Models
DeepSeek
AI Model Benchmark Performance Comparison

DeepSeekX · Mar 25, 2025 · official

AI Model Benchmark Performance Comparison

DeepSeek's grouped bar chart drew 1.6M views on X: 4.6x its median post and #73 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Benchmark accuracy comparison of five AI models

XData Grouped bar chart DeepSeek R1 All DeepSeek models DeepSeek-V3DeepSeek-V3-0324Qwen-MaxGPT-4.5Claude-Sonnet-3.7

DeepSeek: AI Model Benchmark Performance Comparison — Published by DeepSeek on X, Mar 25, 2025. Source: x.com

86/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#5 of 1,162 AI chart posts we hold · #1 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 Reached and resonated quadrant at #5 of 1,162 AI chart posts.

Its score of 86 lands at #5 of 1,162 AI chart posts.

The post drew 1.6M views against DeepSeek's company median of 342K, a 4.6x ratio.

At 1.38 views per follower, it sits in the 82nd percentile among posts with known followers.

18xthe median grouped bar chart post

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

4.6xDeepSeek's median post

1.6M views, where DeepSeek's typical post gets 342K.

top 32%engagement rate

0.92% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

top 39%save rate

0.097% of viewers bookmarked it to come back to. The median post gets 0.076%.

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 #5 of 1,162

Views	1.6M	#73	top 6%
Likes	11.6K	#25	top 2%
Engagement rate	0.92%	#375	top 32%
Save rate	0.097%	#452	top 39%

Among 18 DeepSeek posts

Score #1 of 18

Views	1.6M	#4	top 19%
Likes	11.6K	#4	top 19%
Engagement rate	0.92%	#1	top 3%
Save rate	0.097%	#6	top 31%

Growth

Our reads cover 3 days

Views1.6M

Age at our read567 days

Views per day of life2.8Kviews divided by days since it was posted

Gained between our reads+98views over 3 days, about 35 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 · Mar 25, 2025 · Lead story

DeepSeek posts five-model benchmark comparison chart

A grouped bar chart of benchmark accuracy for five AI models drew 1.6M views and an 86 score.

What happened

DeepSeek published a grouped bar chart on March 25, 2025 comparing benchmark accuracy across five AI models. It was the account's only post that day.

The numbers

The post reached 1.6M views, ranking #73 of 1,162 AI chart posts and #4 of 18 DeepSeek posts. Its score of 86 ranks #5 of 1,162 AI chart posts and #1 of 18 DeepSeek posts.

The lesson

A grouped bar chart with 5 models and a 0.097% save rate shows that a multi-model comparison can travel: 1.6M views at 4.6x DeepSeek's median.

What it means

At #1 of 18 DeepSeek posts and 4.6x the company median of 342K views, this chart sets the account's own bar for benchmark comparisons.

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

25 points read off this chart

Partly publisher's numbers 92%

Series	Group	Value	Read
DeepSeek-V3	MMLU (EM-Pro)	75.9 %	printed
DeepSeek-V3-0324	MMLU (EM-Pro)	81.2 %	printed
Qwen-Max	MMLU (EM-Pro)	76.1 %	printed
GPT-4.5	MMLU (EM-Pro)	86.1 %	printed
Claude-Sonnet-3.7	MMLU (EM-Pro)	80.7 %	printed
DeepSeek-V3	GPQA (Pass@1)	59.1 %	printed
DeepSeek-V3-0324	GPQA (Pass@1)	68.4 %	printed
Qwen-Max	GPQA (Pass@1)	60.1 %	printed
GPT-4.5	GPQA (Pass@1)	71.4 %	printed
Claude-Sonnet-3.7	GPQA (Pass@1)	68 %	printed
DeepSeek-V3	MATH (Pass@500)	90.2 %	printed
DeepSeek-V3-0324	MATH (Pass@500)	94 %	printed

Showing 12 of 25. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/aa9690750284.json
GET https://viral-chart.com/api/charts/aa9690750284.json
GET https://viral-chart.com/api/charts/aa9690750284.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 aa9690750284.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/aa9690750284`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/aa9690750284/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/aa9690750284/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/aa9690750284/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