ResearchBenchmarksHallucination Evaluation on Custom Hallucination Benchmark 80 prompts 1.0 (test)Follow3.64F_dGrok2.97443.14723.323.4928May 5, 2026Evaluation ResultsMethodMethodLinksF_dRCSWHIGrokData Collection=manual...Data Collection=manually gathered2026.053.644.252.432.473.0367.86CopilotData Collection=manual...Data Collection=manually gathered2026.053.63.813.723.282.4870.74ChatGPTData Collection=manual...Data Collection=manually gathered2026.053.211.523.813.153.4757.04GeminiData Collection=genera...Data Collection=generated using an API key2026.0532.252.553.12.653.73