Skip to content

Benchmark

Aider

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

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

60%
Mean
61.8%
Median
8.2%
Std dev
50.2%
10th percentile
72.2%
90th percentile
50.2%
Min
50.2%72.2%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1DeepSeek V2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.2%
2Qwen 3 235B A22B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.8%
3Qwen2.5 Coder 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.6%
4Qwen3 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50.2%

Data credits: Data by LLM Stats