CodegenBench

What is CodegenBench?

CodegenBench evaluates LLM-generated parallel code across x86_64, Sunway, and Kunpeng architectures using BLAS routines and specialized kernels. Scoring…

Released

2026-06-01

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/2606.04023

CodegenBench paper

• Paper https://arxiv.org/abs/2606.04023
• Website https://anonymous.4open.science/r/CodegenBench-EDE1/

Which sources cite CodegenBench?

• CodegenBench

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