Skip to content

Benchmark

APEX-SWE

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

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

Score distribution

56.4%
Mean
56.4%
Median
0%
Std dev
56.4%
10th percentile
56.4%
90th percentile
56.4%
Min

Leaderboard

#ModelScore
1Grok 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.4%

Data credits: Data by LLM Stats