Logical Reasoning on BoardgameQA BBEH
0.34AccuracyCoT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoTModel=Qwen32026.03 | 0.34 | 4,425 | |
| CoTModel=Gemma32026.03 | 0.33 | 5,311 | |
| CoTModel=Llama3.12026.03 | 0.315 | 4,501 | |
| DSTModel=Llama3.12026.03 | 0.14 | 4,307 | |
| DSTModel=Qwen32026.03 | 0.12 | 4,560 | |
| ToTModel=Llama3.12026.03 | 0.1 | 15,004 | |
| DPTSModel=Llama3.12026.03 | 0.095 | 9,604 | |
| ToTModel=Qwen32026.03 | 0.08 | 14,220 | |
| DPTSModel=Qwen32026.03 | 0.08 | 9,953 | |
| ToTModel=Gemma32026.03 | 0.06 | 16,924 | |
| DSTModel=Gemma32026.03 | 0.05 | 5,218 | |
| DPTSModel=Gemma32026.03 | 0.035 | 11,701 |