LetTokenBurn
Sign in
Verified71%Harbor nativeCoding

Aider Polyglot

Aider Polyglot: 6种语言diff编辑

RepoDatasetLeaderboardHomepage

How to run

ltb · aider-polyglot
$ npm i -g lettokenburn-cli
$ ltb bench run aider/aider-polyglot@1 --benchmark aider-polyglot -a claude-code -m anthropic/claude-opus-4-8
$ ltb bench push

Harbor-native: you can also call Harbor directly.

harbor
$ harbor run -d aider/aider-polyglot@1 -a claude-code -m anthropic/claude-opus-4-8

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

61 sourced entries
HarnessSourceConfidenceLink
GPT-588.0N/AIndependentmediumAug 23, 2025aider.chat
o3-pro-2025-06-1084.9N/AIndependentmediumJun 28, 2025aider.chat
gemini-2.5-pro-preview-06-05-32K83.1N/AIndependentmediumJun 6, 2025aider.chat
o381.3N/AIndependentmediumJun 25, 2025aider.chat
Grok 4 070979.6N/AIndependentmediumN/Aaider.chat
Gemini 2.5 Pro Preview 06-0579.1N/AIndependentmediumJun 6, 2025aider.chat
Gemini 2.5 Pro Preview 05-0676.9N/AIndependentmediumMay 7, 2025aider.chat
DeepSeek Reasoner74.2N/AIndependentmediumOct 3, 2025aider.chat
DeepSeek V3.274.2N/AIndependentmediumN/Aaider.chat
Gemini 2.5 Pro Preview 03-2572.9N/AIndependentmediumApr 12, 2025aider.chat
Gemini 2.5 Pro Exp 03-2572.9N/AIndependentmediumN/Aaider.chat
claude-opus-4-20250514-32K72.0N/AIndependentmediumMay 25, 2025aider.chat
o4-mini72.0N/AIndependentmediumApr 16, 2025aider.chat
DeepSeek-R1-052871.4N/AIndependentmediumJun 6, 2025aider.chat
Claude Opus 4 (2025-05-14)70.7N/AIndependentmediumMay 25, 2025aider.chat
DeepSeek Chat70.2N/AIndependentmediumOct 3, 2025aider.chat
claude-3-7-sonnet-20250219-32K64.9N/AIndependentmediumFeb 24, 2025aider.chat
OpenAI/o1-2024-12-17-high61.7N/AIndependentmediumDec 21, 2024aider.chat
claude-sonnet-4-20250514-32K61.3N/AIndependentmediumMay 24, 2025aider.chat
Claude 3.7 Sonnet Thinking (2025-02-19)60.4N/AIndependentmediumFeb 24, 2025aider.chat
o3-mini60.4N/AIndependentmediumJan 31, 2025aider.chat
Qwen3-235B-A22B-Thinking-250759.6N/AIndependentmediumMay 9, 2025aider.chat
Qwen3 235B A22B59.6N/AIndependentmediumN/Aaider.chat
Kimi K2 090559.1N/AIndependentmediumJul 17, 2025aider.chat
Kimi K2 Thinking Turbo59.1N/AIndependentmediumN/Aaider.chat
DeepSeek R156.9N/AIndependentmediumJan 20, 2025aider.chat
Claude Sonnet 4 (2025-05-14)56.4N/AIndependentmediumMay 24, 2025aider.chat
gemini-2.5-flash-preview-05-20-23K55.1N/AIndependentmediumMay 25, 2025aider.chat
DeepSeek V3 032455.1N/AIndependentmediumMar 24, 2025aider.chat
Grok 353.3N/AIndependentmediumApr 10, 2025aider.chat
GPT-4.152.4N/AIndependentmediumApr 14, 2025aider.chat
Claude 3.5 Sonnet51.6N/AIndependentmediumJan 17, 2025aider.chat
Grok 3 Mini Beta49.3N/AIndependentmediumApr 10, 2025aider.chat
DeepSeek-V348.4N/AIndependentmediumN/Aaider.chat
Gemini 2.5 Flash Preview 04-1747.1N/AIndependentmediumApr 20, 2025aider.chat
ChatGPT-4o (2025-03-27)45.3N/AIndependentmediumMar 29, 2025aider.chat
GPT-4.5 Preview (2025-02-27)44.9N/AIndependentmediumFeb 27, 2025aider.chat
Gemini 2.5 Flash Preview 05-2044.0N/AIndependentmediumMay 26, 2025aider.chat
GPT-oss 120B41.8N/AIndependentmediumN/Aepoch.ai
Qwen3-32B40.0N/AIndependentmediumMay 8, 2025aider.chat
Gemini Exp 120638.2N/AIndependentmediumDec 22, 2024aider.chat
Gemini 2.0 Pro Exp 02-0535.6N/AIndependentmediumFeb 25, 2025aider.chat
o1-mini32.9N/AIndependentmediumDec 22, 2024aider.chat
GPT-4.1-mini32.4N/AIndependentmediumApr 14, 2025aider.chat
Claude 3.5 Haiku (2024-10-22)28.0N/AIndependentmediumDec 21, 2024aider.chat
ChatGPT-4o (2025-01-29)27.1N/AIndependentmediumFeb 15, 2025aider.chat
GPT-4o23.1N/AIndependentmediumDec 30, 2024aider.chat
Gemini 2.0 Flash Experimental22.2N/AIndependentmediumDec 22, 2024aider.chat
Qwen Max (2025-01-25)21.8N/AIndependentmediumJan 28, 2025aider.chat
QwQ-32B20.9N/AIndependentmediumMar 6, 2025aider.chat
Top 50 of 61 by score

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

Aider Polyglot (Aider Polyglot) — 6种语言diff编辑. Scoring: Pass rate. Difficulty: 高. Imported from benchmark_research.md (2026-06).