Compare AI models

Specifications
Parameters
7B/67B8B
Context window
4k8k
Benchmarks
HumanEval
73.8%36.22%
MMLU
71.1%69.51%
GSM8K
84.1%58.45%
Overview
CompanyDeepSeekNVIDIA
Release dateNov 29 2023Aug 21 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-LLM leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). DeepSeek-LLM shipped 266 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while Mistral NeMo Minitron 8B has 8B. Context windows are 4k (DeepSeek-LLM) vs 8k (Mistral NeMo Minitron 8B).

On HumanEval, DeepSeek-LLM leads at 73.8% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, DeepSeek-LLM leads at 71.1% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, DeepSeek-LLM leads at 84.1% vs Mistral NeMo Minitron 8B at 58.45%.