Mathematical Reasoning on MA
91.3AccuracyStrategyLLM-SC
Evaluation Results
| Method | Links | |
|---|---|---|
| StrategyLLM-SCBackbone=Meta-Llama-3-70B-Instruct2023.11 | 91.3 | |
| StrategyLLM-SCBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 89.3 | |
| StrategyLLMBackbone=Meta-Llama-3-70B-Instruct2023.11 | 88 | |
| StrategyLLMBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 84 | |
| CoT-SCBackbone=Meta-Llama-3-70B-Instruct2023.11 | 82 | |
| CoTBackbone=Meta-Llama-3-70B-Instruct2023.11 | 81.3 | |
| CoT-SCBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 80.7 | |
| CoTBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 80 | |
| StrategyLLM-SCBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 78 | |
| StrategyLLMBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 76 | |
| SolutionLLMBackbone=Meta-Llama-3-70B-Instruct2023.11 | 72 | |
| StrategyLLM-SCBackbone=Meta-Llama-3-8B-Instruct2023.11 | 66 | |
| StrategyLLMBackbone=Meta-Llama-3-8B-Instruct2023.11 | 64.7 | |
| CoT-SCBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 62.7 | |
| SolutionLLMBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 60.7 | |
| CoTBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 59.3 | |
| CoT-SCBackbone=Meta-Llama-3-8B-Instruct2023.11 | 45.3 | |
| CoTBackbone=Meta-Llama-3-8B-Instruct2023.11 | 44.7 | |
| SolutionLLMBackbone=Meta-Llama-3-8B-Instruct2023.11 | 43.3 | |
| SolutionLLMBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 34.7 |