Compare AI models

Specifications
Parameters
8B0.5B/1.5B/7B/57B/72B
Context window
8k128k
Benchmarks
HumanEval
36.22%86%
MMLU
69.51%82.3%
GSM8K
58.45%91.1%
Overview
CompanyNVIDIAQwen
Release dateAug 21 2024Jun 6 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2 leads Mistral NeMo Minitron 8B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Qwen2 shipped 76 days before Mistral NeMo Minitron 8B, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while Qwen2 has 0.5B/1.5B/7B/57B/72B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 128k (Qwen2).

On HumanEval, Qwen2 leads at 86% vs Mistral NeMo Minitron 8B at 36.22%. On MMLU, Qwen2 leads at 82.3% vs Mistral NeMo Minitron 8B at 69.51%. On GSM8K, Qwen2 leads at 91.1% vs Mistral NeMo Minitron 8B at 58.45%.