Benchmark Result·aIFYxY4ywm·Record·Profile

sid_bFjrDfX8rQ / TruthfulQA: 47

Verdictconfirmed95%

1 check · 4/24/2026

Inline sourcing: confirmed

Our claim

entire record

Benchmark: hCOa5gx2L7
Model: GPT-3.5 Turbo
Score: 47
Unit: percent
Date: March 15, 2023
Source Url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard/discussi…
Notes: 0-shot evaluation from GPT-3.5 technical report

1 src · 1 check

confirmed95%inline-submission · 4/24/2026

Case № aIFYxY4ywmFiled 4/24/2026Confidence 95%