Compare AI models

Specifications
Parameters
—6B
Context window
1M32k
Benchmarks
HumanEval
74.3%9.8%
MATH
54.9%6.9%
HellaSwag
86.5%57%
MMLU
78.9%45.2%
GSM8K
86.2%25.9%
Overview
CompanyGoogleZ.ai
Release dateMay 14 2024Jun 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Flash leads ChatGLM2-6B on 5 of the 5 benchmarks they both report. ChatGLM2-6B shipped 324 days before Gemini 1.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 1.5 Flash) vs 32k (ChatGLM2-6B). Gemini 1.5 Flash is closed, while ChatGLM2-6B is open weight.

On HumanEval, Gemini 1.5 Flash leads at 74.3% vs ChatGLM2-6B at 9.8%. On MATH, Gemini 1.5 Flash leads at 54.9% vs ChatGLM2-6B at 6.9%. On HellaSwag, Gemini 1.5 Flash leads at 86.5% vs ChatGLM2-6B at 57%. On MMLU, Gemini 1.5 Flash leads at 78.9% vs ChatGLM2-6B at 45.2%. On GSM8K, Gemini 1.5 Flash leads at 86.2% vs ChatGLM2-6B at 25.9%.