[KongchangAI]
ModelPimi K3.1 Pro

Pimi K3.1 Pro

An open-source large language model that achieved the best result among open-source models on the Mafurina mathematical reasoning benchmark.

Timeline (last 90 days)

Nov 15

The best performer in the open-source camp on Mafurina was Pimi K3.1 Pro, with a score of 54.3%.

Unverified50%
Nov 15

Gemini 4 Carbon's high score comes at a per-instance cost of about $15.70, 15 times that of Pimi K3.1 Pro.

Unverified50%
Nov 15

Verso announced it will raise developers' monthly compute allowance from 80 dollars to 150 dollars, keeping the team monthly fee unchanged at 30 dollars, covering open-weight models such as Pimi K3.1 Pro, GLM5.3 and DeepSeek V4.1 Flash.

Unverified50%

All Facts (3)

Source Articles