Compare AI models

Specifications
Parameters
—14B
Context window
200k2k
Benchmarks
HumanEval
88.1%32.3%
MMLU
80.9%66.3%
Overview
CompanyAnthropicQwen
Release dateOct 22 2024Sep 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku leads Qwen-14B on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Qwen-14B shipped 393 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 2k (Qwen-14B). Claude 3.5 Haiku is closed, while Qwen-14B is open weight.

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs Qwen-14B at 32.3%. On MMLU, Claude 3.5 Haiku leads at 80.9% vs Qwen-14B at 66.3%.