Compare AI models

Specifications
Parameters
—0.5B/1.5B/3B/7B/14B/32B
Context window
100k128k
API pricing
Cheapest input
—$0.66Cloudflare
Cheapest output
—$1.00Cloudflare
—$182Cloudflare
Benchmarks
HumanEval
71.2%92.7%
MMLU
78.5%77.6%
GSM8K
88%93%
Overview
CompanyAnthropicQwen
Release dateJul 11 2023Sep 19 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Coder leads Claude 2 on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 2 shipped 436 days before Qwen2.5-Coder, so benchmark comparisons should account for the intervening progress.

Context windows are 100k (Claude 2) vs 128k (Qwen2.5-Coder). Claude 2 is closed, while Qwen2.5-Coder is open weight.

On HumanEval, Qwen2.5-Coder leads at 92.7% vs Claude 2 at 71.2%. On MMLU, Claude 2 leads at 78.5% vs Qwen2.5-Coder at 77.6%. On GSM8K, Qwen2.5-Coder leads at 93% vs Claude 2 at 88%.