Benchmarks in 2026 are all over the place, and hallucination rates vary wildly...

https://telegra.ph/The-Paradox-of-Precision-Why-GPT-55-Flunks-the-Reality-Check-05-28

Benchmarks in 2026 are all over the place, and hallucination rates vary wildly by test. Even with web search, the HalluHard benchmark shows a 30.2% error rate