‹ PublicAI Index
The LLM benchmark aggregator.
decisio v0.8.0 on gemma-4-12B-it
Google · 12B
Strongest in Calibration (#33 of 192), weakest in Routing & classification (#48 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 JPT 35B A3B and Cygnet.
§ 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.
Decisions58.9−8#37/1921/1
Calibration58.7−3.1#33/1921/1
Routing & classification59.2−14.8#48/1921/1
§ 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 decisio v0.8.0 on gemma-4-12B-it, 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 52.3%JevBench · Calibration 89.2%
Badge
[](https://publicai.io/model-index/m/decisio-v0-8-0-on-gemma-4-12b-it)