KEEP-Bench finds context compressors often drop required evidence
The best open-weight 31B model keeps all required evidence in 66.8% of 4,102 cases, and the best proprietary model in 61.6%.
1 stories, newest first · one card per story
The best open-weight 31B model keeps all required evidence in 66.8% of 4,102 cases, and the best proprietary model in 61.6%.
Today 30 readers · 30 views · 1 read · all time 108K views