Models
Anthropic
Artificial Analysis Intelligence vs Cost to Run

@ArtificialAnlysX · Apr 18, 2026

Artificial Analysis Intelligence vs Cost to Run

@ArtificialAnlys's scatter plot drew 2.8K views on X: 0.2x @artificialanlys's median post and #1,045 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Most attractive quadrant shows best intelligence per cost

XData Scatter plot Claude Opus 4.6 All Anthropic modelsAlibabaAnthropicDeepSeekGoogleKimiMiniMaxNVIDIAOpenAI

@ArtificialAnlys: Artificial Analysis Intelligence vs Cost to Run — Published by @ArtificialAnlys on X, Apr 18, 2026. Source: x.com

19/ 100

ViralChart score

Small but loved

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

#1,070 of 1,162 AI chart posts we hold · #425 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 Small but loved quadrant at #1,070 of 1,162 AI chart posts.

Its score of 19 lands at #1,070 of 1,162 AI chart posts.

At 2.8K views it runs 0.25x @ArtificialAnlys's median post, ranking #411 of 491 @ArtificialAnlys posts.

Its 0.035% save rate sits at 18th percentile among AI chart posts, 0.46x the 0.076% median.

0.1xthe median scatter plot post

Across 187 scatter plot posts we hold, the median gets 22.4K views.

0.2x@artificialanlys's median post

2.8K views, where @artificialanlys's typical post gets 11.4K.

4posts from @artificialanlys that day

Part of a run of 4 posts on Apr 18, 2026. This one was #4 of 4 by views that day.

bottom 18%save rate

0.035% 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 #1,070 of 1,162

Views	2.8K	#1,045	bottom 10%
Likes	20	#1,021	bottom 12%
Engagement rate	0.78%	#532	top 46%
Save rate	0.035%	#959	bottom 18%

Among 491 @artificialanlys posts

Score #425 of 491

Views	2.8K	#411	bottom 16%
Likes	20	#385	bottom 22%
Engagement rate	0.78%	#265	bottom 46%
Save rate	0.035%	#392	bottom 20%

Growth

One read so far

Views2.8K

Age at our read178 days

Views per day of life16views 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 · Apr 18, 2026

@ArtificialAnlys scatter plot maps intelligence against cost to run

A 15-model scatter plot from @ArtificialAnlys drew 2.8K views and a 0.78% engagement rate, with saves below the AI chart median.

What happened

@ArtificialAnlys posted a scatter plot on Artificial Analysis Intelligence vs Cost to Run on April 18, 2026. It was one of 4 posts from the account that day, alongside an Artificial Analysis Intelligence Index v4.0 post, an AI Model Benchmarks Comparison post and an AA-Omniscence Index and Accuracy post.

The numbers

The post reached 2.8K views, ranking #1,045 of 1,162 AI chart posts and #411 of 491 @ArtificialAnlys posts. Its score of 19 ranks #1,070 of 1,162 AI chart posts and #425 of 491 @ArtificialAnlys posts.

The lesson

The chart shows 15 models on a scatter plot, and the post's 0.035% save rate sits at 18th percentile among AI chart posts. That is 0.46x the 0.076% median save rate for AI chart posts.

What it means

At #425 of 491 @ArtificialAnlys posts by score, this chart post trails the account's own body of work. Its 2.8K views against a 39.9K median among AI chart posts mark it as a low-reach entry.

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

17 points read off this chart

Estimated from the image 58%

Series	Group	Value	Read
DeepSeek	DeepSeek V3.2	34 index	estimated
NVIDIA	NVIDIA Nemotron 3 Super	34 index	estimated
MiniMax	MiniMax-M2.7	50 index	estimated
Google	Gemini 3 Flash	44 index	estimated
Xiaomi	MiMo-V2-Pro	50 index	estimated
xAI	Grok 4.20 0309 v2	50 index	estimated
Kimi	Kimi K2.5	46 index	estimated
Alibaba	Qwen3.5 397B A17B	46 index	estimated
Z AI	GLM-5.1	50 index	estimated
Anthropic	Claude 4.5 Haiku	36 index	estimated
OpenAI	GPT-5.4 mini (xhigh)	46 index	estimated
Google	Gemini 3.1 Pro Preview	54 index	estimated

Showing 12 of 17. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/896c480d74c2.json
GET https://viral-chart.com/api/charts/896c480d74c2.json
GET https://viral-chart.com/api/charts/896c480d74c2.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 896c480d74c2.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/896c480d74c2`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/896c480d74c2/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/896c480d74c2/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/896c480d74c2/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 4.6

Claude Opus 4.6: Long context MRCR v2 retrieval

OfficialX · AnthropicMar 13, 2026

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

Data

Claude Opus 4.6: Claude model behavioral differences

OfficialX · AnthropicJul 13, 2026

Claude model behavioral differences68.2K views · 312 likes

Data

OfficialBlog · AnthropicApr 16, 2026

Knowledge GDPval-AA

OfficialBlog · AnthropicApr 16, 2026

Document OfficeQA Pro reasoning

OfficialBlog · AnthropicApr 16, 2026

Visual ScreenSpot-Pro Navigation Accuracy

OfficialBlog · AnthropicApr 16, 2026

Long-context GraphWalks reasoning

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

OfficialX · AnthropicMay 22, 2025

Claude 4 benchmarks4.3M views · 20.5K likes

Data

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on Apr 18, 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.