Compare AI models

Specifications
Parameters
8B6B
Context window
8k32k
Benchmarks
HumanEval
36.22%9.8%
HellaSwag
83.03%57%
MMLU
69.51%45.2%
GSM8K
58.45%25.9%
Overview
CompanyNVIDIAZ.ai
Release dateAug 21 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral NeMo Minitron 8B leads ChatGLM2-6B on 4 of the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). ChatGLM2-6B shipped 423 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while ChatGLM2-6B has 6B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 32k (ChatGLM2-6B).

On HumanEval, Mistral NeMo Minitron 8B leads at 36.22% vs ChatGLM2-6B at 9.8%. On HellaSwag, Mistral NeMo Minitron 8B leads at 83.03% vs ChatGLM2-6B at 57%. On MMLU, Mistral NeMo Minitron 8B leads at 69.51% vs ChatGLM2-6B at 45.2%. On GSM8K, Mistral NeMo Minitron 8B leads at 58.45% vs ChatGLM2-6B at 25.9%.