Find the right AI for you

Search by name or tell us what you want to do
API servicesChoose how to access modelsAI modelsCapabilities, specifications, and pricingAI toolsFind useful tools by taskMCP directoryConnect tools, data, and workflowsAgent skillsFind reusable skills for AI agentsBenchmarksCompare model performanceOnline toolsConvert accounts, format JSON, estimate costs and test APIsModel timelineExplore model releasesUse casesStart with a practical task
EnterSearch · ↑↓Choose a resultEscClose
Submit中文
Project benchmark

Aider Polyglot code-editing snapshot

Aider Benchmarks · 69 configurations with published scores. Review each metric and its test conditions separately.

Report identity & conditions

Data as of2026-10-14· Report published—. See individual records for run dates and test conditions.

  • The benchmark has 225 exercises across C++, Go, Java, JavaScript, Python and Rust. Some runs report 223 or 224 test cases; the actual count is retained for each run.
  • The observation date is when we retrieved the data. Run dates, samples, reasoning settings, edit formats, tool versions and commits are recorded separately. This leaderboard includes historical runs and is not a current overall model ranking.
  • Display names and CLI aliases do not establish an exact snapshot, so they are not automatically linked to catalog versions. Dollar costs for a run are not reusable API unit prices, and runs with different settings are not controlled comparisons.
Read the original report ↗

Compare metrics within the same report. Each chart explains its direction and scope.
See the details for full values and run conditions.

Percent correct

Results from the original runs, rather than a general capability score. Dates, reasoning settings, edit formats and samples remain separate.: showing 8 of 63 records with values. See details for configurations and dates.

Chart data · 8 entries
Name%
gpt-5 (high)88
gpt-5 (medium)86.7
o3-pro (high)84.9
gemini-2.5-pro-preview-06-05 (32k think)83.1
gpt-5 (low)81.3
o3 (high)81.3
grok-4 (high)79.6
gemini-2.5-pro-preview-06-05 (default think)79.1

Correct edit format

Valid edit format rate. This is separate from task completion accuracy and is not combined into an overall score.: showing 8 of 63 records with values. See details for configurations and dates.

Chart data · 8 entries
Name%
Codestral 25.01100
DeepSeek R1 + claude-3-5-sonnet-20241022100
Gemini 2.0 Pro exp-02-05100
gemini-2.0-flash-exp100
gemini-2.5-pro-preview-06-05 (default think)100
gemma-3-27b-it100
gpt-4o-mini-2024-07-18100
Grok 3 Mini Beta (low)100

Full results & model versions

69 / 69configurations have published scores in this scope. Scored configurations are listed; missing values remain “Not provided.” Different run configurations of the same model are listed separately.

Llama 4 Maverick

Model reported by the benchmark

Run2025-04-06 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.81.2.dev· Submission9445a31

Percent correct
15.6%
Correct edit format
99.1%
Run commandaider --model nvidia_nim/meta/llama-4-maverick-17b-128e-instruct

yi-lightning

Model reported by the benchmark

Run2024-12-23 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.69.2.dev· Submission2b1625e

Percent correct
12.9%
Correct edit format
92.9%
Run commandaider --model openai/yi-lightning

command-a-03-2025-quality

Model reported by the benchmark

Run2025-03-14 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.77.1.dev· Submissiona1aa63f

Percent correct
12%
Correct edit format
99.6%
Run commandOPENAI_API_BASE=https://api.cohere.ai/compatibility/v1 aider --model openai/command-a-03-2025-quality

Codestral 25.01

Model reported by the benchmark

Run2025-01-13 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.71.2.dev· Submission0cba898-dirty

Percent correct
11.1%
Correct edit format
100%
Run commandaider --model mistral/codestral-latest

openhands-lm-32b-v0.1

Model reported by the benchmark

Run2025-04-19 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.82.2.dev· Submissionc08336f

Percent correct
10.2%
Correct edit format
95.1%
Run commandaider --model openrouter/all-hands/openhands-lm-32b-v0.1

gpt-4.1-nano

Model reported by the benchmark

Run2025-04-14 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.81.4.dev· Submission71d1591-dirty

Percent correct
8.9%
Correct edit format
94.2%
Run commandaider --model gpt-4.1-nano

Qwen2.5-Coder-32B-Instruct

Model reported by the benchmark

Run2024-12-22 · 225problems · Formatdiff· Reasoning levelNot listed
Tools0.69.2.dev· Submission6d7e8be-dirty

Percent correct
8%
Correct edit format
71.6%
Run commandaider --model openai/Qwen/Qwen2.5-Coder-32B-Instruct # via hyperbolic

gemma-3-27b-it

Model reported by the benchmark

Run2025-03-15 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.77.1.dev· Submissionfd21f51-dirty

Percent correct
4.9%
Correct edit format
100%
Run commandaider --model openrouter/google/gemma-3-27b-it

gpt-4o-mini-2024-07-18

Model reported by the benchmark

Run2024-12-21 · 225problems · Formatwhole· Reasoning levelNot listed
Tools0.69.2.dev· Submissiona755079-dirty

Percent correct
3.6%
Correct edit format
100%
Run commandaider --model gpt-4o-mini-2024-07-18