With CliffCompaction, open-weight models beat closed ones in long-horizon sessions

Tim_Dettmers · x · 2026-09-23

Tim Dettmers observes that CliffCompaction creates a usefulness gap between open-weight models and closed models that hide their reasoning traces: for long-horizon sessions, open-weight models are far stronger, and some models simply "compact better" than others. This builds on his point that the tool works much better with full thinking traces — consistent with frontier labs, where OpenAI's math and ARC-AGI results largely stem from trace-aware autocompaction.

Related event: Tim Dettmers Open-Sources CliffCompaction, Cutting Long-Context Agent Token Costs by 50%(8 posts)→

Original post →

More from coding & agent

coding & agent channel →