1. Models
  2. Google
  3. ITBench-AA: Average precision at full recall vs. Cost
A
@ArtificialAnlysX · May 27, 2026

ITBench-AA: Average precision at full recall vs. Cost

@ArtificialAnlys's scatter plot drew 2.3K views on X: 0.2x @artificialanlys's median post and #1,065 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Most attractive quadrant: high precision, low cost

Published by @ArtificialAnlys on X, May 27, 2026. Source: x.com
30/ 100

ViralChart score

Small but loved

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

#919 of 1,162 AI chart posts we hold · #312 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 #919 of 1,162 AI chart posts by score.

Its 2.3K views sit at 0.20x @ArtificialAnlys's own median of 11.4K, ranking #425 of 491 @ArtificialAnlys posts.

The score of 30 places it #919 of 1,162 AI chart posts and #312 of 491 @ArtificialAnlys posts.

Engagement of 1.08% is 1.5x the AI chart median of 0.73%, at the 77th percentile among AI chart posts.

0.2x@artificialanlys's median post

2.3K views, where @artificialanlys's typical post gets 11.4K.

0.1xthe median scatter plot post

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

top 23%engagement rate

1.08% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

top 25%save rate

0.130% 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 #919 of 1,162

Views2.3K#1,065bottom 8%
Likes22#1,009bottom 14%
Engagement rate1.08%#266top 23%
Save rate0.130%#291top 25%

Among 491 @artificialanlys posts

Score #312 of 491

Views2.3K#425bottom 14%
Likes22#378bottom 24%
Engagement rate1.08%#141top 29%
Save rate0.130%#147top 30%

Growth

One read so far

Views2.3K
Age at our read138 days
Views per day of life17views 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 27, 2026

@ArtificialAnlys plots ITBench-AA precision against cost

A scatter plot of 30 models drew 2.3K views and a 1.08% engagement rate, 1.5x the AI chart median.

What happened

@ArtificialAnlys posted a scatter plot of ITBench-AA average precision at full recall against cost on May 27, 2026. It was the account's only post that day.

The numbers

The post reached 2.3K views, #1,065 of 1,162 AI chart posts, against a median of 39.9K. Its score of 30 ranks #919 of 1,162 AI chart posts.

The lesson

At 1.08% engagement against a 0.13% save rate, this scatter plot drew likes and replies but few saves. The 30 models shown sit in one chart, and the 1.5x engagement ratio to the AI chart median came with a 0.20x views ratio to the account's own median.

What it means

For @ArtificialAnlys, the gap is stark: 2.3K views against the account's 11.4K median, a 0.20x ratio. The 1.08% engagement rate shows the chart format drew interaction even as views ranked #425 of 491 @ArtificialAnlys posts.

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

Data and API

38 points read off this chart

Estimated from the image 38%
SeriesGroupValueRead
OpenAIArtificial Analysis60 %estimated
MetaArtificial Analysis60 %estimated
GoogleArtificial Analysis60 %estimated
AnthropicArtificial Analysis60 %estimated
DeepSeekArtificial Analysis60 %estimated
xAIArtificial Analysis60 %estimated
MiniMaxArtificial Analysis60 %estimated
KimiArtificial Analysis60 %estimated
XiaomiArtificial Analysis60 %estimated
Z AIArtificial Analysis60 %estimated
AlibabaArtificial Analysis60 %estimated
AlibabaQwen3.5 35B A3B22 %estimated

Showing 12 of 38. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/018fec3f545b.json
GET https://viral-chart.com/api/charts/018fec3f545b.json
GET https://viral-chart.com/api/charts/018fec3f545b.skill.md

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 018fec3f545b.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.38 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

PathReturnsPlan
GET/api/v1/charts/018fec3f545bTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/018fec3f545b/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/018fec3f545b/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/018fec3f545b/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 3

More from Google

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on May 27, 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.