reasoning benchmark
Aider
Aider is a comprehensive code editing benchmark based on 133 practice exercises from Exercism's Python repository, designed to evaluate AI models' ability to translate natural language coding requests into executable code that passes unit tests. The benchmark measures end-to-end code editing capabilities, including GPT's ability to edit existing code and format code changes for automated saving to local files. The Aider Polyglot variant extends this evaluation across 225 challenging exercises spanning C++, Go, Java, JavaScript, Python, and Rust, making it a standard benchmark for assessing multilingual code editing performance in AI research.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
Aider Ranking
Higher score ranks better on this benchmark.
| 1 | DE | 72.2% | 100.0% | 4 | C | |
| 2 | AC | 61.8% | 66.7% | 4 | C | |
| 3 | AC | 55.6% | 33.3% | 4 | C | |
| 4 | AC | 50.2% | 0.0% | 4 | C |
Aider Score Distribution
A closer view of the leading scores on this benchmark.
Aider Highlights
The leading models and scores on this benchmark.
What is Aider?
What Aider measures and how its scores work.
Aider is a comprehensive code editing benchmark based on 133 practice exercises from Exercism's Python repository, designed to evaluate AI models' ability to translate natural language coding requests into executable code that passes unit tests. The benchmark measures end-to-end code editing capabilities, including GPT's ability to edit existing code and format code changes for automated saving to local files. The Aider Polyglot variant extends this evaluation across 225 challenging exercises spanning C++, Go, Java, JavaScript, Python, and Rust, making it a standard benchmark for assessing multilingual code editing performance in AI research.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Aider
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aider|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Aider.
Which model scores highest on Aider?
DeepSeek-V2.5 is currently ranked first with 72.2%.
What does Aider measure?
Aider is a comprehensive code editing benchmark based on 133 practice exercises from Exercism's Python repository, designed to evaluate AI models' ability to translate natural language coding requests into executable code that passes unit tests. The benchmark measures end-to-end code editing capabilities, including GPT's ability to edit existing code and format code changes for automated saving to local files. The Aider Polyglot variant extends this evaluation across 225 challenging exercises spanning C++, Go, Java, JavaScript, Python, and Rust, making it a standard benchmark for assessing multilingual code editing performance in AI research.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.