Compare AI models

Specifications
Parameters
70B6B
Context window
128k32k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%9.8%
MATH
77%6.9%
MMLU
86%45.2%
Overview
CompanyMetaZ.ai
Release dateDec 6 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads ChatGLM2-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). ChatGLM2-6B shipped 530 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while ChatGLM2-6B has 6B. Context windows are 128k (LLaMA 3.3) vs 32k (ChatGLM2-6B).

On HumanEval, LLaMA 3.3 leads at 88.4% vs ChatGLM2-6B at 9.8%. On MATH, LLaMA 3.3 leads at 77% vs ChatGLM2-6B at 6.9%. On MMLU, LLaMA 3.3 leads at 86% vs ChatGLM2-6B at 45.2%.