Compare AI models

Specifications
Parameters
—1.5B/7B/72B
Context window
200k4k
Benchmarks
GSM8K
95%95.9%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Claude 3 Opus on 1 of the 1 benchmark they both report (GSM8K). Claude 3 Opus shipped 199 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Opus) vs 4k (Qwen2.5-Math). Claude 3 Opus is closed, while Qwen2.5-Math is open weight.

On GSM8K, Qwen2.5-Math leads at 95.9% vs Claude 3 Opus at 95%.