Models
DeepSeek
AI Model Benchmarks Comparison

DeepSeekX · Sep 10, 2026 · official

AI Model Benchmarks Comparison

DeepSeek's grouped bar chart drew 7M views on X: 21x its median post and #22 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Model performance across four benchmark suites

XData Grouped bar chart DeepSeek V4 All DeepSeek models Kimi-K3 GLM-5.3DeepSeek-V4.1-FlashOpus5GPT5.6-Sol

DeepSeek: AI Model Benchmarks Comparison — Published by DeepSeek on X, Sep 10, 2026. Source: x.com

80/ 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.

#44 of 1,162 AI chart posts we hold · #3 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

It sits in the Wide but thin quadrant, at #44 of 1,162 AI chart posts by score.

Its 7M views sit 21x above DeepSeek's median post of 342K, the #2 of 18 DeepSeek posts by views.

A score of 80 places it #44 of 1,162 AI chart posts and #3 of 18 DeepSeek posts.

At 6.17 views per follower against a median of 0.20, it lands in the 94th percentile and the top decile.

80xthe median grouped bar chart post

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

21xDeepSeek's median post

7M views, where DeepSeek's typical post gets 342K.

6.17views per follower

7M views from an account with 1.1M followers.

bottom 27%engagement rate

0.49% 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 #44 of 1,162

Views	7M	#22	top 2%
Likes	28.7K	#6	top 1%
Engagement rate	0.49%	#843	bottom 27%
Save rate	0.065%	#665	bottom 43%

Among 18 DeepSeek posts

Score #3 of 18

Views	7M	#2	top 8%
Likes	28.7K	#2	top 8%
Engagement rate	0.49%	#5	top 25%
Save rate	0.065%	#9	top 47%

Growth

Our reads cover 3 days

Views7M

Age at our read33 days

Views per day of life210.3Kviews divided by days since it was posted

Gained between our reads+24.2Kviews over 3 days, about 9.1K 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 · Sep 10, 2026

DeepSeek posts grouped bar chart of model benchmarks

The September 10, 2026 grouped bar chart reached 7M views and a 0.49% engagement rate, landing in the Wide but thin quadrant.

What happened

DeepSeek published a grouped bar chart on September 10, 2026, comparing model performance across four benchmark suites. It was the account's only post that day.

The numbers

It reached 7M views, #22 of 1,162 AI chart posts by views and #2 of 18 DeepSeek posts. Its score of 80 ranks #44 of 1,162 AI chart posts.

The lesson

The chart shows printed values from 17.7 to 74.2 across benchmark suites, and the post drew 7M views against a 39.9K median among AI chart posts. Its 0.49% engagement rate sits below that median, so the wide reach came with thin engagement.

What it means

At #3 of 18 DeepSeek posts by score and #2 of 18 by views, this chart post sits near the top of the account's own output. The 21x gap over DeepSeek's 342K median views shows the account's chart posts can travel far beyond its typical reach.

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

Data and API

20 points read off this chart

Estimated from the image 95%

Series	Group	Value	Read
DeepSeek-V4.1-Flash	Terminal-Bench 3.0	30 score	printed
Kimi-K3	Terminal-Bench 3.0	17.7 score	printed
GLM-3.5	Terminal-Bench 3.0	28.3 score	printed
Opus5	Terminal-Bench 3.0	43.3 score	printed
GPT5.6-Sol	Terminal-Bench 3.0	34.4 score	printed
DeepSeek-V4.1-Flash	DeepSWE v1.1	74.2 score	printed
Kimi-K3	DeepSWE v1.1	67.5 score	printed
GLM-3.5	DeepSWE v1.1	66.9 score	printed
Opus5	DeepSWE v1.1	74 score	printed
GPT5.6-Sol	DeepSWE v1.1	73 score	printed
DeepSeek-V4.1-Flash	CyberGym	88.1 score	printed
Kimi-K3	CyberGym	80 score	printed

Showing 12 of 20. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/ce0dbaebdfc0.json
GET https://viral-chart.com/api/charts/ce0dbaebdfc0.json
GET https://viral-chart.com/api/charts/ce0dbaebdfc0.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 ce0dbaebdfc0.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/ce0dbaebdfc0`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/ce0dbaebdfc0/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/ce0dbaebdfc0/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/ce0dbaebdfc0/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 V4

DeepSeek V4: AI Model Performance Comparison Across Benchmarks

OfficialX · DeepSeekApr 24, 2026

AI Model Performance Comparison Across Benchmarks623.9K views · 3.6K likes