Skip to content
AI Atlas
BenchmarkActivecategory · coding

Aider polyglot

aider.chat/docs/leaderboards

225 Exercism exercises in 6 languages, edit-format aware

quality57

Updated 3 h ago · first seen 11 Sept 2026

bench_01M293SPEMVE6W55699099NES3

Metric
pass rate (2 attempts) · %
Direction
Higher is better
Results
138 · 10 filtered
Leader
QwQ-32B + Qwen 2.5 Coder Instruct 100%

Leaderboard 10 current results · config contains “0.86.2.dev”

Select models with +, then open Compare.

Leaderboard
#ModelScoreConfigEvaluatedSourceActions
1#1DeepSeek-V3.2-Exp (Chat)98.2%date=2025-10-03 · command=aider --model deepseek/deepseek-chat · dirname=2025-10-03-09-21-36--deepseek-v3.2-chat · versions=0.86.2.dev3 Oct 2025aider.chatT2 History
2#2DeepSeek-V3.2-Exp (Reasoner)97.3%date=2025-10-03 · command=aider --model deepseek/deepseek-reasoner · dirname=2025-10-03-09-45-34--deepseek-v3.2-reasoner · versions=0.86.2.dev3 Oct 2025aider.chatT2 History
3#3gpt-5 (high)91.6%date=2025-08-23 · command=aider --model openai/gpt-5 · dirname=2025-08-23-15-47-21--gpt-5-high · versions=0.86.2.dev23 Aug 2025aider.chatT2 History
4#4gpt-5 (medium)OpenAI88.4%date=2025-08-25 · command=aider --model openai/gpt-5 · dirname=2025-08-25-13-23-27--gpt-5-medium · versions=0.86.2.dev25 Aug 2025aider.chatT2 History
5#5gpt-5 (high)88%date=2025-08-23 · command=aider --model openai/gpt-5 · dirname=2025-08-23-15-47-21--gpt-5-high · versions=0.86.2.dev23 Aug 2025aider.chatT2 History
6#6gpt-5 (low)OpenAI86.7%date=2025-08-25 · command=aider --model openai/gpt-5 · dirname=2025-08-25-14-16-37--gpt-5-low · versions=0.86.2.dev25 Aug 2025aider.chatT2 History
7#7gpt-5 (medium)OpenAI86.7%date=2025-08-25 · command=aider --model openai/gpt-5 · dirname=2025-08-25-13-23-27--gpt-5-medium · versions=0.86.2.dev25 Aug 2025aider.chatT2 History
8#8gpt-5 (low)OpenAI81.3%date=2025-08-25 · command=aider --model openai/gpt-5 · dirname=2025-08-25-14-16-37--gpt-5-low · versions=0.86.2.dev25 Aug 2025aider.chatT2 History
9#9DeepSeek-V3.2-Exp (Reasoner)74.2%date=2025-10-03 · command=aider --model deepseek/deepseek-reasoner · dirname=2025-10-03-09-45-34--deepseek-v3.2-reasoner · versions=0.86.2.dev3 Oct 2025aider.chatT2 History
10#10DeepSeek-V3.2-Exp (Chat)70.2%date=2025-10-03 · command=aider --model deepseek/deepseek-chat · dirname=2025-10-03-09-21-36--deepseek-v3.2-chat · versions=0.86.2.dev3 Oct 2025aider.chatT2 History

10 results

Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.

The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.