The AI arena is free today

Open Superagent
AI OrganizationMaintains 2 benchmarks

Cursor: AI benchmarks & research

AI code editor (Anysphere). Maintains CursorBench.

Maintained by Cursor

2 benchmarks

In one line

Cursor maintains CursorBench 4.0 (counts toward the LLM Stats Score, 4 models scored) and CursorBench v3.2 (counts toward the LLM Stats Score, 2 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Cursor.

What is Cursor?

AI code editor (Anysphere). Maintains CursorBench. On LLM Stats it maintains 2 benchmarks, led by CursorBench 4.0 and CursorBench v3.2. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Cursor benchmarks count toward the LLM Stats Score?

CursorBench 4.0 and CursorBench v3.2 count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead Cursor's benchmarks?

Claude Fable 5.2 leads CursorBench 4.0 at 60.0% (4 models scored) and Claude Fable 5.1 leads CursorBench v3.2 at 73.4% (2 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Cursor's official benchmark results?

Cursor's official site is https://cursor.com. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.