‹ PublicAI Index
The LLM benchmark aggregator.
Arbiter 4B
Other · 4B
Strongest in Decisions (#162 of 234), weakest in Calibration (#172 of 234). Above par in 0 of 3 scopes. Among the models it meets almost everywhere, it finishes behind Baselabs mammoth-1 and KnowLine 31B-Gen1 and ahead of DecisionNode Edge 0.9.2 and D1A on Gemma 4 E4B.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Decisions46.4−19.5#162/2341/1
Routing & classification43.8−27.9#163/2341/1
Calibration49.1−12.6#172/2341/1
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Arbiter 4B, left for the other.
§ 3 · Sources
Where the numbers come from
1 publication, 2 figures. Every one links to the page it was read from.
JevBench · Intelligence 27.4%JevBench · Calibration 77.2%
Badge
[](https://publicai.io/model-index/m/arbiter-4b)