Compare AI models

Specifications
Parameters
—6B
Context window
1M8k
Benchmarks
HumanEval
74.3%58.5%
MATH
54.9%25.7%
HellaSwag
86.5%79.7%
MMLU
78.9%61.4%
GSM8K
86.2%72.3%
Overview
CompanyGoogleZ.ai
Release dateMay 14 2024Oct 27 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Flash leads ChatGLM3-6B on 5 of the 5 benchmarks they both report. ChatGLM3-6B shipped 200 days before Gemini 1.5 Flash, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, Gemini 1.5 Flash leads at 74.3% vs ChatGLM3-6B at 58.5%. On MATH, Gemini 1.5 Flash leads at 54.9% vs ChatGLM3-6B at 25.7%. On HellaSwag, Gemini 1.5 Flash leads at 86.5% vs ChatGLM3-6B at 79.7%. On MMLU, Gemini 1.5 Flash leads at 78.9% vs ChatGLM3-6B at 61.4%. On GSM8K, Gemini 1.5 Flash leads at 86.2% vs ChatGLM3-6B at 72.3%.