CursorBench leaderboard
CursorBench
1 models tested · Updated 2026-04-16 · Verified sources only
Claude Opus 4.7 leads at 70.0%
1
Claude Opus 4.7
Anthropic · Blog/Anthropic · 2026-04-16
Up from 58% (Opus 4.6). Confirmed by Cursor CEO Michael Truell in Anthropic blog post.
70.0%
benchmark.space canonical public ledger of AI capability