// BENCHMARK

Aider Benchmark benchmark

AI model leaderboard for the Aider Benchmark benchmark. Compare how large language models score on Aider Benchmark, see the full ranking, and understand what this AI benchmark measures. GPT-5 currently leads with 95.49. Aider's code-editing benchmark — derived from 133 Exercism Python exercises, edits run in a sandbox.

Leaderboard

# Model Organization Score Variant Source
#1 GPT-5 OpenAI 95.49 thinking-high-cited-ring-1t official ↗
#2 gemini-2.5-pro Google DeepMind 94.36 cited-ring-1t official ↗
#3 DeepSeek-V3.1-Terminus DeepSeek 92.86 thinking-cited-ring-1t official ↗
#4 gemini-2.5-pro Google DeepMind 89.85 lowthink-edit-cited-ling-1t official ↗
#5 Qwen3-235B-A22B-Thinking (Jul 2025) Qwen 88.91 thinking-cited-ring-1t official ↗
#6 DeepSeek-V3.1-Terminus DeepSeek 88.16 non-thinking-edit-cited-ling-1t official ↗
#7 Kimi K2 Moonshot 85.34 instruct-0905-edit-cited-ling-1t official ↗
#8 GPT-5 OpenAI 84.4 main-edit-cited-ling-1t official ↗
#9 Ling-1T Ant Group 83.65 edit-acc official ↗
#10 Ring-1T Ant Group 78.57 thinking official ↗
#11 DeepSeek-V2.5 DeepSeek 72.2 from-hf-readme official ↗

Frequently asked questions about Aider Benchmark

What is the Aider Benchmark benchmark?

Aider's code-editing benchmark — derived from 133 Exercism Python exercises, edits run in a sandbox.

How is the Aider Benchmark benchmark scored?

Aider Benchmark is scored using the pass@1 metric, where a higher score is better. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on Aider Benchmark?

As of the latest reported scores on GenAIList, GPT-5 achieves the highest result on Aider Benchmark with a score of 95.49.

Is a higher Aider Benchmark score better?

Yes. On Aider Benchmark a higher score indicates better performance, so models near the top of the leaderboard are the strongest.