Compare AI models

Specifications
Parameters
2B/7B6B
Context window
8k8k
Benchmarks
HumanEval
32.3%58.5%
MATH
24.3%25.7%
HellaSwag
81.2%79.7%
MMLU
64.3%61.4%
GSM8K
46.4%72.3%
Overview
CompanyGoogleZ.ai
Release dateFeb 21 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

ChatGLM3-6B leads Gemma 1 on 3 of the 5 benchmarks they both report. ChatGLM3-6B shipped 117 days before Gemma 1, so benchmark comparisons should account for the intervening progress.

Gemma 1 has 2B/7B parameters, while ChatGLM3-6B has 6B. Context windows are 8k (Gemma 1) vs 8k (ChatGLM3-6B).

On HumanEval, ChatGLM3-6B leads at 58.5% vs Gemma 1 at 32.3%. On MATH, ChatGLM3-6B leads at 25.7% vs Gemma 1 at 24.3%. On HellaSwag, Gemma 1 leads at 81.2% vs ChatGLM3-6B at 79.7%. On MMLU, Gemma 1 leads at 64.3% vs ChatGLM3-6B at 61.4%. On GSM8K, ChatGLM3-6B leads at 72.3% vs Gemma 1 at 46.4%.