Compare AI models

Specifications
Parameters
8B/70B110B
Context window
8k32k
Benchmarks
HumanEval
81.7%52.4%
MATH
50.4%49.6%
MMLU
82%80.4%
GSM8K
93%85.4%
Overview
CompanyMetaQwen
Release dateApr 18 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3 (8B/70B) leads Qwen1.5-110B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). LLaMA 3 (8B/70B) shipped 7 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

LLaMA 3 (8B/70B) has 8B/70B parameters, while Qwen1.5-110B has 110B. Context windows are 8k (LLaMA 3 (8B/70B)) vs 32k (Qwen1.5-110B).

On HumanEval, LLaMA 3 (8B/70B) leads at 81.7% vs Qwen1.5-110B at 52.4%. On MATH, LLaMA 3 (8B/70B) leads at 50.4% vs Qwen1.5-110B at 49.6%. On MMLU, LLaMA 3 (8B/70B) leads at 82% vs Qwen1.5-110B at 80.4%. On GSM8K, LLaMA 3 (8B/70B) leads at 93% vs Qwen1.5-110B at 85.4%.