Models
DeepSeek
deepseek-r1-lite-preview AIME accuracy with test-time comput

DeepSeekX · Nov 20, 2024 · official

deepseek-r1-lite-preview AIME accuracy with test-time compute scaling

DeepSeek's line chart drew 374.3K views on X: 1.1x its median post and #179 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

AIME accuracy scaling with thought tokens

XData Line chart DeepSeek R1 All DeepSeek modelso1-previewr1-lite-preview (Majority Voting)r1-lite-preview (Pass@1)

DeepSeek: deepseek-r1-lite-preview AIME accuracy with test-time compute scaling — Published by DeepSeek on X, Nov 20, 2024. Source: x.com

59/ 100

ViralChart score

Wide but thin

More views than the median post but a lower engagement rate: many saw it, few acted. Common for big accounts.

#462 of 1,162 AI chart posts we hold · #13 of 18 DeepSeek 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

Wide but thin: 374K views but a 0.24% engagement rate, scoring #462 of 1,162 AI chart posts.

Its 0.24% engagement rate sits at the 6th percentile among AI chart posts, in the bottom decile.

The post ranked #1 of 2 DeepSeek posts by views that day.

Line charts draw a 73.7K median among 68 chart posts of this type, and this one reached 374K.

bottom 6%engagement rate

0.24% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

5.1xthe median line chart post

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

bottom 19%save rate

0.038% of viewers bookmarked it to come back to. The median post gets 0.076%.

0.33views per follower

374.3K views from an account with 1.1M followers.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 18 from DeepSeek.

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 #462 of 1,162

Views	374.3K	#179	top 15%
Likes	733	#332	top 29%
Engagement rate	0.24%	#1,094	bottom 6%
Save rate	0.038%	#936	bottom 19%

Among 18 DeepSeek posts

Score #13 of 18

Views	374.3K	#9	top 47%
Likes	733	#11	bottom 42%
Engagement rate	0.24%	#17	bottom 8%
Save rate	0.038%	#16	bottom 14%

Growth

Our reads cover 27 hours

Views374.3K

Age at our read692 days

Views per day of life541views divided by days since it was posted

Gained between our reads+3views over 27 hours, about 3 a day now

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

DeepSeek'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 · Nov 20, 2024

DeepSeek's R1-Lite-Preview AIME Scaling Chart Reaches 374K Views

The line chart plots AIME accuracy against thought tokens, but its 0.24% engagement rate lands in the bottom decile.

What happened

DeepSeek posted a line chart on November 20, 2024, showing AIME accuracy scaling with thought tokens for r1-lite-preview. It was one of 2 DeepSeek posts that day, alongside a benchmarks post at 310K views.

The numbers

It reached 374K views, ranking #179 of 1,162 AI chart posts, against a 39.9K median. Its score of 59 ranks #462 of 1,162 AI chart posts and #13 of 18 DeepSeek posts.

The lesson

A line chart reached 374K views against a 73.7K median for the 68 chart posts of this type, a 5.1x ratio. Its 0.24% engagement rate against a 0.66% median for this type shows the reach did not carry into interaction.

What it means

At #13 of 18 DeepSeek posts by score, this chart sits below the account's own median engagement of 0.41%. The 374K views against a 39.9K median show reach can outrun engagement for this publisher's chart posts.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what DeepSeek posted next

Data and API

17 points read off this chart

Estimated from the image 86%

Series	Value	Read
o1-preview	44.2 %	printed
r1-lite-preview (Majority Voting)	21 %	printed
r1-lite-preview (Majority Voting)	22.7 %	printed
r1-lite-preview (Majority Voting)	28 %	printed
r1-lite-preview (Majority Voting)	29.45 %	printed
r1-lite-preview (Majority Voting)	32 %	printed
r1-lite-preview (Majority Voting)	34 %	printed
r1-lite-preview (Majority Voting)	35.3 %	printed
r1-lite-preview (Majority Voting)	48.7 %	printed
r1-lite-preview (Majority Voting)	52 %	printed
r1-lite-preview (Majority Voting)	59.3 %	printed
r1-lite-preview (Majority Voting)	60 %	printed

Showing 12 of 17. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/23b41f0c6bff.json
GET https://viral-chart.com/api/charts/23b41f0c6bff.json
GET https://viral-chart.com/api/charts/23b41f0c6bff.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 23b41f0c6bff.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/23b41f0c6bff`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/23b41f0c6bff/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/23b41f0c6bff/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/23b41f0c6bff/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