Compare AI models

Specifications
Parameters
—6B
Context window
32k8k
Benchmarks
HumanEval
74.4%58.5%
MATH
53.2%25.7%
HellaSwag
87.8%79.7%
MMLU
83.7%61.4%
GSM8K
88.9%72.3%
Overview
CompanyGoogleZ.ai
Release dateFeb 8 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.0 Ultra leads ChatGLM3-6B on 5 of the 5 benchmarks they both report. ChatGLM3-6B shipped 104 days before Gemini 1.0 Ultra, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Gemini 1.0 Ultra) vs 8k (ChatGLM3-6B). Gemini 1.0 Ultra is closed, while ChatGLM3-6B is open weight.

On HumanEval, Gemini 1.0 Ultra leads at 74.4% vs ChatGLM3-6B at 58.5%. On MATH, Gemini 1.0 Ultra leads at 53.2% vs ChatGLM3-6B at 25.7%. On HellaSwag, Gemini 1.0 Ultra leads at 87.8% vs ChatGLM3-6B at 79.7%. On MMLU, Gemini 1.0 Ultra leads at 83.7% vs ChatGLM3-6B at 61.4%. On GSM8K, Gemini 1.0 Ultra leads at 88.9% vs ChatGLM3-6B at 72.3%.