Compare AI models

Specifications
Parameters
8B0.5B/1.5B/3B/7B/14B/32B/72B
Context window
8k128k
API pricing
Cheapest input
—$0.288DeepInfra
Cheapest output
—$0.32DeepInfra
—$92.00DeepInfra · fp8
Benchmarks
HumanEval
36.22%86.6%
GSM8K
58.45%95.8%
Overview
CompanyNVIDIAQwen
Release dateAug 21 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5 leads Mistral NeMo Minitron 8B on 2 of the 2 benchmarks they both report (HumanEval, GSM8K). Mistral NeMo Minitron 8B shipped 29 days before Qwen2.5, so benchmark comparisons should account for the intervening progress.

Mistral NeMo Minitron 8B has 8B parameters, while Qwen2.5 has 0.5B/1.5B/3B/7B/14B/32B/72B. Context windows are 8k (Mistral NeMo Minitron 8B) vs 128k (Qwen2.5).

On HumanEval, Qwen2.5 leads at 86.6% vs Mistral NeMo Minitron 8B at 36.22%. On GSM8K, Qwen2.5 leads at 95.8% vs Mistral NeMo Minitron 8B at 58.45%.