Dynamic Interactive Conversation on GOODAILTM (2K)
8.41Solved scenariosOBLIVION
Evaluation Results
| Method | Links | |
|---|---|---|
| OBLIVIONModel=GPT-4.1-mini2026.03 | 8.41 | |
| OBLIVIONModel=Qwen3-30B-A3B†2026.03 | 7.75 | |
| OBLIVIONModel=GPT-4o-mini2026.03 | 7.37 | |
| BEYONDPROMPTSModel=GPT-4o-mini, Type=memory2026.03 | 6.37 | |
| FULLCTXModel=GPT-4.1-mini, Type=direct2026.03 | 6.29 | |
| FULLCTXModel=GPT-4o-mini, Type=direct2026.03 | 6.14 | |
| FULLCTXModel=Qwen3-30B-A3B†, Type=direct2026.03 | 5.94 | |
| BEYONDPROMPTSModel=GPT-4.1-mini, Type=memory2026.03 | 5.37 | |
| BEYONDPROMPTSModel=Qwen3-30B-A3B†, Type=memory2026.03 | 5.36 | |
| OBLIVIONModel=Phi-4-mini†2026.03 | 5.06 | |
| FULLCTXModel=Phi-4-mini†, Type=direct2026.03 | 4.28 | |
| BEYONDPROMPTSModel=Phi-4-mini†, Type=memory2026.03 | 3.91 |