Mathematical Reasoning on CP
54AccuracyStrategyLLM-SC
Evaluation Results
| Method | Links | |
|---|---|---|
| StrategyLLM-SCBackbone=Meta-Llama-3-70B-Instruct2023.11 | 54 | |
| SolutionLLMBackbone=Meta-Llama-3-70B-Instruct2023.11 | 51.5 | |
| StrategyLLMBackbone=Meta-Llama-3-70B-Instruct2023.11 | 51.5 | |
| CoTBackbone=Meta-Llama-3-70B-Instruct2023.11 | 48.5 | |
| StrategyLLM-SCBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 47.5 | |
| CoT-SCBackbone=Meta-Llama-3-70B-Instruct2023.11 | 47 | |
| SolutionLLMBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 44.5 | |
| StrategyLLMBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 44.5 | |
| CoTBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 41 | |
| CoT-SCBackbone=Mixtral-8x22B-Instruct-v0.12023.11 | 40.5 | |
| StrategyLLM-SCBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 32 | |
| StrategyLLMBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 28.5 | |
| CoT-SCBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 26.5 | |
| StrategyLLM-SCBackbone=Meta-Llama-3-8B-Instruct2023.11 | 25 | |
| StrategyLLMBackbone=Meta-Llama-3-8B-Instruct2023.11 | 24.5 | |
| CoTBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 24.5 | |
| SolutionLLMBackbone=Mixtral-8x7B-Instruct-v0.12023.11 | 22.5 | |
| SolutionLLMBackbone=Meta-Llama-3-8B-Instruct2023.11 | 20.5 | |
| CoT-SCBackbone=Meta-Llama-3-8B-Instruct2023.11 | 19.5 | |
| CoTBackbone=Meta-Llama-3-8B-Instruct2023.11 | 16 |