LiveCodeBench

Tools & Infrastructure

LiveCodeBench is a continuously updated coding benchmark that uses fresh contest-style problems to resist data contamination, providing a reliable measure of code generation performance.

🌐 Visit website ↗

🔗 Similar tools

Wolfram LLM Benchmarking Project

The Wolfram LLM Benchmarking Project is a continuously updated code generation benchmark t…
JetBrains Kotlin Benchmark

JetBrains Kotlin Benchmark is a public benchmark from JetBrains that evaluates AI coding a…
Stripe Agent Benchmark

Stripe Agent Benchmark is an end-to-end evaluation suite that tests whether AI agents can …
EGC ★ 48

EGC is a cross-session persistent memory layer for AI coding agents, including Claude Code…
Arena (formerly LMArena / Chatbot Arena)

Arena (formerly LMArena/Chatbot Arena) is a crowdsourced AI benchmark that ranks models vi…
DeepSeek-Coder-V2 ★ 7.0k

DeepSeek-Coder-V2 is a code generation model that matches GPT-4's performance on standard …

Models & AI Labs