Compare AI models

Specifications
Parameters
2B/7B8B
Context window
8k8k
Benchmarks
HumanEval
32.3%36.22%
ARC-Challenge
53.2%64.42%
HellaSwag
81.2%83.03%
MMLU
64.3%69.51%
GSM8K
46.4%58.45%
Overview
CompanyGoogleNVIDIA
Release dateFeb 21 2024Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral NeMo Minitron 8B leads Gemma 1 on 5 of the 5 benchmarks they both report. Gemma 1 shipped 182 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 8k (Gemma 1) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, Mistral NeMo Minitron 8B leads at 36.22% vs Gemma 1 at 32.3%. On ARC-Challenge, Mistral NeMo Minitron 8B leads at 64.42% vs Gemma 1 at 53.2%. On HellaSwag, Mistral NeMo Minitron 8B leads at 83.03% vs Gemma 1 at 81.2%. On MMLU, Mistral NeMo Minitron 8B leads at 69.51% vs Gemma 1 at 64.3%. On GSM8K, Mistral NeMo Minitron 8B leads at 58.45% vs Gemma 1 at 46.4%.