LiveCodeBench Pro
LiveCodeBench Pro: Frontier Hard Algorithmic Benchmark
Hard subset of LiveCodeBench focusing on advanced competitive programming problems (Div 1 / Div 2 Codeforces and Hard LeetCode).
Verified Model Leaderboard
Ranked by verified Pass@1 (%) score from official technical reports.
| Rank | AI Model & Provider | Score (Pass@1 (%)) | Evaluation Methodology | Verification Date | Source |
|---|---|---|---|---|---|
| #1 | OpenAI o1 OpenAI • Reinforcement Learning Reasoning Model | 63.8% | Pass@1 on hard competitive problems | Dec 2024 | LiveCodeBench Evaluation |
Evaluation Methodology & Harness
Pass@1 evaluation with strict execution time limits and memory boundaries to measure frontier algorithmic reasoning.
Curated set of 200+ Hard-tier competitive problems with comprehensive stress test suites.
Why This Benchmark Matters
Differentiates reasoning models (o1, o3-mini, DeepSeek-R1, Claude 3.7 Sonnet) from standard instruction-tuned models.
Known Limitations & Contamination Risks
Extremely challenging; standard non-reasoning models often score below 25%.
Data Accuracy & Verification Notice
AI model specifications, pricing records, and benchmark metrics published on this platform are compiled directly from authoritative sources (official provider documentation, research papers, and verified evaluation harnesses). Benchmark results reflect specific test harnesses and prompting methodologies; scores are not directly comparable across differing evaluation setups.