Compare AI models

Specifications
Parameters
70B7B
Context window
128k64k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%83.5%
Overview
CompanyMetaQwen
Release dateDec 6 2024Apr 16 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads CodeQwen1.5 on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 234 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while CodeQwen1.5 has 7B. Context windows are 128k (LLaMA 3.3) vs 64k (CodeQwen1.5).

On HumanEval, LLaMA 3.3 leads at 88.4% vs CodeQwen1.5 at 83.5%.