Dynamic Interactive Conversation on GOODAILTM 32K
6.79Solved ScenariosOBLIVION
Evaluation Results
| Method | Links | |
|---|---|---|
| OBLIVIONModel=GPT-4.1-mini2026.03 | 6.79 | |
| BEYONDPROMPTSModel=GPT-4.1-mini, Type=memory2026.03 | 6.68 | |
| OBLIVIONModel=GPT-4o-mini2026.03 | 6.26 | |
| OBLIVIONModel=Qwen3-30B-A3B†2026.03 | 6.1 | |
| FULLCTXModel=GPT-4.1-mini, Type=direct2026.03 | 6.05 | |
| FULLCTXModel=GPT-4o-mini, Type=direct2026.03 | 5.65 | |
| FULLCTXModel=Qwen3-30B-A3B†, Type=direct2026.03 | 5.38 | |
| BEYONDPROMPTSModel=GPT-4o-mini, Type=memory2026.03 | 4.87 | |
| BEYONDPROMPTSModel=Qwen3-30B-A3B†, Type=memory2026.03 | 4.23 | |
| OBLIVIONModel=Phi-4-mini†2026.03 | 3.36 | |
| BEYONDPROMPTSModel=Phi-4-mini†, Type=memory2026.03 | 2.65 | |
| FULLCTXModel=Phi-4-mini†, Type=direct2026.03 | 1.33 |