Skip to content
trckr.ai

Loading…

Learn · Compare

Compare two models.

Side by side

Swap

DeepSeek V4 Flash 0731

DeepSeek's updated free-to-download model that is better at completing agent-style tasks and coding, free for anyone to use under the MIT license.

Release page →

Kimi K3

Moonshot AI's Kimi K3 is a very large model that can read text, images and video, free to download for research and non-commercial use and aimed at long coding and knowledge-work tasks.

Release page →

The basics

Released

Jul 31
Jul 16

What it does

Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.Sees images: Understands pictures, screenshots and charts you share with it.
Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.Sees images: Understands pictures, screenshots and charts you share with it.Watches video: Understands video clips you share with it.

Knowledge cutoff

The latest events it learned about

May 2025
Not published

Download

FreeOpen weights
FreeOpen weights, non-commercial licence

Where to use it

DeepSeek's app: DeepSeek ↗
Moonshot AI's app: Kimi ↗

Price and limits, for developers

Input

Per million tokens

$0.15Cheaper
$3.00

Output

Per million tokens

$0.60Cheaper
$15.00

Cached input

Per million tokens

$0.003Cheaper
$0.30

Context window

How much it takes in at once

1.05M tokens about 790,000 words
1.05M tokens about 790,000 words

Longest answer

393K tokens about 290,000 words
Not listed

How they score

Combined test score

Epoch Capabilities Index · Epoch AI

154#49 of 237
159#23 of 237Higher

Kimi K3 scores 4 points higher.

Chat answers, by people's votes

LMArena text, adjusted for style · LMArena

1,439#85 of 86
1,487#16 of 86Higher

In blind votes, people pick Kimi K3 over DeepSeek V4 Flash 0731 about 57% of the time.

Building apps, by people's votes

LMArena WebDev · LMArena

1,582#36 of 85
1,657#15 of 85Higher

In blind votes, people pick Kimi K3 over DeepSeek V4 Flash 0731 about 61% of the time.

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 . 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.

Free alerts

Know the moment a new model drops.

Pick one or several. Each has its own settings for what you hear about.