← back to paper

Review history

arxiv: 2603.29759 · 2 revisions

TSHA: A Benchmark for Visual Language Models in Trustworthy Safety Hazard Assessment Scenarios

1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   152806 ms 18313 in 17684 out 2026-08-02T17:00:28.227049+00:00
2. 2026-07-13 UNVERDICTED LOW v1.1.0-grok45 novelty 5.0
   34539 ms 12976 in 2873 out 2026-07-13T15:34:10.237537+00:00