Pith. sign in

← back to paper

Review history

arxiv: 2606.27537 · 6 revisions

MemoBench: Benchmarking World Modeling in Dynamically Changing Environments

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 7.0
    157348 ms 24092 in 16398 out 2026-08-02T09:55:40.454826+00:00
  2. 2026-07-14 CONDITIONAL HIGH v1.1.0-grok45 novelty 7.0
    38916 ms 30104 in 3798 out 2026-07-14T17:13:19.749447+00:00
  3. 2026-07-03 UNVERDICTED LOW v0.9.1-grok novelty 7.0
    25718 ms 5707 in 1265 out 2026-07-03T22:42:19.722164+00:00
  4. 2026-07-02 UNVERDICTED LOW v0.9.1-grok novelty 6.0
    16808 ms 5707 in 1022 out 2026-07-02T20:50:30.444064+00:00
  5. 2026-07-01 UNVERDICTED LOW v0.9.1-grok novelty 7.0
    29262 ms 5707 in 1164 out 2026-07-01T06:23:58.213603+00:00
  6. 2026-06-29 UNVERDICTED LOW v0.9.1-grok novelty 7.0
    35008 ms 5707 in 949 out 2026-06-29T02:00:25.681890+00:00