Compare AI models

Specifications
Parameters
236B110B
Context window
128k32k
Benchmarks
HumanEval
81.1%52.4%
MATH
53.9%49.6%
MMLU
77.8%80.4%
GSM8K
92.2%85.4%
Overview
CompanyDeepSeekQwen
Release dateMay 6 2024Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2 leads Qwen1.5-110B on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). Qwen1.5-110B shipped 11 days before DeepSeek V2, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 has 236B parameters, while Qwen1.5-110B has 110B. Context windows are 128k (DeepSeek V2) vs 32k (Qwen1.5-110B).

On HumanEval, DeepSeek V2 leads at 81.1% vs Qwen1.5-110B at 52.4%. On MATH, DeepSeek V2 leads at 53.9% vs Qwen1.5-110B at 49.6%. On MMLU, Qwen1.5-110B leads at 80.4% vs DeepSeek V2 at 77.8%. On GSM8K, DeepSeek V2 leads at 92.2% vs Qwen1.5-110B at 85.4%.