‹ PublicAI Index
The LLM benchmark aggregator.
Sieve 31B V2
Other · 31B
Strongest in Calibration (#4 of 234), weakest in Routing & classification (#27 of 234). Above par in 3 of 3 scopes. Among the models it meets almost everywhere, it finishes behind Baselabs mammoth-1 and Fastino GLiDE 1.2 and ahead of AJev lm6q and Nimble V4.
§ 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.
Decisions63.5−2.4#16/2341/1
Calibration61.1−0.6#4/2341/1
Routing & classification66−5.7#27/2341/1
§ 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 Sieve 31B V2, 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 68.7%JevBench · Calibration 93.4%
Badge
[](https://publicai.io/model-index/m/sieve-31b-v2)