True, but even some of the apples to apples is favorable to Gemini Ultra 90.04% ... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		bryanh on Dec 6, 2023 \| parent \| context \| favorite \| on: Gemini AI True, but even some of the apples to apples is favorable to Gemini Ultra 90.04% CoT@32 vs. GPT-4 87.29% CoT@32 (via API).

dongobread on Dec 6, 2023 [–]

This isn't apples to apples - they're taking the optimal prompting technique for their own model, then using that technique for both models. They should be comparing it against the optimal prompting technique for GPT-4.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact