all the models — AI benchmark observatory
← Benchmarks

LiveCodeBench Pro

LiveCodeBench Pro is an advanced evaluation benchmark for large language models for code that uses Elo ratings to rank models based on their performance on coding tasks. It evaluates models on real-world coding problems from programming contests (LeetCode, AtCoder, CodeForces) and provides a relative ranking system where higher Elo scores indicate superior performance.

id livecodebench-pro · max 3000 · 5 models reported

#ModelScore
1Gemini 3.1 Pro
Google
2887.00
2Gemini 3 Pro
Google
2439.00
3Gemini 3 Flash
Google
2316.00
4Seed 1.8
ByteDance
1930.00
5Muse Spark
Meta
0.80