Compare AI models

Specifications
Parameters
70B14B
Context window
128k2k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%32.3%
MATH
77%24.8%
MMLU
86%66.3%
Overview
CompanyMetaQwen
Release dateDec 6 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads Qwen-14B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Qwen-14B shipped 438 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while Qwen-14B has 14B. Context windows are 128k (LLaMA 3.3) vs 2k (Qwen-14B).

On HumanEval, LLaMA 3.3 leads at 88.4% vs Qwen-14B at 32.3%. On MATH, LLaMA 3.3 leads at 77% vs Qwen-14B at 24.8%. On MMLU, LLaMA 3.3 leads at 86% vs Qwen-14B at 66.3%.