Φ-Bench

What is Φ-Bench?

Evaluates LLMs on tasks across the LLM infrastructure stack, from kernel completion to end-to-end system optimization using real-world code repositories.

Released

2026-09-09

Evaluates

Language & Knowledge, Software & AI Compute, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.10226

Φ-Bench paper

• Paper https://arxiv.org/abs/2609.10226

Which sources cite Φ-Bench?

• Φ-Bench

Related Language & Knowledge, Software & AI Compute, cs.CL benchmarks

• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABC-Bench
• Active-SWE
• ActiveSciBench
• AdaMem-Bench
• AdaPlanBench