LiveCodeBench Pro

A harder competitive-programming benchmark family built from Codeforces, ICPC, and IOI problems, with quarter-specific public leaderboards and difficulty-aware reporting.

6 models

Higher is better.

1GPT-5.4OpenAI87.5
2Gemini 3.1 ProGoogle82.9
3Muse SparkMeta80.0
4Grok 4.20xAI74.2
5Claude Opus 4.6Anthropic70.7
6MiniCPM5-1BOpenBMB22.7

Higher is better. Bar colour: blue proprietary, orange open weights, green other.

About this benchmark

Metric: Competitive programming
Tasks: Quarter-specific contest programming sets
Authors: LiveCodeBench Pro authors (2025)
Source: LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? ↗

Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.