Compare AI models

Specifications
Parameters
8B—
Context window
8k200k
Benchmarks
HumanEval
36.22%99.3%
MMLU
69.51%90.3%
Overview
CompanyNVIDIAOpenAI
Release dateAug 21 2024Apr 16 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

o4-mini-high leads Mistral NeMo Minitron 8B on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Mistral NeMo Minitron 8B shipped 238 days before o4-mini-high, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Mistral NeMo Minitron 8B) vs 200k (o4-mini-high). Mistral NeMo Minitron 8B is open weight, while o4-mini-high is closed.

On HumanEval, o4-mini-high leads at 99.3% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, o4-mini-high leads at 90.3% vs Mistral NeMo Minitron 8B at 69.51%.