Open-Weight Models Trail Closed Frontier on Cyber by 4-7 Months
UK AISI's July 17 evaluation finds GLM-5.2 and DeepSeek V4-Pro match closed frontier models from 4-7 months ago at a fraction of the cost.
Tag
Tag
UK AISI's July 17 evaluation finds GLM-5.2 and DeepSeek V4-Pro match closed frontier models from 4-7 months ago at a fraction of the cost.