← All topics
cursorbench
Latest stories covering cursorbench, with summaries and links to related coverage.
1 stories · 1 reports · page 1 of 1
Connected topics
CursorBench 3.1
research
3 min read
CursorBench 3.1 evaluates AI agents on ambiguous, multi-file tasks based on real Cursor sessions, with scores indicating performance. Fable 5 Max achieved the highest score of 72.9%, while GPT-5.5 Extra High scored 64.3%.