Geometric Reasoning on Geo BBEH
45AccuracyCoT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CoTModel=Qwen32026.03 | 45 | 3,468 | |
| CoTModel=Gemma32026.03 | 32.5 | 4,115 | |
| CoTModel=Llama3.12026.03 | 25.5 | 3,556 | |
| ToTModel=Llama3.12026.03 | 10 | 8,648 | |
| DSTModel=Llama3.12026.03 | 8.5 | 4,601 | |
| DPTSModel=Llama3.12026.03 | 7.5 | 6,050 | |
| ToTModel=Qwen32026.03 | 6 | 8,984 | |
| ToTModel=Gemma32026.03 | 6 | 10,762 | |
| DSTModel=Gemma32026.03 | 5.5 | 5,809 | |
| DSTModel=Qwen32026.03 | 4 | 4,994 | |
| DPTSModel=Gemma32026.03 | 3.5 | 7,437 | |
| DPTSModel=Qwen32026.03 | 3 | 6,299 |