Learn · Compare

Compare two models.

Side by side

Swap

Qwen (Alibaba)

Qwen3-30B-A3B-Instruct

DeepSeek

DeepSeek-V3 (Mar 2025)

Release page →

The basics

Released

Jul 29, 2025

Mar 24, 2025

What it does

Knowledge cutoff

The latest events it learned about

Not published

Download

FreeOpen weights

FreeOpen weights, licence has limits

Where to use it

Qwen's app: Qwen Chat ↗

DeepSeek's app: DeepSeek ↗

Price and limits, for developers

Input

Per million tokens

$0.10Cheaper

$0.32

Output

Per million tokens

$0.30Cheaper

$0.89

Cached input

Per million tokens

$0.10

Not listed

Context window

How much it takes in at once

262K tokens about 200,000 wordsBigger

164K tokens about 120,000 words

Longest answer

Not listed

16K tokens about 12,000 words

How they score

Combined test score

Epoch Capabilities Index · Epoch AI

135#134 of 237

135#133 of 237

Too close to call: Qwen3-30B-A3B-Instruct and DeepSeek-V3 (Mar 2025) are within the margin of error.

Green marks the better of the two on each row, red the other. Rows where one side isn't listed, or where the gap is too close to call, stay plain.

Popular comparisons

Not sure where to start? Which AI should I use? gives a pick for what you want to do. How to read AI rankings explains the numbers.

Rankings from LMArena and Epoch AI, both CC BY 4.0, updated 28m ago. Developer prices, context windows and knowledge cutoffs from the labs' own listings on models.dev and from OpenRouter. The app links go to each maker's own app when no source says exactly where the model is available.