Auto-formulation on NLP4LP Easy
85.7AccuracyORLM
Evaluation results
| Method | Links | |
|---|---|---|
| ORLMLLM=Deepseek-Math, Method Category=fine-tuning LLMs2024.07 | 85.7 | |
| OptiMUS-0.2LLM=GPT-4o, Method Category=agentic frameworks2024.07 | 84.4 | |
| LLMOPTLLM=Qwen1.5-14B, Method Category=fine-tuning LLMs2024.07 | 83.8 | |
| OptiMUS-0.3LLM=o3, Method Category=agentic frameworks2024.07 | 79.9 | |
| OptiMUS-0.3LLM=GPT-4o, Method Category=agentic frameworks2024.07 | 78.2 | |
| CoELLM=GPT-4o, Method Category=agentic frameworks2024.07 | 64.2 | |
| StandardLLM=o3, Method Category=direct prompting2024.07 | 62.7 | |
| ReflexionLLM=GPT-4o, Method Category=direct prompting2024.07 | 35.8 | |
| StandardLLM=GPT-4o, Method Category=direct prompting2024.07 | 34.6 |