Skip to content

Benchmark

CWE-Bench

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

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

62.1%
Mean
68%
Median
10.6%
Std dev
47.2%
10th percentile
71%
90th percentile
47.2%
Min
47.2%71%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemini 4 Carbon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71%
2Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim68%
3Gemini 3.8 Flash Cyber· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim47.2%

Data credits: Data by LLM Stats