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…

Modality
text
Categories
reasoning, code
Openness
unknown
Source
llm_stats
Reported scores
4

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
DeepSeek-V2.5DeepSeek0.7222024-05-08evidence
Qwen2.5-Coder 7B InstructQwen0.5562024-09-19evidence
Qwen3 235B A22BQwen0.6182025-04-29evidence
Qwen3 32BQwen0.5022025-04-29evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.