Models
Anthropic
SWE-Atlas-OnA Coding Agent Index vs. Cost per Task

@ArtificialAnlysX · May 21, 2026

SWE-Atlas-OnA Coding Agent Index vs. Cost per Task

@ArtificialAnlys's scatter plot drew 246.8K views on X: 22x @artificialanlys's median post and #236 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Coding Agent Index vs. Cost per Task

XData Scatter plot Claude Opus 4.7 All Anthropic models GLM-5 Claude Code DeepSeek V4GPT-5.5Curson CLI 2.5Kimi K2.6Gemini 3.1

72/ 100

ViralChart score

Wide but thin

More views than the median post but a lower engagement rate: many saw it, few acted. Common for big accounts.

#186 of 1,162 AI chart posts we hold · #44 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 Wide but thin quadrant, with a score rank of #186 of 1,162 AI chart posts.

Its 247K views sit 22x above @ArtificialAnlys's company median of 11.4K, ranking #46 of 491 @ArtificialAnlys posts by views.

A score of 72 places it #186 of 1,162 AI chart posts and #44 of 491 @ArtificialAnlys posts.

It was one of 3 posts from this account that day, ranking #2 of 3 by views.

22x@artificialanlys's median post

246.8K views, where @artificialanlys's typical post gets 11.4K.

11xthe median scatter plot post

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

3posts from @artificialanlys that day

Part of a run of 3 posts on May 21, 2026. This one was #2 of 3 by views that day.

top 37%save rate

0.100% of viewers bookmarked it to come back to. The median post gets 0.076%.

Public X numbers from our read on Oct 13, 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 #186 of 1,162

Views	246.8K	#236	top 20%
Likes	1.3K	#224	top 19%
Engagement rate	0.63%	#679	bottom 42%
Save rate	0.100%	#434	top 37%

Among 491 @artificialanlys posts

Score #44 of 491

Views	246.8K	#46	top 9%
Likes	1.3K	#39	top 8%
Engagement rate	0.63%	#325	bottom 34%
Save rate	0.100%	#194	top 39%

Growth

Our reads cover 22 hours

Views246.8K

Age at our read146 days

Views per day of life1.7Kviews divided by days since it was posted

Gained between our reads+16views over 22 hours, about 17 a day now

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 21, 2026

@ArtificialAnlys posts Coding Agent Index vs. Cost per Task scatter

The scatter plot drew 247K views against a 39.9K median among AI chart posts, with a 0.63% engagement rate.

What happened

@ArtificialAnlys published a scatter plot on May 21, 2026, titled Coding Agent Index vs. Cost per Task. It was one of 3 posts from this account that day, alongside Artificial Analysis Intelligence Index v4.0 and AA-Omniscence Index and Accuracy.

The numbers

It reached 247K views, ranking #236 of 1,162 AI chart posts by views and #46 of 491 @ArtificialAnlys posts. Its score of 72 ranks #186 of 1,162 AI chart posts.

The lesson

At 0.100% save rate and 0.63% engagement rate, this scatter plot's 247K views came with below-median engagement. A single scatter plot with 8 models shown can travel far while drawing few saves.

What it means

Its 247K views rank #46 of 491 @ArtificialAnlys posts, yet its score rank of #186 of 1,162 AI chart posts trails its view rank. The gap between 247K views and a 39.9K median shows reach without matching engagement.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what @artificialanlys posted next

Data and API

10 points read off this chart

Estimated from the image 30%

Group	Value	Read
Claude Opus 4.7 (High)	67 index	estimated
GPT-5.5 (High)	65 index	estimated
Claude Opus 4.7 (Medium)	63 index	estimated
Claude Opus 4.7 (Low)	61 index	estimated
GPT-5.5 (Medium)	58 index	estimated
GLM-5.1 (High)	53 index	estimated
Kimi K2.6 (High)	50 index	estimated
DeepSeek V4 (High)	50 index	estimated
Claude Opus 4.7 (Medium)	48 index	estimated
Gemini 3.1 Pro (High)	43 index	estimated

Max plan · API

GET https://viral-chart.com/api/posts/a6f8a80647b9.json
GET https://viral-chart.com/api/charts/a6f8a80647b9.json
GET https://viral-chart.com/api/charts/a6f8a80647b9.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 a6f8a80647b9.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 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/a6f8a80647b9`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/a6f8a80647b9/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/a6f8a80647b9/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/a6f8a80647b9/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 4.7

Claude Opus 4.7: Claude Opus 4.7 ranks #1 in Code Arena

X · @arenaApr 17, 2026

Claude Opus 4.7 ranks #1 in Code Arena367.5K views · 729 likes