reasoning benchmark
Aider Leaderboard
Aider is a code editing benchmark based on 133 Exercism Python exercises, with a Polyglot variant covering 225 exercises in C++, Go, Java, JavaScript, Python, and Rust.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
Aider Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Score72.20% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score61.80% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelAC | Score55.60% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score50.20% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
Aider Highlights
The leading models and scores on this benchmark.
Aider Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Aider
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Aider?
What Aider measures and how its scores work.
Aider evaluates AI models on translating natural language coding requests into executable code that passes unit tests, including editing existing code and formatting changes for automated saving to local files.
It measures end-to-end code editing capabilities and multilingual code editing performance; its metric is Score, reported as a ratio.
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
- No
- Evaluation key
- overall
LLM Stats. 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 72.20%.
What are the top three models on Aider?
The current leaders are DeepSeek-V2.5 (72.20%), Qwen3 235B A22B (61.80%), and Qwen2.5-Coder 7B Instruct (55.60%).
Which Aider model has the lowest official input price?
Qwen2.5-Coder 7B Instruct has the lowest matched official input price at $0.14 input / $0.29 output per 1M tokens.
Which models are fastest among Aider results?
The fastest matched records are DeepSeek-V2.5 (100.00 tok/s via DeepSeek), Qwen3 32B (26.95 tok/s via DeepInfra), and Qwen3 235B A22B (21.74 tok/s via DeepInfra).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.