Models
DeepSeek
AI Model Performance Comparison Across Benchmarks

DeepSeekX · Jan 20, 2025 · official

AI Model Performance Comparison Across Benchmarks

DeepSeek's grouped bar chart drew 12.6M views on X: 37x its median post and #8 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

DeepSeek-R1 leads across multiple benchmarks

XData Grouped bar chart DeepSeek R1 All DeepSeek models DeepSeek-R1 DeepSeek-V3OpenAI-o1-1217DeepSeek-R1-32BOpenAI-o1-mini

DeepSeek: AI Model Performance Comparison Across Benchmarks — Published by DeepSeek on X, Jan 20, 2025. Source: x.com

79/ 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.

#58 of 1,162 AI chart posts we hold · #4 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

The post sits in the Wide but thin quadrant, with a score rank of #58 of 1,162 AI chart posts.

At 12.6M views, this post runs 37x DeepSeek's median of 342K and ranks #1 of 18 DeepSeek posts by views.

Its 11 views per follower sit at the 97th percentile among posts with known followers, against a median of 0.20.

A score of 79 places it at #58 of 1,162 AI chart posts and #4 of 18 DeepSeek posts.

37xDeepSeek's median post

12.6M views, where DeepSeek's typical post gets 342K.

144xthe median grouped bar chart post

Across 108 grouped bar chart posts we hold, the median gets 87.5K views.

11views per follower

12.6M views from an account with 1.1M followers.

bottom 15%engagement rate

0.37% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

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 #58 of 1,162

Views	12.6M	#8	top 1%
Likes	35.1K	#5	top 1%
Engagement rate	0.37%	#985	bottom 15%
Save rate	0.077%	#578	top 50%

Among 18 DeepSeek posts

Score #4 of 18

Views	12.6M	#1	top 3%
Likes	35.1K	#1	top 3%
Engagement rate	0.37%	#12	bottom 36%
Save rate	0.077%	#8	top 42%

Growth

Our reads cover 3 days

Views12.6M

Age at our read631 days

Views per day of life19.9Kviews divided by days since it was posted

Gained between our reads+382views over 3 days, about 135 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 · Jan 20, 2025 · Lead story

DeepSeek posts grouped bar chart of benchmark accuracy

A grouped bar chart of benchmark accuracy drew 12.6M views and a 0.37% engagement rate, landing in the Wide but thin quadrant.

What happened

DeepSeek, an official account, posted a grouped bar chart on January 20, 2025. That day the account posted 合法性2 posts, including one on input/output pricing for o1-class inference models at 1.3M views.

The numbers

The post reached 12.6M views, ranking #8 of 1,162 AI chart posts by views and #1 of 18 DeepSeek posts. Its score of 79 ranks #58 of 1,162 AI chart posts.

The lesson

A grouped bar chart with 5 models shown drew 12.6M views but a 0.37% engagement rate and a 0.077% save rate. The chart shows DeepSeek-R1 at 79.8% on AIME (Pass@1) and 96.3% on Codeforces (Percentile).

What it means

At #4 of 18 DeepSeek posts by score, this chart trails the account's top posts despite 12.6M views. The 0.37% engagement rate sits below the AI chart median, so the reach gap to the 39.9K median views is not matched by engagement.

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

30 points read off this chart

Partly publisher's numbers 99%

Series	Group	Value	Read
DeepSeek-R1	AIME (Pass@1)	79.8 %	printed
OpenAI-o1-1217	AIME (Pass@1)	79.2 %	printed
DeepSeek-R1-32B	AIME (Pass@1)	72.6 %	printed
OpenAI-o1-mini	AIME (Pass@1)	63.6 %	printed
DeepSeek-V3	AIME (Pass@1)	39.2 %	printed
DeepSeek-R1	Codeforces (Percentile)	96.3 %	printed
OpenAI-o1-1217	Codeforces (Percentile)	96.6 %	printed
DeepSeek-R1-32B	Codeforces (Percentile)	90.6 %	printed
OpenAI-o1-mini	Codeforces (Percentile)	93.4 %	printed
DeepSeek-V3	Codeforces (Percentile)	58.7 %	printed
DeepSeek-R1	GPQA Diamond (Pass@1)	71.5 %	printed
OpenAI-o1-1217	GPQA Diamond (Pass@1)	75.7 %	printed

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

Max plan · API

GET https://viral-chart.com/api/posts/f7542d88b140.json
GET https://viral-chart.com/api/charts/f7542d88b140.json
GET https://viral-chart.com/api/charts/f7542d88b140.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 f7542d88b140.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/f7542d88b140`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/f7542d88b140/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/f7542d88b140/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/f7542d88b140/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 Benchmark Performance Comparison

OfficialX · DeepSeekMar 25, 2025

AI Model Benchmark Performance Comparison1.6M views · 11.6K likes