Compare AI models

Specifications
Parameters
—110B
Context window
200k32k
Benchmarks
HumanEval
75.9%52.4%
MMLU
76.7%80.4%
GSM8K
88.9%85.4%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude 3 Haiku leads Qwen1.5-110B on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Claude 3 Haiku shipped 52 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Haiku) vs 32k (Qwen1.5-110B). Claude 3 Haiku is closed, while Qwen1.5-110B is open weight.

On HumanEval, Claude 3 Haiku leads at 75.9% vs Qwen1.5-110B at 52.4%. On MMLU, Qwen1.5-110B leads at 80.4% vs Claude 3 Haiku at 76.7%. On GSM8K, Claude 3 Haiku leads at 88.9% vs Qwen1.5-110B at 85.4%.