1. Models
  2. DeepSeek
  3. Artificial Analysis Intelligence vs Output Tokens
A
@ArtificialAnlysX · Aug 21, 2025

Artificial Analysis Intelligence vs Output Tokens

@ArtificialAnlys's scatter plot drew 73.6K views on X: 6.4x @artificialanlys's median post and #447 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

DeepSeek models show intelligence gains with increased output tokens

XDataScatter plotAll DeepSeek modelsDeepSeek V3 0324 (Mar '25)DeepSeek V3.1 (Non-reasoning)DeepSeek V3.1 (Reasoning)DeepSeek R1 0528
Published by @ArtificialAnlys on X, Aug 21, 2025. Source: x.com
72/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#191 of 1,162 AI chart posts we hold · #47 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 Reached and resonated quadrant, at #191 of 1,162 AI chart posts.

Its 73.6K views are 6.4x @ArtificialAnlys's median post, ranking #110 of 491 @ArtificialAnlys posts.

The 0.18% save rate sits at the 87th percentile among AI chart posts, against a 0.076% median.

A score of 72 places it #191 of 1,162 AI chart posts and #47 of 491 @ArtificialAnlys posts.

6.4x@artificialanlys's median post

73.6K views, where @artificialanlys's typical post gets 11.4K.

2charts in this one post

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

top 13%save rate

0.177% of viewers bookmarked it to come back to. The median post gets 0.076%.

top 14%engagement rate

1.25% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

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 #191 of 1,162

Views73.6K#447top 38%
Likes768#318top 27%
Engagement rate1.25%#165top 14%
Save rate0.177%#154top 13%

Among 491 @artificialanlys posts

Score #47 of 491

Views73.6K#110top 22%
Likes768#77top 16%
Engagement rate1.25%#85top 17%
Save rate0.177%#78top 16%

Growth

One read so far

Views73.6K
Age at our read418 days
Views per day of life176views 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 · Aug 21, 2025

@ArtificialAnlys maps DeepSeek intelligence against output tokens

A scatter plot of DeepSeek models drew 73.6K views and a 0.18% save rate, above the AI chart median.

What happened

@ArtificialAnlys posted a scatter plot on August 21, 2025, on Artificial Analysis Intelligence vs Output Tokens. It came with 2 charts in the post, including Artificial Analysis Intelligence Index v2.2, and 1 post from this account that day.

The numbers

It reached 73.6K views, #447 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 72 ranks #191 of 1,162 AI chart posts.

The lesson

A 0.18% save rate, at the 87th percentile among AI chart posts, came with a scatter plot of 4 models. The chart shows DeepSeek V3 0324 (Mar '25) at 44 and DeepSeek R1 0528 at 62 on the Artificial Analysis Intelligence Index.

What it means

At 6.4x @ArtificialAnlys's median views, this post ranks #110 of 491 @ArtificialAnlys posts, while its score rank is #47 of 491. The gap between #110 by views and #47 by score shows the account's chart posts travel further than their engagement score alone.

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

Updates: what @artificialanlys posted next

  1. Terminal-Bench Hard Benchmark Leaderboard4K views
  2. r²-Bench Telecom Benchmark Leaderboard8.2K views
  3. Token usage in AI evaluations1.5K views
  4. Big Bench Audio Intelligence16.7K views
  5. Artificial Analysis Intelligence Index v3.0732.4K views
  6. Output Tokens Used to Run All Evaluations in13.2K views

Data and API

4 points read off this chart

Estimated from the image 43%
SeriesGroupValueRead
DeepSeek V3 0324 (Mar '25)44printed
DeepSeek V3.1 (Non-reasoning)48estimated
DeepSeek R1 052862printed
DeepSeek V3.1 (Reasoning)52estimated

Max plan · API

GET https://viral-chart.com/api/posts/4c278e54715b.json
GET https://viral-chart.com/api/charts/9ead84dcf229.json
GET https://viral-chart.com/api/charts/9ead84dcf229.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI docs

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 9ead84dcf229.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.43 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/9ead84dcf229Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/9ead84dcf229/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/9ead84dcf229/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/9ead84dcf229/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

DeepSeek V3.1: Artificial Analysis Intelligence Index v2.2
X · @ArtificialAnlysAug 21, 2025
Artificial Analysis Intelligence Index v2.273.6K views · 768 likes
Data
DeepSeek V3.1: Intelligence vs. Output Tokens
X · @ArtificialAnlysOct 13, 2025
Intelligence vs. Output Tokens21K views · 190 likes
Data
DeepSeek V3.1: Output Token Speed by Provider
X · @ArtificialAnlysOct 13, 2025
Output Token Speed by Provider21K views · 190 likes
Data

More from DeepSeek

DeepSeek table chart: LLM benchmark comparison3.4x
DeepSeek·Dec 2024
LLM benchmark comparison
7.4M views12.9K likes0.2% eng.
Data
DeepSeek table chart: DeepSeek-V4 API pricing0.5x
DeepSeek·Aug 2026
DeepSeek-V4 API pricing
625.6K views1.8K likes0.4% eng.
Data
DeepSeek annotated chart: Benchmark Performance Radar0.1x
DeepSeek·Nov 2024
Benchmark Performance Radar
151.7K views500 likes0.4% eng.
Data
DeepSeek R1: AI Model Performance Comparison Across Benchmarks
OfficialX · DeepSeekJan 20, 2025
AI Model Performance Comparison Across Benchmarks12.6M views · 35.1K likes
Data
DeepSeek V4: AI Model Benchmarks Comparison
OfficialX · DeepSeekSep 10, 2026
AI Model Benchmarks Comparison7M views · 28.7K likes
Data
DeepSeek V3: AI Model Performance Comparison
OfficialX · DeepSeekDec 1, 2025
AI Model Performance Comparison5.3M views · 15.9K likes
Data
DeepSeek R1: AI Model Benchmark Performance Comparison
OfficialX · DeepSeekMar 25, 2025
AI Model Benchmark Performance Comparison1.6M views · 11.6K likes
Data
DeepSeek R1: AI Model Accuracy Comparison Across Benchmarks
OfficialX · DeepSeekMay 29, 2025
AI Model Accuracy Comparison Across Benchmarks1.5M views · 9.6K likes
Data
DeepSeek R1: Input/Output Pricing for o1-Class Inference Models
OfficialX · DeepSeekJan 20, 2025
Input/Output Pricing for o1-Class Inference Models1.3M views · 3.4K likes
Data

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on Aug 21, 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.