Skip to content
AI Atlas
BenchmarkActivecategory · coding

Aider polyglot

aider.chat/docs/leaderboards

225 Exercism exercises in 6 languages, edit-format aware

quality57

Updated 4 h ago · first seen 11 Sept 2026

bench_01M293SPEMVE6W55699099NES3

Metric
pass rate (2 attempts) · %
Direction
Higher is better
Results
138 · 8 filtered
Leader
QwQ-32B + Qwen 2.5 Coder Instruct 100%

Score history · yi-lightning 2 rows

Not enough history to chart — 2 observations, all dated 23 Dec 2024. Rows under different configurations count separately; the list below shows each one.

  • 92.9%date=2024-12-23 · command=aider --model openai/yi-lightning · dirname=2024-12-23-01-11-56--yi-test · versions=0.69.2.dev23 Dec 2024
  • 12.9%date=2024-12-23 · command=aider --model openai/yi-lightning · dirname=2024-12-23-01-11-56--yi-test · versions=0.69.2.dev23 Dec 2024

Back to the full leaderboard

Leaderboard 8 current results · config contains “diff-fenced”

Select models with +, then open Compare.

Leaderboard
#ModelScoreConfigEvaluatedSourceActions
1#1gemini-2.5-pro-preview-06-05 (default think)100%date=2025-06-06 · command=aider --model gemini/gemini-2.5-pro-preview-06-05 · dirname=2025-06-06-18-38-56--gemini0605-diff-fenced · versions=0.84.1.dev6 Jun 2025aider.chatT2 History
2#2gemini-2.5-pro-preview-06-05 (32k think)99.6%date=2025-06-06 · command=aider --model gemini/gemini-2.5-pro-preview-06-05 --thinking-tokens 32k · dirname=2025-06-06-16-36-21--gemini0605-32k-think-diff-fenced · versions=0.84.1.dev6 Jun 2025aider.chatT2 History
3#3Gemini 2.5 Pro Preview 05-06Google97.3%date=2025-05-07 · command=aider --model gemini/gemini-2.5-pro-preview-05-06 · dirname=2025-05-07-19-32-40--gemini0506-diff-fenced-completion_cost · versions=0.82.4.dev7 May 2025aider.chatT2 History
4#4Gemini 2.5 Pro Preview 03-2592.4%date=2025-04-12 · command=aider --model gemini/gemini-2.5-pro-preview-03-25 · dirname=2025-04-12-04-55-50--gemini-25-pro-diff-fenced · versions=0.81.3.dev12 Apr 2025aider.chatT2 History
5#5gemini-2.5-pro-preview-06-05 (32k think)83.1%date=2025-06-06 · command=aider --model gemini/gemini-2.5-pro-preview-06-05 --thinking-tokens 32k · dirname=2025-06-06-16-36-21--gemini0605-32k-think-diff-fenced · versions=0.84.1.dev6 Jun 2025aider.chatT2 History
6#6gemini-2.5-pro-preview-06-05 (default think)79.1%date=2025-06-06 · command=aider --model gemini/gemini-2.5-pro-preview-06-05 · dirname=2025-06-06-18-38-56--gemini0605-diff-fenced · versions=0.84.1.dev6 Jun 2025aider.chatT2 History
7#7Gemini 2.5 Pro Preview 05-06Google76.9%date=2025-05-07 · command=aider --model gemini/gemini-2.5-pro-preview-05-06 · dirname=2025-05-07-19-32-40--gemini0506-diff-fenced-completion_cost · versions=0.82.4.dev7 May 2025aider.chatT2 History
8#8Gemini 2.5 Pro Preview 03-2572.9%date=2025-04-12 · command=aider --model gemini/gemini-2.5-pro-preview-03-25 · dirname=2025-04-12-04-55-50--gemini-25-pro-diff-fenced · versions=0.81.3.dev12 Apr 2025aider.chatT2 History

8 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.