Models
Anthropic
Tokens used to run all evaluations in the

@ArtificialAnlysX · Mar 26, 2026

Tokens used to run all evaluations in the

@ArtificialAnlys's bar chart drew 3.6K views on X: 0.3x @artificialanlys's median post and #1,008 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Tokens used across AI models

XData Bar chart Claude Sonnet 4 All Anthropic models Gemini 3 ProGPT-5.1-mini (high)GPT-5.1-nano (high)Claude 4.5 (max)Claude Opus 4.5 (max)GPT-5.4 (high)K-EXAONE 7NVIDIA Nemotron 3 Super

@ArtificialAnlys: Tokens used to run all evaluations in the — Published by @ArtificialAnlys on X, Mar 26, 2026. Source: x.com

11/ 100

ViralChart score

Quiet

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

#1,147 of 1,162 AI chart posts we hold · #481 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, at #1,147 of 1,162 AI chart posts.

Its score of 11 lands at #1,147 of 1,162 AI chart posts.

A 0.000% save rate sits in the bottom decile, 2nd percentile among AI chart posts.

At 3.6K views it runs 0.32x this company's median of 11.4K.

bottom 2%save rate

0.000% of viewers bookmarked it to come back to. The median post gets 0.076%.

0.1xthe median bar chart post

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

0.3x@artificialanlys's median post

3.6K views, where @artificialanlys's typical post gets 11.4K.

4posts from @artificialanlys that day

Part of a run of 4 posts on Mar 26, 2026. This one was #4 of 4 by views that day.

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 #1,147 of 1,162

Views	3.6K	#1,008	bottom 13%
Likes	13	#1,083	bottom 7%
Engagement rate	0.44%	#905	bottom 22%
Save rate	0.000%	#1,133	bottom 2%

Among 491 @artificialanlys posts

Score #481 of 491

Views	3.6K	#380	bottom 23%
Likes	13	#428	bottom 12%
Engagement rate	0.44%	#406	bottom 17%
Save rate	0.000%	#467	bottom 3%

Growth

One read so far

Views3.6K

Age at our read201 days

Views per day of life18views 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 · Mar 26, 2026

@ArtificialAnlys charts tokens used across AI models

A 24-model bar chart of tokens used across AI models drew 3.6K views and a 0.000% save rate.

What happened

@ArtificialAnlys posted a bar chart on March 26, 2026 showing tokens used across AI models, with 24 models shown. It was one of 4 posts from the account that day, alongside AI Model Intelligence vs Cost, Speech Reasoning (Big Bench Audio) and GDPval-AA Agentic Leaderboard.

The numbers

It reached 3.6K views, #1,008 of 1,162 AI chart posts, against a median of 39.9K among AI chart posts. Its score of 11 ranks #481 of 491 @ArtificialAnlys posts.

The lesson

A 0.000% save rate puts this 24-model bar chart in the bottom decile among AI chart posts, against a median of 0.076%. The chart shows tokens on the y-axis, and readers kept none of it.

What it means

At 0.32x this company's median views, the post ranks #380 of 491 @ArtificialAnlys posts by views. The gap to the 11.4K company median is where this chart sits.

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

36 points read off this chart

Estimated from the image 61%

Group	Value	Read
GPT-5.1 (High)	230 M	printed
GPT-5.1 nano (High)	210 M	printed
Claude Sonnet 4.5 (max)	200 M	printed
Claude Opus 4.6 (max)	190 M	printed
GPT-5.1 (Low)	160 M	estimated
K-EXAONE 3.5	120 M	estimated
NVIDIA Nemotron Super 49B v1.1	110 M	estimated
GPT-5.1 nano (High)	100 M	printed
GLM-5	110 M	printed
MiniMax-M2 Flash (Feb 2026)	100 M	printed
Kim K2.5	110 M	estimated
Claude 4.5 Haiku	100 M	estimated

Showing 12 of 36. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/6017fc5ba716.json
GET https://viral-chart.com/api/charts/6017fc5ba716.json
GET https://viral-chart.com/api/charts/6017fc5ba716.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 6017fc5ba716.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/6017fc5ba716`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/6017fc5ba716/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/6017fc5ba716/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/6017fc5ba716/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 Sonnet 4

OfficialBlog · AnthropicFeb 17, 2026

Vending-Bench Arena Sonnet4.6 vs. Sonnet 4.5

OfficialBlog · AnthropicSep 29, 2025

Misaligned behavior scores in simulated settings

Claude Sonnet 4: Claude Arena Frontend Rankings

X · @arenaJul 2, 2026

Claude Arena Frontend Rankings94.9K views · 777 likes

Data

Claude Sonnet 4: Artificial Analysis Intelligence Index v3.0

X · @ArtificialAnlysDec 3, 2025

Artificial Analysis Intelligence Index v3.083.7K views · 878 likes

Data

Claude Sonnet 4: Code Arena Top 15: Agentic Coding

X · @arenaApr 22, 2026

Code Arena Top 15: Agentic Coding72.9K views · 340 likes

Data

Claude Sonnet 4: Time per Intelligence Index Task

X · @ArtificialAnlysJun 16, 2026

Time per Intelligence Index Task12.6K views · 78 likes

Data

More from Anthropic

Anthropic stacked bar chart: Firefox Security Vulnerabilities

4.7x

Anthropic·Mar 2026

Firefox Security Vulnerabilities

3.2M views14.8K likes0.5% eng.

Data

Anthropic line chart: US GDP AI scenarios

0.4x

Anthropic·Sep 2026

US GDP AI scenarios

856.3K views1.2K likes0.2% eng.

Data

Anthropic bar chart: RL reward hacking risks

1.0x

Anthropic·Sep 2026

RL reward hacking risks

806.5K views3.2K likes0.5% eng.

Data

Claude Opus 4: Opus 4.8 benchmark comparison

OfficialX · AnthropicMay 28, 2026

Opus 4.8 benchmark comparison15.5M views · 66.3K likes

Data

Claude Mythos: Opus 4.7 Benchmark Comparison

OfficialX · AnthropicApr 16, 2026

Opus 4.7 Benchmark Comparison14.1M views · 79.6K likes

Data

Claude agents and computer use: AI Model Benchmark Comparison

OfficialX · AnthropicNov 24, 2025

AI Model Benchmark Comparison7.8M views · 18.8K likes

Data

Claude Fable 5: Claude Mythos 5 and Fable 5 Benchmark Comparison

OfficialX · AnthropicJun 9, 2026

Claude Mythos 5 and Fable 5 Benchmark Comparison6.3M views · 15.4K likes

Data

Claude Fable 5: AI Model Benchmark Comparison

OfficialX · AnthropicJul 24, 2026

AI Model Benchmark Comparison5.8M views · 10.7K likes

Data

Claude Opus 4.6: Long context MRCR v2 retrieval

OfficialX · AnthropicMar 13, 2026

Long context MRCR v2 retrieval5.7M views · 24.6K likes

Data

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on Mar 26, 2026 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.