Compare AI models

Specifications
Parameters
70B6B
Context window
128k8k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%58.5%
MATH
77%25.7%
MMLU
86%61.4%
Overview
CompanyMetaZ.ai
Release dateDec 6 2024Oct 27 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads ChatGLM3-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). ChatGLM3-6B shipped 406 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while ChatGLM3-6B has 6B. Context windows are 128k (LLaMA 3.3) vs 8k (ChatGLM3-6B).

On HumanEval, LLaMA 3.3 leads at 88.4% vs ChatGLM3-6B at 58.5%. On MATH, LLaMA 3.3 leads at 77% vs ChatGLM3-6B at 25.7%. On MMLU, LLaMA 3.3 leads at 86% vs ChatGLM3-6B at 61.4%.