Compare AI models

Specifications
Parameters
8B/70B—
Context window
8k1M
Benchmarks
HumanEval
81.7%86.6%
MATH
50.4%81.1%
GSM8K
93%93.8%
Overview
CompanyMetaQwen
Release dateApr 18 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Turbo (1M) leads LLaMA 3 (8B/70B) on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). LLaMA 3 (8B/70B) shipped 211 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 8k (LLaMA 3 (8B/70B)) vs 1M (Qwen2.5-Turbo (1M)). LLaMA 3 (8B/70B) is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Qwen2.5-Turbo (1M) leads at 86.6% vs LLaMA 3 (8B/70B) at 81.7%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs LLaMA 3 (8B/70B) at 50.4%. On GSM8K, Qwen2.5-Turbo (1M) leads at 93.8% vs LLaMA 3 (8B/70B) at 93%.