Models
DeepSeek
Throughput per User vs Output Throughput Pareto Frontiers

@SemiAnalysis_X · Apr 9, 2026

Throughput per User vs Output Throughput Pareto Frontiers

@SemiAnalysis_'s line chart drew 6.3K views on X: 0.2x @semianalysis_'s median post and #898 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Pareto frontiers comparing baseline and DWDP throughput performance

XData Line chart DeepSeek R1 All DeepSeek modelsBaselineDWDP

@SemiAnalysis_: Throughput per User vs Output Throughput Pareto Frontiers — Published by @SemiAnalysis_ on X, Apr 9, 2026. Source: x.com

11/ 100

ViralChart score

Quiet

Fewer views and a lower engagement rate than the median post.

#1,146 of 1,162 AI chart posts we hold · #23 of 24 @semianalysis_ 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 Quiet quadrant, at #1,146 of 1,162 AI chart posts.

Its 6.3K views sit at 0.16x @SemiAnalysis_'s median post, against a company median of 40.3K.

At #1,146 of 1,162 AI chart posts, the score of 11 lands in the bottom of the field.

A 0.000% save rate puts it at the 2nd percentile among AI chart posts, in the bottom decile.

0.2x@semianalysis_'s median post

6.3K views, where @semianalysis_'s typical post gets 40.3K.

0.1xthe median line chart post

Across 68 line chart posts we hold, the median gets 73.7K views.

bottom 2%save rate

0.000% of viewers bookmarked it to come back to. The median post gets 0.076%.

bottom 5%engagement rate

0.21% 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 24 from @semianalysis_.

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 #1,146 of 1,162

Views	6.3K	#898	bottom 23%
Likes	7	#1,140	bottom 2%
Engagement rate	0.21%	#1,109	bottom 5%
Save rate	0.000%	#1,122	bottom 2%

Among 24 @semianalysis_ posts

Score #23 of 24

Views	6.3K	#21	bottom 15%
Likes	7	#24	bottom 2%
Engagement rate	0.21%	#22	bottom 10%
Save rate	0.000%	#24	bottom 2%

Growth

One read so far

Views6.3K

Age at our read186 days

Views per day of life34views 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.

@semianalysis_'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 · Apr 9, 2026

@SemiAnalysis_ posts throughput Pareto frontiers line chart

A line chart on throughput per user versus output throughput Pareto frontiers drew 6.3K views and a 0.000% save rate.

What happened

@SemiAnalysis_ published a line chart on Throughput per User vs Output Throughput Pareto Frontiers on April 9, 2026. It was the account's only post that day.

The numbers

It reached 6.3K views, #898 of 1,162 AI chart posts, and ranked #21 of 24 @SemiAnalysis_ posts by views. Its score of 11 ranked #23 of 24 @SemiAnalysis_ posts.

The lesson

A 0.000% save rate at the 2nd percentile among AI chart posts: this line chart of 2 models gave readers nothing to keep. The median save rate among AI chart posts is 0.076%.

What it means

At #23 of 24 @SemiAnalysis_ posts, this chart sits below the account's own 40.3K median views. The 6.3K views against the 39.9K median among AI chart posts mark it as a below-median chart post.

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

Updates: what @semianalysis_ posted next

Data and API

30 points read off this chart

Estimated from the image 30%

Series	Group	Value	Read
		1720 tok/s/gpu	estimated
		1680 tok/s/gpu	estimated
		1600 tok/s/gpu	estimated
		1400 tok/s/gpu	estimated
		1350 tok/s/gpu	estimated
		1300 tok/s/gpu	estimated
		1200 tok/s/gpu	estimated
		250 tok/s/gpu	estimated
		1750 tok/s/gpu	estimated
		1700 tok/s/gpu	estimated
		1600 tok/s/gpu	estimated
		1450 tok/s/gpu	estimated

Showing 12 of 30. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/47fa4240916f.json
GET https://viral-chart.com/api/charts/bdc7ee018dfa.json
GET https://viral-chart.com/api/charts/bdc7ee018dfa.skill.md

Make one like this Open the post JSON Chart data JSON Skill file API 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 bdc7ee018dfa.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 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 plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/bdc7ee018dfa`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/bdc7ee018dfa/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/bdc7ee018dfa/render?view=1`	The draw-only view this page uses	Open
POST	`/mcp`	Tool get_chart_data with this id, for Claude, Cursor and other agents	Max

curlMax

curl -s https://viral-chart.com/api/v1/charts/bdc7ee018dfa/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 R1

DeepSeek R1: AI Model Performance Comparison Across Benchmarks

OfficialX · DeepSeekJan 20, 2025

AI Model Performance Comparison Across Benchmarks12.6M views · 35.1K likes