Models
Qwen
Average Score vs Output Tokens

@ArtificialAnlysX · Aug 24, 2026

Average Score vs Output Tokens

@ArtificialAnlys's scatter plot drew 1.7K views on X: 0.2x @artificialanlys's median post and #1,096 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Average Score vs Output Tokens for AI models

XData Scatter plot Qwen3 All Qwen modelsQwen3.5 9BGemma 4 4BLFM2.5-2.6BNVIDIA Nemotron Nano 9B V2Ling 3.0 TinyNanbeige4.2-3BOrnith-1D-9BGemma 4 E4B

@ArtificialAnlys: Average Score vs Output Tokens — Published by @ArtificialAnlys on X, Aug 24, 2026. Source: x.com

33/ 100

ViralChart score

Small but loved

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

#865 of 1,162 AI chart posts we hold · #277 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, with a score rank of #865 of 1,162 AI chart posts.

Its 1.7K views sit at 0.15x this account's 11.4K median, ranking #445 of 491 @ArtificialAnlys posts.

The 2.02% engagement rate lands in the 98th percentile of AI chart posts, against a 0.73% median.

It ranked #4 of 4 posts from this account that day, with 4 posts published.

0.2x@artificialanlys's median post

1.7K 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 2%engagement rate

2.02% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

4posts from @artificialanlys that day

Part of a run of 4 posts on Aug 24, 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 #865 of 1,162

Views	1.7K	#1,096	bottom 6%
Likes	31	#950	bottom 18%
Engagement rate	2.02%	#23	top 2%
Save rate	0.115%	#351	top 30%

Among 491 @artificialanlys posts

Score #277 of 491

Views	1.7K	#445	bottom 9%
Likes	31	#340	bottom 31%
Engagement rate	2.02%	#8	top 2%
Save rate	0.115%	#165	top 34%

Growth

One read so far

Views1.7K

Age at our read49 days

Views per day of life35views 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 · Aug 24, 2026

@ArtificialAnlys scatter plot on Average Score vs Output Tokens

A 20-model scatter plot drew 1.7K views and a 2.02% engagement rate, the 98th percentile among AI chart posts.

What happened

@ArtificialAnlys posted a scatter plot on Average Score vs Output Tokens on August 24, 2026. It was one of 4 posts from the account that day, alongside Peak Inference Memory at 4K Context, Mobile Device Benchmark Evaluations and AI model performance.

The numbers

The post reached 1.7K views, ranking #1,096 of 1,162 AI chart posts and #445 of 491 @ArtificialAnlys posts. Its 2.02% engagement rate ranked #23 of 1,162 AI chart posts.

The lesson

A 2.02% engagement rate at the 98th percentile came with a 0.12% save rate. The 20-model scatter plot drew 1.7K views, below the 39.9K median among AI chart posts.

What it means

At #277 of 491 @ArtificialAnlys posts by score, this scatter plot trails the account's 11.4K median views by 0.15x. Its 2.02% engagement rate sits above the account's own 0.82% median.

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

21 points read off this chart

Estimated from the image 50%

Series	Group	Value	Read
Alibaba	Qwen3.5 9B (Non-reasoning)	59	estimated
Google	Gemma 4 4B (Non-reasoning)	55	estimated
Google	Gemma 4 4B (Reasoning)	54	estimated
Google	Gemma 4 E2B (Non-reasoning)	52	estimated
Google	Gemma 4 E2B (Reasoning)	51	estimated
IBM	Granite 4.1B	50	estimated
IBM	Granite 4.0 350M	20	estimated
Liquid AI	LFM2.5-1.2B-Instruct	45	estimated
Liquid AI	LFM2.5-2.6B-Exp	42	estimated
Liquid AI	LFM2.5-350M	30	estimated
Liquid AI	LFM2.5-2.6B	55	estimated
Nanbeige	Nanbeige-2.3B	58	estimated

Showing 12 of 21. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/970bb5acd156.json
GET https://viral-chart.com/api/charts/970bb5acd156.json
GET https://viral-chart.com/api/charts/970bb5acd156.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 970bb5acd156.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/970bb5acd156`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/970bb5acd156/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/970bb5acd156/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/970bb5acd156/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.