Compare AI models

Specifications
Parameters
8B/70B1.5B/7B/72B
Context window
8k4k
Benchmarks
MATH
50.4%85.9%
GSM8K
93%95.9%
Overview
CompanyMetaQwen
Release dateApr 18 2024Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads LLaMA 3 (8B/70B) on 2 of the 2 benchmarks they both report (MATH, GSM8K). LLaMA 3 (8B/70B) shipped 154 days before Qwen2.5-Math, so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 4k (Qwen2.5-Math).

On MATH, Qwen2.5-Math leads at 85.9% vs LLaMA 3 (8B/70B) at 50.4%. On GSM8K, Qwen2.5-Math leads at 95.9% vs LLaMA 3 (8B/70B) at 93%.