[KongchangAI]
Benchmark

CursorBench 4.0

A benchmark introduced by Cursor for evaluating model performance in real coding workflows.

Timeline (last 90 days)

Nov 11

Claude Fable 5.2 Max scored 60% on CursorBench 4.0, second only to carbon high's 60.4%.

Unverified50%
Nov 11

The score gap between carbon high and Fable Max on CursorBench 4.0 is only 0.4 percentage points.

Unverified50%
Nov 10

Gemini 4 Carbon ranks first on the CursorBench 4.0, Perplexity's WANDR, and Zapier's AutomationBench benchmarks, and its cost per task is more than 2 times lower than the next-best external model.

Unverified50%
Oct 29

On the fifth edition of the Comprehensive Intelligence leaderboard, Gemini 4 Carbon scored 59 points, ranking first and overtaking Claude Opus 5.5, 9 points higher than Argon.

Expired75%
Sep 11

Cursor has launched CursorBench 4.0 for evaluating agent performance on real-world, ambiguous, multi-file tasks, and the addition of long-horizon problems has caused scores to drop across all models.

Unverified50%

All Facts (4)

Source Articles