Compare AI models

Specifications
Parameters
16B/236B—
Context window
128k1M
Benchmarks
LiveCodeBench
43.4%37.8%
HumanEval
90.2%86.6%
MATH
75.7%81.1%
GSM8K
94.9%93.8%
Overview
CompanyDeepSeekQwen
Release dateJun 14 2024Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek Coder V2 leads Qwen2.5-Turbo (1M) on 3 of the 4 benchmarks they both report (LiveCodeBench, HumanEval, MATH, GSM8K). DeepSeek Coder V2 shipped 154 days before Qwen2.5-Turbo (1M), so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2) vs 1M (Qwen2.5-Turbo (1M)). DeepSeek Coder V2 is open weight, while Qwen2.5-Turbo (1M) is closed.

On LiveCodeBench, DeepSeek Coder V2 leads at 43.4% vs Qwen2.5-Turbo (1M) at 37.8%. On HumanEval, DeepSeek Coder V2 leads at 90.2% vs Qwen2.5-Turbo (1M) at 86.6%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs DeepSeek Coder V2 at 75.7%. On GSM8K, DeepSeek Coder V2 leads at 94.9% vs Qwen2.5-Turbo (1M) at 93.8%.