WeightBench scores language models on 42 weight-editing tasks
Claude Opus 5.5 scores 0.535 overall; GPT-6.1-sol scores 0.568 on 38 tasks.
1 stories, newest first · one card per story
Claude Opus 5.5 scores 0.535 overall; GPT-6.1-sol scores 0.568 on 38 tasks.
Today 992 readers · 1.2K views · 168 reads · all time 202K views