Compare AI models

Specifications
Parameters
8B1.5B/7B/72B
Context window
8k4k
Benchmarks
GSM8K
58.45%95.9%
Overview
CompanyNVIDIAQwen
Release dateAug 21 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Mistral NeMo Minitron 8B on 1 of the 1 benchmark they both report (GSM8K). Mistral NeMo Minitron 8B shipped 29 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 4k (Qwen2.5-Math).

On GSM8K, Qwen2.5-Math leads at 95.9% vs Mistral NeMo Minitron 8B at 58.45%.