Models
DeepSeek
AI Model MATH Accuracy Over Time

DeepSeekX · Feb 6, 2024 · official

AI Model MATH Accuracy Over Time

DeepSeek's line chart drew 257.1K views on X: 0.8x its median post and #231 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

AI model MATH Top1 accuracy progression over time

XData Line chart DeepSeek-Coder All DeepSeek modelsGemini-UltraGPT-4 APIDeepSeekMath-7BGPT-4 early versionQwen-72BLlemma-34BMistral-7BQwen-14B

DeepSeek: AI Model MATH Accuracy Over Time — Published by DeepSeek on X, Feb 6, 2024. Source: x.com

73/ 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.

#156 of 1,162 AI chart posts we hold · #8 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, at #156 of 1,162 AI chart posts.

Its 0.25% save rate sits at the 95th percentile among AI chart posts, against a 0.076% median.

The post scores 73 and ranks #156 of 1,162 AI chart posts, #8 of 18 DeepSeek posts.

Line charts draw 3.5x the median views for the type: 257K against 73.7K.

top 5%save rate

0.254% of viewers bookmarked it to come back to. The median post gets 0.076%.

0.23views per follower

257.1K views from an account with 1.1M followers.

3.5xthe median line chart post

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

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 #156 of 1,162

Views	257.1K	#231	top 20%
Likes	1K	#272	top 23%
Engagement rate	0.49%	#849	bottom 27%
Save rate	0.254%	#61	top 5%

Among 18 DeepSeek posts

Score #8 of 18

Views	257.1K	#11	bottom 42%
Likes	1K	#9	top 47%
Engagement rate	0.49%	#6	top 31%
Save rate	0.254%	#1	top 3%

Growth

Our reads cover 23 hours

Views257.1K

Age at our read981 days

Views per day of life262views divided by days since it was posted

Gained between our reads+5views over 23 hours, about 5 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 · Feb 6, 2024

DeepSeek charts AI model MATH accuracy over time

A line chart of MATH Top1 accuracy drew 257K views and a 0.25% save rate, with engagement at 0.49%.

What happened

DeepSeek posted a line chart on February 6, 2024, tracking AI model MATH Top1 accuracy over time. It was the account's only post that day.

The numbers

It reached 257K views, ranking #231 of 1,162 AI chart posts, and scored 73, ranking #156 of 1,162 AI chart posts.

The lesson

A 0.25% save rate, at the 95th percentile among AI chart posts, shows readers bookmark a line chart of MATH Top1 accuracy even when the 0.49% engagement rate trails the 0.66% median for the type.

What it means

For DeepSeek, this ranks #8 of 18 DeepSeek posts by score while its 0.49% engagement rate sits below the 0.66% median for line charts, so the 257K views arrive with a thinner engagement rate than the type's median.

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

7 points read off this chart

Estimated from the image 45%

Group	Value	Read
LLaMA1-65B	10	printed
WizardMath-70B	22.25	estimated
Qwen-14B	25	printed
Mistral-7B	28	printed
Llemma-34B	30	printed
Qwen-72B	34.25	estimated
DeepSeekMath-7B	50.5	estimated

Max plan · API

GET https://viral-chart.com/api/posts/eba5bef2b574.json
GET https://viral-chart.com/api/charts/eba5bef2b574.json
GET https://viral-chart.com/api/charts/eba5bef2b574.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 eba5bef2b574.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.45 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/eba5bef2b574`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/eba5bef2b574/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/eba5bef2b574/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/eba5bef2b574/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-Coder

DeepSeek-Coder: AI Model Accuracy Comparison Across Benchmarks

OfficialX · DeepSeekJun 17, 2024

AI Model Accuracy Comparison Across Benchmarks489.6K views · 1.6K likes