Compare AI models

Specifications
Parameters
1B/3B/11B/90B110B
Context window
128k32k
API pricing
Cheapest input
$0.027Cloudflare—
Cheapest output
$0.201Cloudflare—
$15.45Cloudflare—
Benchmarks
MATH
68%49.6%
MMLU
86%80.4%
Overview
CompanyMetaQwen
Release dateSep 25 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.2 leads Qwen1.5-110B on 2 of the 2 benchmarks they both report (MATH, MMLU). Qwen1.5-110B shipped 153 days before LLaMA 3.2, so benchmark comparisons should account for the intervening progress.

LLaMA 3.2 has 1B/3B/11B/90B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (LLaMA 3.2) vs 32k (Qwen1.5-110B).

On MATH, LLaMA 3.2 leads at 68% vs Qwen1.5-110B at 49.6%. On MMLU, LLaMA 3.2 leads at 86% vs Qwen1.5-110B at 80.4%.