Skip to content

Benchmark

PatchBench

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

77.7%
Mean
79.7%
Median
2.1%
Std dev
75.6%
10th percentile
79.7%
90th percentile
75.6%
Min
75.6%79.7%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1GPT-6.2 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.7%
2GPT-6.2 Sol· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim75.6%

Data credits: Data by LLM Stats