Benchmarks are noisy in 2026, and your hallucination rates change based on the...

https://garrettwigp625.tearosediner.net/why-did-vectara-hallucination-rates-jump-on-the-7-700-document-dataset

Benchmarks are noisy in 2026, and your hallucination rates change based on the test you run. Even with web search, HalluHard hits a 30.2% error rate. Don't rely on generic scores