ResearchBenchmarksLanguage Understanding on MMLU HS US History (test)Follow94.26AccuracyProTeGi92.731293.128193.52593.9219May 14, 2026Evaluation ResultsMethodMethodLinksAccuracyProTeGiLLM=GPT-4oLLM=GPT-4o2026.0594.26PromptAgentLLM=GPT-4oLLM=GPT-4o2026.0593.93PSAO_LLMLLM=GPT-4oLLM=GPT-4o2026.0593.84BaselineLLM=GPT-4oLLM=GPT-4o2026.0593.77MIPROLLM=GPT-4oLLM=GPT-4o2026.0593.61COPROLLM=GPT-4oLLM=GPT-4o2026.0592.95GEPALLM=GPT-4oLLM=GPT-4o2026.0592.79