Compare AI models

Specifications
Parameters
70B9B
Context window
128k128k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%82.3%
Overview
CompanyMetaZ.ai
Release dateDec 6 2024Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX4-ALL-9B shipped 154 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 128k (LLaMA 3.3) vs 128k (CodeGeeX4-ALL-9B).

On HumanEval, LLaMA 3.3 leads at 88.4% vs CodeGeeX4-ALL-9B at 82.3%.