Compare AI models

Specifications
Parameters
—6B
Context window
8k8k
API pricing
Cheapest input
$30.00Azure—
Cheapest output
$60.00Azure—
$9,000Azure—
Benchmarks
HumanEval
67%58.5%
HellaSwag
95.3%79.7%
MMLU
86.4%61.4%
GSM8K
92%72.3%
Overview
CompanyOpenAIZ.ai
Release dateMar 14 2023Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4 leads ChatGLM3-6B on 4 of the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). GPT-4 shipped 227 days before ChatGLM3-6B, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (GPT-4) vs 8k (ChatGLM3-6B). GPT-4 is closed, while ChatGLM3-6B is open weight.

On HumanEval, GPT-4 leads at 67% vs ChatGLM3-6B at 58.5%. On HellaSwag, GPT-4 leads at 95.3% vs ChatGLM3-6B at 79.7%. On MMLU, GPT-4 leads at 86.4% vs ChatGLM3-6B at 61.4%. On GSM8K, GPT-4 leads at 92% vs ChatGLM3-6B at 72.3%.