Compare AI models

Specifications
Parameters
—7B
Context window
200k64k
Benchmarks
HumanEval
88.1%83.5%
Overview
CompanyAnthropicQwen
Release dateOct 22 2024Apr 16 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 189 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 64k (CodeQwen1.5). Claude 3.5 Haiku is closed, while CodeQwen1.5 is open weight.

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs CodeQwen1.5 at 83.5%.