Compare AI models

Specifications
Parameters
—6B
Context window
1M32k
Benchmarks
HumanEval
71.9%9.8%
MATH
58.5%6.9%
HellaSwag
92.5%57%
MMLU
81.9%45.2%
GSM8K
91.7%25.9%
Overview
CompanyGoogleZ.ai
Release dateFeb 15 2024Jun 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 1.5 Pro leads ChatGLM2-6B on 5 of the 5 benchmarks they both report. ChatGLM2-6B shipped 235 days before Gemini 1.5 Pro, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, Gemini 1.5 Pro leads at 71.9% vs ChatGLM2-6B at 9.8%. On MATH, Gemini 1.5 Pro leads at 58.5% vs ChatGLM2-6B at 6.9%. On HellaSwag, Gemini 1.5 Pro leads at 92.5% vs ChatGLM2-6B at 57%. On MMLU, Gemini 1.5 Pro leads at 81.9% vs ChatGLM2-6B at 45.2%. On GSM8K, Gemini 1.5 Pro leads at 91.7% vs ChatGLM2-6B at 25.9%.