‹ PublicAI Index
The LLM benchmark aggregator.
Ministral 3 14B
Mistral · 14B · open weights
Strongest in Factual grounding (#98 of 104), weakest in Safety (#300 of 327). Above par in 0 of 4 scopes. Among the models it meets almost everywhere, it finishes behind Claude Opus 5.5 and GPT-6 Astra and ahead of O3 Mini and Llama 3.1 8B Instruct.
§ 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.
Agents40.4−25.9#282/2982/6
Knowledge work34.6−36.1#185/2082/2
Safety42.5−18.9#300/3271/3
Factual grounding26−44.7#98/1041/1
§ 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 Ministral 3 14B, 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.
GDPval-AA 255
AA-Briefcase 132
Vectara · Factual consistency 80.6%
Badge
[](https://publicai.io/model-index/m/ministral-3-14b)