← back to paper

Review history

arxiv: 2608.02705 · 2 revisions

Can Training Logs Make Model Comparisons More Precise?

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   121444 ms 12010 in 13707 out 2026-08-15T15:00:52.177813+00:00
2. 2026-08-07 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   175487 ms 12018 in 18919 out 2026-08-07T00:09:47.107012+00:00