Compare AI models

Specifications
Parameters
—110B
Context window
8k32k
API pricing
Cheapest input
$30.00Azure—
Cheapest output
$60.00Azure—
$9,000Azure—
Benchmarks
HumanEval
67%52.4%
HellaSwag
95.3%87.5%
MMLU
86.4%80.4%
GSM8K
92%85.4%
Overview
CompanyOpenAIQwen
Release dateMar 14 2023Apr 25 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4 leads Qwen1.5-110B on 4 of the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). GPT-4 shipped 408 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (GPT-4) vs 32k (Qwen1.5-110B). GPT-4 is closed, while Qwen1.5-110B is open weight.

On HumanEval, GPT-4 leads at 67% vs Qwen1.5-110B at 52.4%. On HellaSwag, GPT-4 leads at 95.3% vs Qwen1.5-110B at 87.5%. On MMLU, GPT-4 leads at 86.4% vs Qwen1.5-110B at 80.4%. On GSM8K, GPT-4 leads at 92% vs Qwen1.5-110B at 85.4%.