Models
DeepSeek
Token usage in AI evaluations

@ArtificialAnlysX · Sep 9, 2025

Token usage in AI evaluations

@ArtificialAnlys's bar chart drew 1.5K views on X: 0.1x @artificialanlys's median post and #1,106 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Token usage across AI models

XData Bar chart DeepSeek V3 All DeepSeek models Grok 4 Llama 4 Maverick Gemini 2.5 Pro GPT-4.1gpt-oss-120b (high)Nemotron Super 49B v1.5Qwen3-2357-A22BGLM-4.5

@ArtificialAnlys: Token usage in AI evaluations — Published by @ArtificialAnlys on X, Sep 9, 2025. Source: x.com

25/ 100

ViralChart score

Small but loved

Fewer views than the median post but a higher engagement rate: a smaller crowd that acted on it.

#1,004 of 1,162 AI chart posts we hold · #374 of 491 @artificialanlys 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 Small but loved quadrant, at #1,004 of 1,162 AI chart posts.

Its aperçu 1.5K views sit at 0.14x @ArtificialAnlys's median post, ranking #451 of 491 @ArtificialAnlys posts.

Engagement lands at 1.36%, the 89th percentile among AI chart posts and above the 0.73% median.

The score of 25 places it #1,004 of 1,162 AI chart posts and #374 of 491 @ArtificialAnlys posts.

0.1x@artificialanlys's median post

1.5K views, where @artificialanlys's typical post gets 11.4K.

0.1xthe median bar chart post

Across 241 bar chart posts we hold, the median gets 25.6K views.

top 11%engagement rate

1.36% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

bottom 42%save rate

0.065% of viewers bookmarked it to come back to. The median post gets 0.076%.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 491 from @artificialanlys.

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 #1,004 of 1,162

Views	1.5K	#1,106	bottom 5%
Likes	19	#1,034	bottom 11%
Engagement rate	1.36%	#129	top 11%
Save rate	0.065%	#669	bottom 42%

Among 491 @artificialanlys posts

Score #374 of 491

Views	1.5K	#451	bottom 8%
Likes	19	#395	bottom 20%
Engagement rate	1.36%	#62	top 13%
Save rate	0.065%	#279	bottom 43%

Growth

One read so far

Views1.5K

Age at our read398 days

Views per day of life4views divided by days since it was posted

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

@artificialanlys'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 9, 2025

@ArtificialAnlys bar chart on token usage in AI evaluations

A 21-model bar chart on token usage drew 1.5K views and a 1.36% engagement rate, the 89th percentile among AI chart posts.

What happened

On September 9, 2025, @ArtificialAnlys posted a bar chart on token usage across AI models. It was the account's only post that day.

The numbers

The post reached 1.5K views, #1,106 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 25 ranks #1,004 of 1,162 AI chart posts.

The lesson

At 1.36% engagement against a 0.73% median among AI chart posts, this bar chart shows that a 21-model comparison can hold attention even at 1.5K views.

What it means

At #374 of 491 @ArtificialAnlys posts by score and 0.14x the account's median views, this chart sits below the account's typical reach while its 1.36% engagement rate runs above the 0.82% median for this account.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what @artificialanlys posted next

Data and API

50 points read off this chart

Estimated from the image 53%

Series	Group	Value	Read
Answer Tokens	Grok 4	120 M	printed
Reasoning Tokens	Grok 4	120 M	printed
Answer Tokens	gpt-oss-120b (high)	110 M	printed
Reasoning Tokens	gpt-oss-120b (high)	110 M	printed
Answer Tokens	Llama 4 Maverick	100 M	printed
Reasoning Tokens	Llama 4 Maverick	110 M	estimated
Answer Tokens	SuperNova V3.2 120B	100 M	estimated
Reasoning Tokens	SuperNova V3.2 120B	110 M	estimated
Answer Tokens	Qwen3 2357-A22B	96 M	estimated
Reasoning Tokens	Qwen3 2357-A22B	110 M	estimated
Answer Tokens	GLM 4.5	96 M	printed
Reasoning Tokens	GLM 4.5	100 M	estimated

Showing 12 of 50. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/bf59a869f2ef.json
GET https://viral-chart.com/api/charts/bf59a869f2ef.json
GET https://viral-chart.com/api/charts/bf59a869f2ef.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 bf59a869f2ef.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/bf59a869f2ef`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/bf59a869f2ef/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/bf59a869f2ef/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/bf59a869f2ef/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: AI Model Performance Comparison

OfficialX · DeepSeekDec 1, 2025

AI Model Performance Comparison5.3M views · 15.9K likes