Models
Google
Cost to Run AI Evaluations

@ArtificialAnlysX · May 9, 2025

Cost to Run AI Evaluations

@ArtificialAnlys's bar chart drew 12.7K views on X: 1.1x @artificialanlys's median post and #782 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Cost to run all AI evaluations varies widely

XData Bar chart Gemini 2 All Google models o3 Gemini 2.5 Pro DeepSeek R1 Grok 3 GPT-4.1 Gemini 2.5 Flash Llama 4 Maverick Llama 4 Scout

@ArtificialAnlys: Cost to Run AI Evaluations — Published by @ArtificialAnlys on X, May 9, 2025. Source: x.com

54/ 100

ViralChart score

Small but loved

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

#566 of 1,162 AI chart posts we hold · #176 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 lands in Small but loved, at #566 of 1,162 AI chart posts.

A 0.40% save rate puts it at the 99th percentile among AI chart posts, 5.2x the 0.076% median.

The bar chart drew 12.7K views against a 25.6K median for bar charts, 0.49x.

Its 12.7K views sit 1.1x above this account's 11.4K median, at #237 of 491 @ArtificialAnlys posts.

top 1%save rate

0.395% of viewers bookmarked it to come back to. The median post gets 0.076%.

top 7%engagement rate

1.56% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.5xthe median bar chart post

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

1.1x@artificialanlys's median post

12.7K views, where @artificialanlys's typical post gets 11.4K.

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 #566 of 1,162

Views	12.7K	#782	bottom 33%
Likes	172	#682	bottom 41%
Engagement rate	1.56%	#85	top 7%
Save rate	0.395%	#12	top 1%

Among 491 @artificialanlys posts

Score #176 of 491

Views	12.7K	#237	top 48%
Likes	172	#198	top 40%
Engagement rate	1.56%	#40	top 8%
Save rate	0.395%	#6	top 1%

Growth

One read so far

Views12.7K

Age at our read522 days

Views per day of life24views 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 · May 9, 2025

@ArtificialAnlys charts cost to run AI evaluations

A bar chart of evaluation costs drew 12.7K views and a 0.40% save rate, 5.2x the AI chart median.

What happened

On May 9, 2025, @ArtificialAnlys posted a bar chart on the cost to run AI evaluations, showing 18 models. It was the account's only post that day.

The numbers

The post reached 12.7K views, ranking #782 of 1,162 AI chart posts and #237 of 491 @ArtificialAnlys posts. Its 0.40% save rate ranked #12 of 1,162 AI chart posts.

The lesson

A 0.40% save rate, 5.2x the AI chart median, shows readers kept this 18-model cost comparison. The bar chart itself drew 12.7K views, 0.49x the 25.6K median for bar charts.

What it means

The 12.7K views sit 1.1x above this account's 11.4K median, but #782 of 1,162 AI chart posts leaves a wide gap to the 39.9K median among AI chart posts.

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

29 points read off this chart

Estimated from the image 40%

Series	Group	Value	Read
Input Cost	o3	1786 USD	estimated
Output Cost	o3	1951 USD	estimated
Input Cost	Claude 3.7 Sonnet Thinking	1356 USD	estimated
Output Cost	Claude 3.7 Sonnet Thinking	1485 USD	estimated
Input Cost	Gemini 2.5 Pro	713 USD	estimated
Output Cost	Gemini 2.5 Pro	844 USD	estimated
Input Cost	Gemini 2.5 Flash (Reasoning)	394 USD	estimated
Output Cost	Gemini 2.5 Flash (Reasoning)	445 USD	estimated
Input Cost	o4-mini (high)	304 USD	estimated
Output Cost	o4-mini (high)	323 USD	estimated
Input Cost	DeepSeek R1	158 USD	estimated
Output Cost	DeepSeek R1	154 USD	estimated

Showing 12 of 29. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/0d96c5fc097b.json
GET https://viral-chart.com/api/charts/0d96c5fc097b.json
GET https://viral-chart.com/api/charts/0d96c5fc097b.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 0d96c5fc097b.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.40 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/0d96c5fc097b`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/0d96c5fc097b/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/0d96c5fc097b/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/0d96c5fc097b/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 Gemini 2

Gemini 2: Gemini 2.5 Flash Native Audio Benchmarks

OfficialX · GoogleDec 16, 2025

Gemini 2.5 Flash Native Audio Benchmarks212.3K views · 1.7K likes