What it measures

Hard division Codeforces/ICPC competitive programming extension of LiveCodeBench.

Reading the measurement

A preference result depends on the opponents, judges and prompts in the comparison pool. Use it to study which outputs people or judges favor, then check correctness and reliability with a separate task-based evaluation. Ratings from different arenas do not share a universal scale.

Published evaluation

Source Elo rating calibrated against human programming-contest participants. Easy, medium and hard pass@1 and percentile are separate source measures.

Where this fits in an evaluation suite

The agent wrapper is part of the system. Pin tools, dependencies, timeouts, tests, and the repository revision. Compare contest coding separately from repository maintenance.

Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.

A reproducible comparison

Source Elo rating calibrated against human programming-contest participants. Easy, medium and hard pass@1 and percentile are separate source measures.

Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.

PRIMARY EVIDENCE & FURTHER READING

  1. LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? — published result table ↗

    Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He et al. · 2025

    All 19 authors

    Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He, Dongruixuan Li, Stanley Wei, Hangyi Hao, Jianzhu Yao, Peiyao Sheng, Zixuan Wang, Wenhao Chai, Aleksandra Korolova, Peter Henderson, Sanjeev Arora, Pramod Viswanath, Jingbo Shang, Saining Xie

Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.