ResearchBenchmarksLanguage Understanding on MMLU College Medicine (test)Follow87.88AccuracyGEPA81.109682.867384.62586.3827May 14, 2026Evaluation ResultsMethodMethodLinksAccuracyGEPALLM=GPT-4oLLM=GPT-4o2026.0587.88PSAO_LLMLLM=GPT-4oLLM=GPT-4o2026.0586.44BaselineLLM=GPT-4oLLM=GPT-4o2026.0583.43PromptAgentLLM=GPT-4oLLM=GPT-4o2026.0582.75COPROLLM=GPT-4oLLM=GPT-4o2026.0582.16MIPROLLM=GPT-4oLLM=GPT-4o2026.0582.16ProTeGiLLM=GPT-4oLLM=GPT-4o2026.0581.37