Reasoning on MA
98.7AccuracyStrategyLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| StrategyLLMModel=GPT-42023.11 | 98.7 | |
| StrategyLLM-SCModel=GPT-42023.11 | 98.7 | |
| SolutionLLMModel=GPT-42023.11 | 96.7 | |
| CoT-SCModel=GPT-42023.11 | 94.7 | |
| CoTModel=GPT-42023.11 | 92.7 | |
| StrategyLLM-SCModel=Claude-3-Sonnet2023.11 | 88 | |
| StrategyLLMModel=Claude-3-Sonnet2023.11 | 83.3 | |
| CoT-SCModel=Claude-3-Sonnet2023.11 | 76.7 | |
| CoTModel=Claude-3-Sonnet2023.11 | 72.7 | |
| SolutionLLMModel=Claude-3-Sonnet2023.11 | 69.3 |