwen 2.5-14B2026.04 | 8.53 | 7.93 | |
| GAMModel=Llama 3.2-3B2026.04 | 7.36 | 6.85 | |
| MemorybankModel=Qwen 2.5-7B2026.04 | 7.22 | 7.05 | |
| Mem0Model=Llama 3.2-3B2026.04 | 6.85 | 5.75 | |
| MemoryOSModel=Qwen 2.5-7B2026.04 | 6.76 | 5.11 | |
| A-MemModel=GPT-4o-mini2026.04 | 6.49 | 5.97 | |
| ReadAgentModel=Qwen 2.5-7B2026.04 | 6.41 | 6.35 | |
| MemorybankModel=GPT-4o-mini2026.04 | 5.95 | 6.06 | |
| MemoryOSModel=Llama 3.2-3B2026.04 | 5.85 | 4.46 | |
| MemgptModel=Qwen 2.5-14B2026.04 | 5.83 | 5.81 | |
| A-MemModel=Qwen 2.5-7B2026.04 | 5.49 | 5.79 | |
| MemgptModel=Qwen 2.5-7B2026.04 | 4.94 | 4.43 | |
| ReadAgentModel=GPT-4o-mini2026.04 | 4.5 | 3.16 | |
| A-MemModel=Llama 3.2-3B2026.04 | 4.11 | 3.27 | |
| ReadAgentModel=Llama 3.2-3B2026.04 | 3.97 | 4.04 | |
| MemorybankModel=Llama 3.2-3B2026.04 | 3.93 | 3.6 | |
| MemgptModel=Llama 3.2-3B2026.04 | 3.9 | 3.36 | |
| MemgptModel=GPT-4o-mini2026.04 | 3.87 | 3.28 |