‹ PublicAI Index
The LLM benchmark aggregator.
Celeris 1
Celeris
Strongest in Knowledge work (#145 of 177), weakest in Agents (#237 of 267). Above par in 0 of 4 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and GPT-6 Astra and ahead of Gemma 3 4B It and UI-TARS 1.5 7B.
§ 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.
Core abilities41.6−25.8#178/2041/3
General intelligence37.9−32.2#186/2041/3
Agents40.1−28#237/2672/5
Knowledge work37.1−36.5#145/1772/2
§ 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 Celeris 1, left for the other.
§ 3 · Sources
Where the numbers come from
3 publications, 3 figures. Every one links to the page it was read from.
Artificial Analysis Intelligence Index 6
GDPval-AA 288
AA-Briefcase 153
Badge
[](https://publicai.io/model-index/m/celeris-1)