Comment by themgt
6 hours ago
You can look at the benchmark and the GPT-5 failures like answering "April 22, 2019" instead of the correct "Oct 23, 2018" for the question:
What day, month, and year was Carrie Underwood's album "Cry Pretty" certified Gold by the RIAA?
If your idea of the smartest person in the world is the guy who always wins tuesday night pub trivia, this blog post is for you. It also gets it's foundational factual claim wrong (as seen via epoch.ai). Very on brand.
https://epoch.ai/benchmarks/simple-qa-verified?view=graph&ta...
https://logs.epoch.ai/inspect-viewer/c79c08da/viewer.html?lo...
Not sure what you're trying to claim here tbh - Oct 23, 2018 is what the answer checker is looking for, it correctly judged "April 22, 2019." as incorrect: https://logs.epoch.ai/inspect-viewer/c79c08da/viewer.html?lo... (row 10, I don't see a way to link directly) and the correct answer matches the Wikipedia article's claim: https://en.wikipedia.org/wiki/Cry_Pretty and the RIAA's site it uses as a citation: https://www.riaa.com/gold-platinum/?reload=1786913260239&tab...