Compare AI models

Specifications
Parameters
—14.3B
Context window
200k32k
Benchmarks
HumanEval
88.1%34.2%
MMLU
80.9%62.5%
Overview
CompanyAnthropicQwen
Release dateOct 22 2024Mar 28 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3.5 Haiku leads Qwen1.5-MoE on 2 of the 2 benchmarks they both report (HumanEval, MMLU). Qwen1.5-MoE shipped 208 days before Claude 3.5 Haiku, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3.5 Haiku) vs 32k (Qwen1.5-MoE). Claude 3.5 Haiku is closed, while Qwen1.5-MoE is open weight.

On HumanEval, Claude 3.5 Haiku leads at 88.1% vs Qwen1.5-MoE at 34.2%. On MMLU, Claude 3.5 Haiku leads at 80.9% vs Qwen1.5-MoE at 62.5%.