Aider Polyglot

Measures: 225 hard Exercism exercises in C++, Go, Java, JavaScript, Python and Rust, solved through the Aider editing tool; scored on the share whose tests pass.

Maintainer: Aider
Introduced: 2024
Status: Active
Saturation: Near-ceiling
Typical provenance: Independent
In scoring set: Yes

Official leaderboard

Leaderboard

Show independent results only

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

Leaderboard
Model	Percent correct	Provenance	Source	Evaluated
GPT-4o mini OpenAI	3.6%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemma 3 27B Google DeepMind	4.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Qwen2.5-Coder-32B-Instruct Alibaba Group	8.0%	Third party	Aider LLM Leaderboards via Epoch AI	—
GPT-4.1 nano OpenAI	8.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Codestral 25.01 Mistral AI	11.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Command A Cohere	12.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Yi-Lightning 01.AI	12.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Llama 4 Maverick Meta	15.6%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Qwen2.5-Coder-32B-Instruct Alibaba Group	16.4%	Third party	Aider LLM Leaderboards via Epoch AI	—
DeepSeek-V2.5 DeepSeek	17.8%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.0 Flash Thinking Google DeepMind	18.2%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-4o OpenAI	18.2%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
QwQ-32B Alibaba Group	20.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Qwen2.5-Max Alibaba Group	21.8%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.0 Flash Google DeepMind	22.2%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-4o OpenAI	23.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude 3.5 Haiku Anthropic	28.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-4.1 mini OpenAI	32.4%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o1-mini OpenAI · Unknown effort	32.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Grok 3 Mini SpaceXAI (xAI) · Low effort	34.7%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.0 Pro Google DeepMind	35.6%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.0 Pro Google DeepMind	38.2%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Qwen3-32B Alibaba Group	40.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
gpt-oss-120b OpenAI · High effort	41.8%	Third party	Aider LLM Leaderboards via Epoch AI	—
gpt-oss-120b OpenAI · High effort	41.8%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.5 Flash Google DeepMind	44.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-4.5 OpenAI	44.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.5 Flash Google DeepMind	47.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-V3 DeepSeek	48.4%	Third party	Aider LLM Leaderboards via Epoch AI	—
Grok 3 Mini SpaceXAI (xAI) · High effort	49.3%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude 3.5 Sonnet Anthropic	51.6%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-4.1 OpenAI	52.4%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Grok 3 SpaceXAI (xAI)	53.3%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o3-mini OpenAI · Medium effort	53.8%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.5 Flash Google DeepMind · 23K effort	55.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude Sonnet 4 Anthropic	56.4%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-R1 DeepSeek	56.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Kimi K2 Moonshot AI	59.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Qwen3-235B-A22B Alibaba Group	59.6%	Third party	Aider LLM Leaderboards via Epoch AI	—
Qwen3-235B-A22B-Instruct-2507 Alibaba Group	59.6%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude 3.7 Sonnet Anthropic	60.4%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o3-mini OpenAI · High effort	60.4%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude Sonnet 4 Anthropic · 32K effort	61.3%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o1 OpenAI · High effort	61.7%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude 3.7 Sonnet Anthropic · 32K effort	64.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-V3.2 DeepSeek	70.2%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-V3.2-Exp DeepSeek	70.2%	Third party	Aider LLM Leaderboards via Epoch AI	—
Claude Opus 4 Anthropic	70.7%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-R1 DeepSeek	71.4%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Claude Opus 4 Anthropic · 32K effort	72.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o4-mini OpenAI · High effort	72.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.5 Pro Google DeepMind	72.9%	Third party	Aider LLM Leaderboards via Epoch AI	—
Gemini 2.5 Pro Google DeepMind	72.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-V3.2 DeepSeek	74.2%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
DeepSeek-V3.2-Exp DeepSeek · Thinking effort	74.2%	Third party	Aider LLM Leaderboards via Epoch AI	—
Gemini 2.5 Pro Google DeepMind	76.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o3 OpenAI · Medium effort	76.9%	Third party	Aider LLM Leaderboards via Epoch AI	—
o3 OpenAI · Unknown effort	76.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.5 Pro Google DeepMind	79.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Grok 4 SpaceXAI (xAI)	79.6%	Third party	Aider LLM Leaderboards via Epoch AI	—
Grok 4 SpaceXAI (xAI) · High effort	79.6%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-5 OpenAI · Low effort	81.3%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o3 OpenAI · High effort	81.3%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
Gemini 2.5 Pro Google DeepMind · 32K effort	83.1%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
o3-pro OpenAI · High effort	84.9%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-5 OpenAI · Medium effort	86.7%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—
GPT-5 OpenAI · High effort	88.0%	Third party	https://aider.chat/docs/leaderboards/ via Epoch AI	—

Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks, CC BY 4.0.

Sources

Epoch AI