top | item 38545318 (no title) bryanh | 2 years ago Page 7 of their technical report [0] has a better apples to apples comparison. Why they choose to show apples to oranges on their landing page is odd to me.[0] https://storage.googleapis.com/deepmind-media/gemini/gemini_... discuss order hn newest polygamous_bat|2 years ago I assume these landing pages are made for wall st analysts rather than people who understand LLM eval methods. bryanh|2 years ago 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). load replies (1) rockinghigh|2 years ago Showing dominance in AI is also targeted at their entreprise customers who spend millions on Google Cloud services.
polygamous_bat|2 years ago I assume these landing pages are made for wall st analysts rather than people who understand LLM eval methods. bryanh|2 years ago 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). load replies (1) rockinghigh|2 years ago Showing dominance in AI is also targeted at their entreprise customers who spend millions on Google Cloud services.
bryanh|2 years ago 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). load replies (1)
rockinghigh|2 years ago Showing dominance in AI is also targeted at their entreprise customers who spend millions on Google Cloud services.
polygamous_bat|2 years ago
bryanh|2 years ago
rockinghigh|2 years ago