LLVM-Bench

What is LLVM-Bench?

LLVM-Bench evaluates LLMs on resolving LLVM compiler issues with 423 real-world tasks, using an automated evaluation platform.

Released

2026-07-01

Evaluates

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

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.00700

LLVM-Bench paper

• Paper https://arxiv.org/abs/2607.00700

Which sources cite LLVM-Bench?

• LLVM-Bench

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

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