Models
DeepSeek
AI Model Performance Comparison

DeepSeekX · Dec 1, 2025 · official

AI Model Performance Comparison

DeepSeek's grouped bar chart drew 5.3M views on X: 16x its median post and #31 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Performance comparison of AI models across reasoning and agentic tasks

XData Grouped bar chart DeepSeek V3 All DeepSeek modelsDeepSeek-V3.2-SpecialeDeepSeek-V3.2ThinkingGPT-5-HighClaude-4.5-SonnetGemini-3.0-Pro

DeepSeek: AI Model Performance Comparison — Published by DeepSeek on X, Dec 1, 2025. Source: x.com

77/ 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.

#92 of 1,162 AI chart posts we hold · #5 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 #92 of 1,162 AI chart posts.

Its 5.3M views sit 16x above DeepSeek's median post at 342K, ranking #3 of 18 DeepSeek posts.

At 4.67 views per follower against a 0.20 median, it lands in the 93rd percentile, a top decile band.

A score of 77 places it at #92 of 1,162 AI chart posts and #5 of 18 DeepSeek posts.

61xthe median grouped bar chart post

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

16xDeepSeek's median post

5.3M views, where DeepSeek's typical post gets 342K.

4.67views per follower

5.3M views from an account with 1.1M followers.

bottom 17%engagement rate

0.39% 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 #92 of 1,162

Views	5.3M	#31	top 3%
Likes	15.9K	#18	top 2%
Engagement rate	0.39%	#970	bottom 17%
Save rate	0.059%	#732	bottom 37%

Among 18 DeepSeek posts

Score #5 of 18

Views	5.3M	#3	top 14%
Likes	15.9K	#3	top 14%
Engagement rate	0.39%	#11	bottom 42%
Save rate	0.059%	#10	bottom 47%

Growth

Our reads cover 3 days

Views5.3M

Age at our read316 days

Views per day of life16.9Kviews divided by days since it was posted

Gained between our reads+236views over 3 days, about 88 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 · Dec 1, 2025 · Lead story

DeepSeek posts grouped bar chart of AI model performance

The December 1, 2025 grouped bar chart drew 5.3M views and 15.9K likes, with a 0.39% engagement rate.

What happened

DeepSeek published a grouped bar chart on December 1, 2025 comparing AI model performance across reasoning and agentic tasks. It was the account's only post that day.

The numbers

The post reached 5.3M views, ranking #31 of 1,162 AI chart posts by views and #3 of 18 DeepSeek posts. Its score of 77 ranks #92 of 1,162 AI chart posts.

The lesson

A grouped bar chart with 5 models shown drew 5.3M views, 16x DeepSeek's median of 342K. The 0.39% engagement rate against a 0.059% save rate marks wide but thin reach.

What it means

At #5 of 18 DeepSeek posts by score, this chart sits below the account's top posts despite 5.3M views. The 0.39% engagement rate against the 39.9K median views among AI chart posts shows reach without matching 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

44 points read off this chart

Estimated from the image 52%

Series	Group	Value	Read
DeepSeek-V3.2-Speciale	AIME 2025 (Pass@1)	96 % / Rating	printed
DeepSeek-V3.2-Thinking	AIME 2025 (Pass@1)	93.1 % / Rating	printed
GPT-5-High	AIME 2025 (Pass@1)	94.6 % / Rating	printed
Claude-4.5-Sonnet	AIME 2025 (Pass@1)	95 % / Rating	printed
DeepSeek-V3.2-Speciale	HMMT 2025 (Pass@1)	99.2 % / Rating	printed
DeepSeek-V3.2-Thinking	HMMT 2025 (Pass@1)	89.25 % / Rating	printed
GPT-5-High	HMMT 2025 (Pass@1)	88.3 % / Rating	printed
Claude-4.5-Sonnet	HMMT 2025 (Pass@1)	79.2 % / Rating	printed
DeepSeek-V3.2-Speciale	HLE (Pass@1)	28.45 % / Rating	printed
DeepSeek-V3.2-Thinking	HLE (Pass@1)	19.4 % / Rating	printed
GPT-5-High	HLE (Pass@1)	32 % / Rating	printed
Claude-4.5-Sonnet	HLE (Pass@1)	13.7 % / Rating	printed

Showing 12 of 44. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/ea5cf0aba918.json
GET https://viral-chart.com/api/charts/ea5cf0aba918.json
GET https://viral-chart.com/api/charts/ea5cf0aba918.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 ea5cf0aba918.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/ea5cf0aba918`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/ea5cf0aba918/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/ea5cf0aba918/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/ea5cf0aba918/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

DeepSeek V3: Inference costs of DeepSeek-V3.1-Terminus and DeepSeek-V3.2-Exp

OfficialX · DeepSeekSep 29, 2025

Inference costs of DeepSeek-V3.1-Terminus and DeepSeek-V3.2-Exp194.6K views · 679 likes