Pith. sign in

← back to paper

Review history

arxiv: 2607.05264 · 2 revisions

SteelBench: Evaluating Vision-Language Models in Real-World Industrial Environments

  1. 2026-07-11 ACCEPT HIGH v1.1.0-grok45 novelty 7.0
    38265 ms 37886 in 3671 out 2026-07-11T07:27:00.241756+00:00
  2. 2026-07-07 ACCEPT HIGH v1.1.0-glm novelty 7.0
    419412 ms 36577 in 3982 out 2026-07-07T20:41:42.722223+00:00