Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
200k4k
Benchmarks
GSM8K
92.3%96.7%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Aug 8 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2-Math leads Claude 3 Sonnet on 1 of the 1 benchmark they both report (GSM8K). Claude 3 Sonnet shipped 157 days before Qwen2-Math, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Sonnet) vs 4k (Qwen2-Math). Claude 3 Sonnet is closed, while Qwen2-Math is open weight.

On GSM8K, Qwen2-Math leads at 96.7% vs Claude 3 Sonnet at 92.3%.