Compare AI models

Specifications
Parameters
—6B
Context window
1M8k
Benchmarks
HumanEval
71.9%58.5%
MATH
58.5%25.7%
HellaSwag
92.5%79.7%
MMLU
81.9%61.4%
GSM8K
91.7%72.3%
Overview
CompanyGoogleZ.ai
Release dateFeb 15 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Pro leads ChatGLM3-6B on 5 of the 5 benchmarks they both report. ChatGLM3-6B shipped 111 days before Gemini 1.5 Pro, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Pro) vs 8k (ChatGLM3-6B). Gemini 1.5 Pro is closed, while ChatGLM3-6B is open weight.

On HumanEval, Gemini 1.5 Pro leads at 71.9% vs ChatGLM3-6B at 58.5%. On MATH, Gemini 1.5 Pro leads at 58.5% vs ChatGLM3-6B at 25.7%. On HellaSwag, Gemini 1.5 Pro leads at 92.5% vs ChatGLM3-6B at 79.7%. On MMLU, Gemini 1.5 Pro leads at 81.9% vs ChatGLM3-6B at 61.4%. On GSM8K, Gemini 1.5 Pro leads at 91.7% vs ChatGLM3-6B at 72.3%.