cd/entity/CwI-Benchยท homeโ€บ entitiesโ€บ CwI-Bench
grep -l @cwi-bench /news/*.json | wc -l โ†’ 1

CwI-Bench

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

04:00
2026-08-13
arxiv.org
artificial-intelligence

Self-Evolving Code-with-Image Reasoning

A new arXiv preprint (2608.11292v1) introduces Code-with-Image Bench (CwI-Bench), a benchmark of 30 task families requiring models to implement visual algorithms in Python. The authors report that GPTโ€ฆ

// co-occurs with top 3 entities
// topics top 4 topics