Compare AI models

Specifications
Parameters
—7B/14B
Context window
200k1M
Benchmarks
HumanEval
84.9%88.4%
GSM8K
95%94.8%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Jan 27 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3 Opus and Qwen2.5-1M are evenly matched across the 2 benchmarks they both report (HumanEval, GSM8K). Claude 3 Opus shipped 329 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Opus) vs 1M (Qwen2.5-1M). Claude 3 Opus is closed, while Qwen2.5-1M is open weight.

On HumanEval, Qwen2.5-1M leads at 88.4% vs Claude 3 Opus at 84.9%. On GSM8K, Claude 3 Opus leads at 95% vs Qwen2.5-1M at 94.8%.