WeightBench scores LLMs on reading, fixing and writing weights
Opus 5.5 scores 0.535 on all 42 tasks; models can write small policies but cannot patch language models.
1 stories, newest first · one card per story
Opus 5.5 scores 0.535 on all 42 tasks; models can write small policies but cannot patch language models.
Today 1K readers · 1.1K views · 101 reads · all time 211K views