Logical Reasoning on Causal BBEH
49AccuracyCoT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoTModel=Gemma32026.03 | 49 | 5,257 | |
| CoTModel=Qwen32026.03 | 42.5 | 4,406 | |
| CoTModel=Llama3.12026.03 | 37 | 4,458 | |
| DSTModel=Llama3.12026.03 | 6.5 | 4,786 | |
| ToTModel=Llama3.12026.03 | 5 | 10,749 | |
| ToTModel=Qwen32026.03 | 4 | 11,212 | |
| DPTSModel=Llama3.12026.03 | 4 | 8,343 | |
| DSTModel=Qwen32026.03 | 3.5 | 5,044 | |
| DSTModel=Gemma32026.03 | 3 | 5,825 | |
| DPTSModel=Qwen32026.03 | 2.5 | 8,627 | |
| ToTModel=Gemma32026.03 | 1.5 | 13,319 | |
| DPTSModel=Gemma32026.03 | 0.5 | 10,258 |