ResearchBenchmarksLanguage Understanding on MMLU HS World History (test)Follow95.38AccuracyPSAO_LLM88.443290.244192.04593.8459May 14, 2026Evaluation ResultsMethodMethodLinksAccuracyPSAO_LLMLLM=GPT-4oLLM=GPT-4o2026.0595.38ProTeGiLLM=GPT-4oLLM=GPT-4o2026.0593.14COPROLLM=GPT-4oLLM=GPT-4o2026.0593MIPROLLM=GPT-4oLLM=GPT-4o2026.0592.71BaselineLLM=GPT-4oLLM=GPT-4o2026.0592.43GEPALLM=GPT-4oLLM=GPT-4o2026.0591.86PromptAgentLLM=GPT-4oLLM=GPT-4o2026.0588.71