Benchmark RadarAI BENCHMARK PROFILE
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
- Readiness
- Paper only
- Primary field
- General AI
Why it matters
Provides a large-scale benchmark for system-level compiler issue resolution, addressing a gap in LLM evaluation for complex software engineering tasks.
Motivation
LLVM is a widely used compiler infrastructure whose scale and complexity make issue resolution labor-intensive and challenging.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.