CRJudgeBench

What is CRJudgeBench?

Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers.

Released

2026-09-29

Evaluates

Code & Software, Software & AI Compute, cs.SE

Openness

unknown

Importer

Claire Radar

Review status

rule-auto-admitted

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.37216

CRJudgeBench paper and dataset

• Paper https://arxiv.org/abs/2609.37216
• Dataset https://huggingface.co/datasets/dcloud347/CRJudgeBenchmark

Which sources cite CRJudgeBench?

• CRJudgeBench

Related Code & Software, Software & AI Compute, cs.SE benchmarks

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