1. Models
  2. DeepSeek
  3. Intelligence vs. Output Tokens
A
@ArtificialAnlysX · Oct 13, 2025

Intelligence vs. Output Tokens

@ArtificialAnlys's scatter plot drew 21K views on X: 1.8x @artificialanlys's median post and #708 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Intelligence vs. Output Tokens for DeepSeek Models

XDataScatter plotAll DeepSeek modelsDeepSeek V3.2DeepSeek V3.1 TerminusDeepSeek V3.2 ExpDeepSeek V3.1 0528DeepSeek V3.1 R1 TerminusDeepSeek V3.2 0324
Published by @ArtificialAnlys on X, Oct 13, 2025. Source: x.com
53/ 100

ViralChart score

Small but loved

Fewer views than the median post but a higher engagement rate: a smaller crowd that acted on it.

#584 of 1,162 AI chart posts we hold · #180 of 491 @artificialanlys posts. Score = views 40%, likes 30%, engagement rate 15%, save rate 15%, each as a percentile of every AI chart post we hold.

Our read

The post sits in the Small but loved quadrant, at #584 of 1,162 AI chart posts.

Its 0.18% save rate sits at the 88th percentile among AI chart posts, against a 0.076% median.

The post carries 3 charts, and every chart in the post shares the post's numbers.

It ranked #2 of 2 posts from this account that day by views.

3charts in this one post

The numbers belong to the post, so every chart in it shares them and it is ranked once.

top 12%save rate

0.181% of viewers bookmarked it to come back to. The median post gets 0.076%.

top 24%engagement rate

1.06% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

2posts from @artificialanlys that day

Part of a run of 2 posts on Oct 13, 2025. This one was #2 of 2 by views that day.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 491 from @artificialanlys.

Where it sits

Reach against resonance

Each dot is a post. Right is more views, up is a higher engagement rate. The lines are the medians, so the four corners are the four kinds of post.

Among 1,162 AI chart posts we hold

Score #584 of 1,162

Views21K#708bottom 39%
Likes190#660bottom 43%
Engagement rate1.06%#282top 24%
Save rate0.181%#145top 12%

Among 491 @artificialanlys posts

Score #180 of 491

Views21K#207top 42%
Likes190#193top 39%
Engagement rate1.06%#151top 31%
Save rate0.181%#72top 15%

Growth

One read so far

Views21K
Age at our read364 days
Views per day of life58views divided by days since it was posted

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

@artificialanlys's posts over time

Every post from this account we hold, by date and views. This one is marked; the line is the running median of the last 10.

News · Oct 13, 2025

@ArtificialAnlys charts DeepSeek intelligence against output tokens

A scatter plot of DeepSeek models drew 21K views and a 0.18% save rate, above the 0.076% median among AI chart posts.

What happened

On October 13, 2025, @ArtificialAnlys posted a scatter plot of Intelligence vs. Output Tokens for DeepSeek Models, with 3 charts in the post. The account posted 2 posts that day, including one on Speech Reasoning (Big Bench Audio) at 149K views.

The numbers

The post reached 21K views, ranking #708 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 53 ranks #584 of 1,162 AI chart posts and #180 of 491 @ArtificialAnlys posts.

The lesson

A 0.18% save rate, at the 88th percentile among AI chart posts, shows readers kept this scatter plot at more than the 0.076% median rate. The 3 charts in the post share its numbers, so the save rate covers the whole set.

What it means

At #180 of 491 @ArtificialAnlys posts, this chart sits below the account's own top ranks while its save rate beats the AI chart median. The 21K views against the 39.9K median among AI chart posts mark it as wide but thin on reach.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Data and API

8 points read off this chart

Partly publisher's numbers 86%
SeriesGroupValueRead
DeepSeek V3.2 Exp45estimated
DeepSeek V3.184.8estimated
DeepSeek V3.1 Terminus84.8estimated
DeepSeek V3 032441estimated
DeepSeek V3.1 Terminus84.8estimated
DeepSeek V3.1 R1 052884.8estimated
DeepSeek V3.1 Exp84.8estimated
DeepSeek V3.257estimated

Max plan · API

GET https://viral-chart.com/api/posts/41e0b63206f7.json
GET https://viral-chart.com/api/charts/41e0b63206f7.json
GET https://viral-chart.com/api/charts/41e0b63206f7.skill.md

Static files in this prototype. The post JSON holds the public numbers, ranks, score, quadrant, our reads and, when checked, our copy.

API · Max

Use this chart via API

On the Max plan you can pull this chart's numbers with the provenance of each one, as JSON or CSV, with its redraw spec, or call it from an agent over MCP. Chart id 41e0b63206f7.

PathReturnsPlan
GET/api/v1/charts/41e0b63206f7Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/41e0b63206f7/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/41e0b63206f7/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/41e0b63206f7/data \
  -H "Authorization: Bearer $VIRALCHART_KEY"
Claude CodeMax
claude mcp add --transport http viralchart https://viral-chart.com/mcp \
  --header "Authorization: Bearer $VIRALCHART_KEY"

60 requests a minute per key; over that you get 429 with Retry-After. Up to 5 keys per account, made on your account page and shown once. Without Max, the data route answers 402 with a link to the plans. The numbers describe a chart its publisher owns, and every file carries a license note.

More charts about DeepSeek V3.1

More from DeepSeek

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on Oct 13, 2025 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.