Compare AI models

Specifications
Parameters
7B/67B7B/14B
Context window
4k1M
Benchmarks
HumanEval
73.8%88.4%
MATH
32.6%79.5%
GSM8K
84.1%94.8%
Overview
CompanyDeepSeekQwen
Release dateNov 29 2023Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-1M leads DeepSeek-LLM on 3 of the 3 benchmarks they both report (HumanEval, MATH, GSM8K). DeepSeek-LLM shipped 425 days before Qwen2.5-1M, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 4k (DeepSeek-LLM) vs 1M (Qwen2.5-1M).

On HumanEval, Qwen2.5-1M leads at 88.4% vs DeepSeek-LLM at 73.8%. On MATH, Qwen2.5-1M leads at 79.5% vs DeepSeek-LLM at 32.6%. On GSM8K, Qwen2.5-1M leads at 94.8% vs DeepSeek-LLM at 84.1%.