Compare AI models

Specifications
Parameters
—110B
Context window
200k32k
Benchmarks
HumanEval
73%52.4%
MMLU
81.5%80.4%
GSM8K
92.3%85.4%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

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

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

On HumanEval, Claude 3 Sonnet leads at 73% vs Qwen1.5-110B at 52.4%. On MMLU, Claude 3 Sonnet leads at 81.5% vs Qwen1.5-110B at 80.4%. On GSM8K, Claude 3 Sonnet leads at 92.3% vs Qwen1.5-110B at 85.4%.