Price Per TokenPrice Per Token

Best LLM for Coding

Compare coding performance across LLMs ranked by community votes, with LiveCodeBench and Aider benchmark scores alongside pricing information.

Get our weekly newsletter on pricing changes, new releases, and tools.

OpenClaw

Deploy OpenClaw in Under 1 Minute— We handle hosting, scaling, and maintenance

About This Leaderboard

This leaderboard ranks AI models by community votes from developers, with benchmark_livecodebench and other benchmark scores shown alongside, helping you find the best llm for coding.

Pricing is shown per million tokens from OpenRouter. Compare coding performance across LLMs ranked by community votes, with LiveCodeBench and Aider benchmark scores alongside pricing information.

Frequently Asked Questions

Based on benchmark_livecodebench scores and community developer votes, the top-ranked model currently leads our coding leaderboard. However, the best model depends on your use case — autocomplete, multi-file editing, or agentic coding each favor different models.
LiveCodeBench uses fresh competitive programming problems released after model training cutoffs, preventing data contamination. Models are scored on their ability to generate correct solutions, with scores reported as pass@1 percentages.
Mid-tier models typically offer the best value for coding tasks, delivering strong benchmark scores at a fraction of frontier model cost. Check the pricing column in our table to compare cost vs. benchmark performance for each model.
Benchmark scores are updated when new evaluations are published by Artificial Analysis. Community votes update in real-time. Pricing data is refreshed daily from OpenRouter.

Built by @aellman

Follow us:
Advertise | Terms of Service | Privacy Policy

2026 68 Ventures, LLC. All rights reserved.