Compare AI models

Specifications
Parameters
2B/7B6B
Context window
8k32k
Benchmarks
HumanEval
32.3%9.8%
MATH
24.3%6.9%
HellaSwag
81.2%57%
MMLU
64.3%45.2%
GSM8K
46.4%25.9%
Overview
CompanyGoogleZ.ai
Release dateFeb 21 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemma 1 leads ChatGLM2-6B on 5 of the 5 benchmarks they both report. ChatGLM2-6B shipped 241 days before Gemma 1, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while ChatGLM2-6B has 6B. Context windows are 8k (Gemma 1) vs 32k (ChatGLM2-6B).

On HumanEval, Gemma 1 leads at 32.3% vs ChatGLM2-6B at 9.8%. On MATH, Gemma 1 leads at 24.3% vs ChatGLM2-6B at 6.9%. On HellaSwag, Gemma 1 leads at 81.2% vs ChatGLM2-6B at 57%. On MMLU, Gemma 1 leads at 64.3% vs ChatGLM2-6B at 45.2%. On GSM8K, Gemma 1 leads at 46.4% vs ChatGLM2-6B at 25.9%.