Compare AI models

Specifications
Parameters
8B/70B14B
Context window
8k2k
Benchmarks
HumanEval
81.7%32.3%
MATH
50.4%24.8%
MMLU
82%66.3%
GSM8K
93%61.3%
Overview
CompanyMetaQwen
Release dateApr 18 2024Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3 (8B/70B) leads Qwen-14B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen-14B shipped 206 days before LLaMA 3 (8B/70B), so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while Qwen-14B has 14B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 2k (Qwen-14B).

On HumanEval, LLaMA 3 (8B/70B) leads at 81.7% vs Qwen-14B at 32.3%. On MATH, LLaMA 3 (8B/70B) leads at 50.4% vs Qwen-14B at 24.8%. On MMLU, LLaMA 3 (8B/70B) leads at 82% vs Qwen-14B at 66.3%. On GSM8K, LLaMA 3 (8B/70B) leads at 93% vs Qwen-14B at 61.3%.