Compare AI models

Specifications
Parameters
70B110B
Context window
128k32k
API pricing
Cheapest input
$0.10DeepInfra—
Cheapest output
$0.32DeepInfra—
$36.00DeepInfra · turbo · fp8—
Benchmarks
HumanEval
88.4%52.4%
MATH
77%49.6%
MMLU
86%80.4%
Overview
CompanyMetaQwen
Release dateDec 6 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 3.3 leads Qwen1.5-110B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). Qwen1.5-110B shipped 225 days before LLaMA 3.3, so benchmark comparisons should account for the intervening progress.

LLaMA 3.3 has 70B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (LLaMA 3.3) vs 32k (Qwen1.5-110B).

On HumanEval, LLaMA 3.3 leads at 88.4% vs Qwen1.5-110B at 52.4%. On MATH, LLaMA 3.3 leads at 77% vs Qwen1.5-110B at 49.6%. On MMLU, LLaMA 3.3 leads at 86% vs Qwen1.5-110B at 80.4%.