Skip to content

Benchmark

CursorBench v3.2

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
2
Scores recorded
2
Sources
1
IQ weight
No weight published

Score distribution

71.6%
Mean
73.4%
Median
1.8%
Std dev
69.9%
10th percentile
73.4%
90th percentile
69.9%
Min
69.9%73.4%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Fable 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.4%
2Grok 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69.9%

Data credits: Data by LLM Stats