Other · model

1-bit Bonsai 4B benchmark scores

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

As of 2026-10-10, 1-bit Bonsai 4B (Other) has measured scores on 1 benchmark and estimated scores on 2 more.

Benchmark	Score	Source
IFBench	23.6%	estimated ± 9.6 pp, low confidence
IFEval	69.6%	measured
AA-IFBench	15.6%	estimated ± 7.4 pp, medium confidence