Friday, April 11, 2025

AI reasoning models cost more to benchmark, making it harder to independently verify claims; Artificial Analysis: OpenAI's o1 costs $2,767.05 to evaluate (Kyle Wiggers/TechCrunch)

Kyle Wiggers / TechCrunch:
AI reasoning models cost more to benchmark, making it harder to independently verify claims; Artificial Analysis: OpenAI's o1 costs $2,767.05 to evaluate  —  AI labs like OpenAI claim that their so-called “reasoning” AI models, which can “think” through problems step by step …



No comments:

Post a Comment

DeepSeek releases V4.1-Flash-1017, an update it says offers "stronger benchmark performance, faster task completion, and shorter outputs" than its predecessor (Saritha Rai/Bloomberg)

Saritha Rai / Bloomberg : DeepSeek releases V4.1-Flash-1017, an update it says offers “stronger benchmark performance, faster task comple...