Compare AI models

Specifications
Parameters
8B/70B/405B110B
Context window
128k32k
API pricing
Cheapest input
$0.02DeepInfra—
Cheapest output
$0.04DeepInfra—
$6.00DeepInfra · fp8—
Benchmarks
HumanEval
89%52.4%
MATH
73.8%49.6%
MMLU
87.3%80.4%
GSM8K
96.8%85.4%
Overview
CompanyMetaQwen
Release dateJul 23 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.1 leads Qwen1.5-110B on 4 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen1.5-110B shipped 89 days before LLaMA 3.1, so benchmark comparisons should account for the intervening progress.

LLaMA 3.1 has 8B/70B/405B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (LLaMA 3.1) vs 32k (Qwen1.5-110B).

On HumanEval, LLaMA 3.1 leads at 89% vs Qwen1.5-110B at 52.4%. On MATH, LLaMA 3.1 leads at 73.8% vs Qwen1.5-110B at 49.6%. On MMLU, LLaMA 3.1 leads at 87.3% vs Qwen1.5-110B at 80.4%. On GSM8K, LLaMA 3.1 leads at 96.8% vs Qwen1.5-110B at 85.4%.