2.5B · GGUF · Apache-2.0

Vulcan 2.5B Math

The Vulcan model that leans toward mathematics. It came from the same selection league as Vulcan 2.5B Coder and posted the league's best score on the final four question sets, which include the maths questions.

base: CherryPit 1.2CherryPit 1.2 85% · SWE 9% · Math 5%strength 1.05
League

How it scored

5.02last four sets, best in the league
0.728per question overall, 4th
33 / 49answers correct
Full results

League table

Every candidate from the selection league. Scores are per question, with 0, 0.5 or 1 for each answer. "Last four" is the score on the final four question sets, which include mathematics. Questions varied between models, so treat close scores as ties.

#modeltieransweredcorrectscorelast fourmixlicence
Download

Files

Files and a like-for-like maths benchmark are coming soon.