Pith. sign in

← back to paper

Review history

arxiv: 2606.09426 · 2 revisions

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

  1. 2026-07-12 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.5
    43455 ms 37673 in 3957 out 2026-07-12T14:35:57.359719+00:00
  2. 2026-06-27 UNVERDICTED LOW v0.9.1-grok novelty 6.0
    19418 ms 5776 in 1421 out 2026-06-27T16:27:51.552891+00:00