Models
Anthropic
Token Usage per Task

@ArtificialAnlysX · Sep 24, 2026

Token Usage per Task

@ArtificialAnlys's bar chart drew 7.3K views on X: 0.6x @artificialanlys's median post and #869 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Token usage per task across AI models

XData Bar chart Claude Opus 5 All Anthropic models DeepSeek V4 Muse Spark Codex Claude CodeClaude 5.5Grok 4.7Opencode 5.5Gemini 3.8

@ArtificialAnlys: Token Usage per Task — Published by @ArtificialAnlys on X, Sep 24, 2026. Source: x.com

22/ 100

ViralChart score

Quiet

Fewer views and a lower engagement rate than the median post.

#1,039 of 1,162 AI chart posts we hold · #400 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

The post sits in the Quiet quadrant, with a score rank of #1,039 of 1,162 AI chart posts.

Its score of 22 sits at #1,039 of 1,162 AI chart posts, below the median.

The post landed at #5 of 6 by views among the account's 6 posts that day.

A save rate of 0.041% puts it at the 22nd percentile among AI chart posts, against a 0.076% median.

6posts from @artificialanlys that day

Part of a run of 6 posts on Sep 24, 2026. This one was #5 of 6 by views that day.

0.3xthe median bar chart post

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

bottom 22%save rate

0.041% of viewers bookmarked it to come back to. The median post gets 0.076%.

bottom 23%engagement rate

0.45% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

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 #1,039 of 1,162

Views	7.3K	#869	bottom 25%
Likes	30	#954	bottom 18%
Engagement rate	0.45%	#896	bottom 23%
Save rate	0.041%	#909	bottom 22%

Among 491 @artificialanlys posts

Score #400 of 491

Views	7.3K	#293	bottom 40%
Likes	30	#341	bottom 30%
Engagement rate	0.45%	#404	bottom 18%
Save rate	0.041%	#372	bottom 24%

Growth

One read so far

Views7.3K

Age at our read19 days

Views per day of life389views 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 24, 2026

@ArtificialAnlys posts token usage per task bar chart

A bar chart of token usage per task across 10 models drew 7.3K views and a 0.45% engagement rate.

What happened

@ArtificialAnlys posted a bar chart on September 24, 2026, showing token usage per task across 10 models. It was one of 6 posts from the account that day, alongside Terminal-Bench-Science 0.1: Score and other topics.

The numbers

The post reached 7.3K views, ranking #869 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 22 ranks #1,039 of 1,162 AI chart posts and #400 of 491 @ArtificialAnlys posts.

The lesson

A save rate of 0.041% at the 22nd percentile among AI chart posts, against a 0.076% median, shows this 10-model bar chart was not kept for later reference. The chart shows output tokens ranging from 23.9 down to 9.3, but the low save rate marks it as a post readers scrolled past.

What it means

At #400 of 491 @ArtificialAnlys posts, this chart sits in the account's lower range, and its 7.3K views fall far below the 39.9K median among AI chart posts. The gap to that median is the measured distance between this post and typical AI chart reach.

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

75 points read off this chart

Estimated from the image 53%

Series	Group	Value	Read
Output	DeepSeek V4 (max) (DeepSeek)	23.9 M	printed
Cached Input	DeepSeek V4 (max) (DeepSeek)	0.3 M	estimated
Input	DeepSeek V4 (max) (DeepSeek)	0 M	estimated
Output	Muse Spark (max) (Meta)	16.1 M	printed
Cached Input	Muse Spark (max) (Meta)	0.6 M	estimated
Input	Muse Spark (max) (Meta)	0 M	estimated
Output	Opus 5.5 (max) (Anthropic)	14.6 M	estimated
Cached Input	Opus 5.5 (max) (Anthropic)	1 M	estimated
Input	Opus 5.5 (max) (Anthropic)	0 M	estimated
Output	Grok Bull (high) (SpaceXAI)	13.6 M	estimated
Cached Input	Grok Bull (high) (SpaceXAI)	0.7 M	estimated
Input	Grok Bull (high) (SpaceXAI)	0 M	estimated

Showing 12 of 75. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/99a4429e2f62.json
GET https://viral-chart.com/api/charts/99a4429e2f62.json
GET https://viral-chart.com/api/charts/99a4429e2f62.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 99a4429e2f62.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/99a4429e2f62`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/99a4429e2f62/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/99a4429e2f62/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/99a4429e2f62/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 Claude Opus 5

Claude Opus 5: Business workflows AutomationBench by effort level

OfficialX · AnthropicSep 22, 2026

Business workflows AutomationBench by effort level1.5M views · 3.6K likes