Compare AI models

Specifications
Parameters
7B/67B110B
Context window
4k32k
Benchmarks
HumanEval
73.8%52.4%
MATH
32.6%49.6%
MMLU
71.1%80.4%
GSM8K
84.1%85.4%
Overview
CompanyDeepSeekQwen
Release dateNov 29 2023Apr 25 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen1.5-110B leads DeepSeek-LLM on 3 of the 4 benchmarks they both report (HumanEval, MATH, MMLU, GSM8K). DeepSeek-LLM shipped 148 days before Qwen1.5-110B, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while Qwen1.5-110B has 110B. Context windows are 4k (DeepSeek-LLM) vs 32k (Qwen1.5-110B).

On HumanEval, DeepSeek-LLM leads at 73.8% vs Qwen1.5-110B at 52.4%. On MATH, Qwen1.5-110B leads at 49.6% vs DeepSeek-LLM at 32.6%. On MMLU, Qwen1.5-110B leads at 80.4% vs DeepSeek-LLM at 71.1%. On GSM8K, Qwen1.5-110B leads at 85.4% vs DeepSeek-LLM at 84.1%.