Compare AI models

Specifications
Parameters
8B72B
Context window
8k32k
Benchmarks
HumanEval
36.22%35.4%
MMLU
69.51%77.4%
GSM8K
58.45%78.9%
Overview
CompanyNVIDIAQwen
Release dateAug 21 2024Nov 30 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen-72B leads Mistral NeMo Minitron 8B on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen-72B shipped 265 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while Qwen-72B has 72B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 32k (Qwen-72B).

On HumanEval, Mistral NeMo Minitron 8B leads at 36.22% vs Qwen-72B at 35.4%. On MMLU, Qwen-72B leads at 77.4% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, Qwen-72B leads at 78.9% vs Mistral NeMo Minitron 8B at 58.45%.