Compare AI models

Specifications
Parameters
—110B
Context window
200k32k
Benchmarks
HumanEval
84.9%52.4%
MMLU
88.2%80.4%
GSM8K
95%85.4%
Overview
CompanyAnthropicQwen
Release dateMar 4 2024Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

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

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

On HumanEval, Claude 3 Opus leads at 84.9% vs Qwen1.5-110B at 52.4%. On MMLU, Claude 3 Opus leads at 88.2% vs Qwen1.5-110B at 80.4%. On GSM8K, Claude 3 Opus leads at 95% vs Qwen1.5-110B at 85.4%.