UOJ-Bench

What is UOJ-Bench?

UOJ-Bench is a benchmark for evaluating LLMs in code generation, hacking, and repair, built from real-world submissions on the Universal Online Judge and…

Released

2026-06-11

Evaluates

Code, Code & Software, Code generation, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.12864

UOJ-Bench paper

• Paper https://arxiv.org/abs/2606.12864

Which sources cite UOJ-Bench?

• UOJ-Bench

Related Code, Code & Software, Code generation, Software & AI Compute benchmarks

• Active-SWE
• AFT-Bench
• Agent App Benchmark
• Agent Retrieval Bench
• Agent Systems Benchmark (ASB)
• Agentic Evaluation in 2D Mazes
• Agentic Security Benchmark
• AgentInfraBench