Long-context Memory Evaluation on Mem-Gallery
81F1 ScoreOMNIMEM
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| OMNIMEMBackbone=GPT-5.12026.04 | 81 | 46 | 37.4 | 63.9 | 51.5 | |
| OMNIMEMBackbone=GPT-4o2026.04 | 79.7 | 44.9 | 36.6 | 62.7 | 50.5 | |
| OMNIMEMBackbone=GPT-5-nano2026.04 | 78.7 | 43.7 | 35.7 | 61.7 | 49.4 | |
| OMNIMEMBackbone=GPT-4.1-nano2026.04 | 78 | 43 | 35.3 | 61 | 48.8 | |
| OMNIMEMBackbone=GPT-4o-mini2026.04 | 74.9 | 40.3 | 33.4 | 58.3 | 46.5 | |
| SimpleMemBackbone=GPT-5.12026.04 | 53.8 | 35 | 31.2 | 47 | 39.5 | |
| SimpleMemBackbone=GPT-4o2026.04 | 53.5 | 34.8 | 31 | 46.8 | 39 | |
| SimpleMemBackbone=GPT-5-nano2026.04 | 52.2 | 34 | 30.2 | 45.8 | 38.5 | |
| SimpleMemBackbone=GPT-4.1-nano2026.04 | 51.8 | 33.8 | 30 | 45.2 | 38 | |
| MemVerseBackbone=GPT-4o2026.04 | 50.5 | 33 | 27 | 44 | 35.5 | |
| A-MEMBackbone=GPT-5-nano2026.04 | 50.5 | 33.2 | 29 | 44.5 | 36.8 | |
| SimpleMemBackbone=GPT-4o-mini2026.04 | 49.8 | 31.8 | 29 | 43.5 | 36.8 | |
| MemVerseBackbone=GPT-5.12026.04 | 47.8 | 31.2 | 26.2 | 41.8 | 34.5 | |
| MemVerseBackbone=GPT-5-nano2026.04 | 47.8 | 31.5 | 26.2 | 42 | 34.5 | |
| MemVerseBackbone=GPT-4.1-nano2026.04 | 47 | 30.8 | 25.5 | 41 | 34 | |
| MemVerseBackbone=GPT-4o-mini2026.04 | 45 | 29.5 | 24.8 | 39.5 | 33 | |
| MemGPTBackbone=GPT-4o2026.04 | 43.5 | 29.8 | 27.5 | 39 | 33.5 | |
| MemGPTBackbone=GPT-5.12026.04 | 42.5 | 27.5 | 25 | 37.8 | 31.5 | |
| A-MEMBackbone=GPT-5.12026.04 | 40.8 | 26.8 | 24.2 | 36.5 | 30.2 | |
| MemGPTBackbone=GPT-4o-mini2026.04 | 39.8 | 26.2 | 24.2 | 35.5 | 29.8 | |
| MemGPTBackbone=GPT-5-nano2026.04 | 38.8 | 25.5 | 23 | 34.5 | 28.8 | |
| A-MEMBackbone=GPT-4o2026.04 | 37 | 25.2 | 24 | 33.2 | 28.5 | |
| A-MEMBackbone=GPT-4.1-nano2026.04 | 36.5 | 24.2 | 22.5 | 32.5 | 27.5 | |
| MemGPTBackbone=GPT-4.1-nano2026.04 | 36 | 23.8 | 21.8 | 31.8 | 26.8 | |
| Claude-MemBackbone=GPT-5-nano2026.04 | 35 | 24.9 | 21.7 | 31.5 | 26.4 | |
| A-MEMBackbone=GPT-4o-mini2026.04 | 33 | 22.2 | 20.5 | 29.8 | 25.2 | |
| Claude-MemBackbone=GPT-5.12026.04 | 30.5 | 20.3 | 18.8 | 27.9 | 23 | |
| Claude-MemBackbone=GPT-4.1-nano2026.04 | 30.3 | 19.4 | 17.2 | 26.8 | 22.3 | |
| Mem0Backbone=GPT-4o2026.04 | 29.8 | 19.2 | 18.2 | 26.8 | 22.4 | |
| Mem0Backbone=GPT-4o-mini2026.04 | 29.1 | 18.8 | 18.5 | 26.5 | 22.3 | |
| Mem0Backbone=GPT-5-nano2026.04 | 28.3 | 17.6 | 16.5 | 25 | 21 | |
| Claude-MemBackbone=GPT-4o-mini2026.04 | 27.2 | 17.5 | 17.2 | 24.5 | 21 | |
| Mem0Backbone=GPT-5.12026.04 | 27 | 17.5 | 15.7 | 24 | 20 | |
| Mem0Backbone=GPT-4.1-nano2026.04 | 26.8 | 17.6 | 15.6 | 23.8 | 19.9 | |
| Claude-MemBackbone=GPT-4o2026.04 | 21 | 14.8 | 14.8 | 19.4 | 17 |