‹ PublicAI Index
The LLM benchmark aggregator.
JPT 4B
Other · 4B
Strongest in Calibration (#58 of 192), weakest in Routing & classification (#82 of 192). Above par in 3 of 3 scopes. Among the models it meets almost everywhere, it finishes behind Chon 1.0 12B and vLLM-SR d3 and ahead of deck-4B v1.0 and Jebadiah 9B v2.1.
§ 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.
Decisions55−11.9#67/1921/1
Calibration57.1−4.7#58/1921/1
Routing & classification52.9−21.1#82/1921/1
§ 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 JPT 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 40.8%JevBench · Calibration 86.9%
Badge
[](https://publicai.io/model-index/m/jpt-4b)