Models
xAI
Output Tokens per Second

@ArtificialAnlysX · Sep 19, 2025

Output Tokens per Second

@ArtificialAnlys's bar chart drew 12.1K views on X: 1.1x @artificialanlys's median post and #791 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Output Tokens per Second comparison

XData Bar chart Grok 4 All xAI models o3 Gemini 2.5 Pro Llama 4 Maverick GPT-4.1 Grok 4.1Grok 4.1 FastGrok Code Fast 1gpt-oss-120b (high)

@ArtificialAnlys: Output Tokens per Second — Published by @ArtificialAnlys on X, Sep 19, 2025. Source: x.com

40/ 100

ViralChart score

Small but loved

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

#753 of 1,162 AI chart posts we hold · #220 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

Small but loved: views below the AI chart median, engagement above it, ranked #753 of 1,162.

Its launch-day rank was #3 of 3 posts from this account that day, with 3 posts total.

The 2-chart post shares its numbers across both charts, a level factor for reach.

Its 0.98% engagement rate sits at the 72nd percentile, above the 0.73% median for all AI chart posts.

2charts in this one post

The numbers belong to the post, so every chart in it shares them and it is ranked once.

3posts from @artificialanlys that day

Part of a run of 3 posts on Sep 19, 2025. This one was #3 of 3 by views that day.

top 28%engagement rate

0.98% 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.

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 #753 of 1,162

Views	12.1K	#791	bottom 32%
Likes	109	#754	bottom 35%
Engagement rate	0.98%	#330	top 28%
Save rate	0.058%	#740	bottom 36%

Among 491 @artificialanlys posts

Score #220 of 491

Views	12.1K	#243	top 49%
Likes	109	#225	top 46%
Engagement rate	0.98%	#175	top 36%
Save rate	0.058%	#302	bottom 39%

Growth

One read so far

Views12.1K

Age at our read388 days

Views per day of life31views 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 · Sep 19, 2025

@ArtificialAnlys Output Tokens per Second chart draws 12.1K views

A 2-chart bar comparison of 19 models, posted September 19, 2025, with 109 likes.

What happened

On September 19, 2025, @ArtificialAnlys posted a bar chart comparing Output Tokens per Second across 19 models, alongside a second chart on End-to-End Output Response Time. It was one of 3 posts that day.

The numbers

The post drew 12.1K views, ranking #791 of 1,162 AI chart posts, with a score of 40 (#753 of 1,162). Its engagement rate was 0.98%, above the 0.73% median.

The lesson

A 2-chart post with 19 models still got 12.1K views, but its save rate was 0.058%, far below the engagement rate. Readers engaged but did not save this multi-model comparison.

What it means

At #220 of 491 @ArtificialAnlys posts, this post underperformed its own median views of 39.9K. Its engagement rate beat the account median of 0.82%, but reach lagged.

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 88%

Group	Value	Read
Grok 4 Fast	344 tokens/s	printed
Grok Code Fast 1	259 tokens/s	printed
gpt-oss-20B (high)	243 tokens/s	printed
gpt-oss-120B (high)	220 tokens/s	printed
o3	185 tokens/s	printed
GPT-5 (minimal)	148 tokens/s	printed
Gemini 2.5 Pro	146 tokens/s	printed
Llama 4 Maverick	141 tokens/s	printed
Gemini 2.5 Flash	128 tokens/s	printed
GPT-5 (high)	125 tokens/s	printed
GPT-4.1	123 tokens/s	printed
Mistral Medium 3.1	69 tokens/s	printed

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

Max plan · API

GET https://viral-chart.com/api/posts/3c17edbf697e.json
GET https://viral-chart.com/api/charts/3c17edbf697e.json
GET https://viral-chart.com/api/charts/3c17edbf697e.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 3c17edbf697e.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/3c17edbf697e`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/3c17edbf697e/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/3c17edbf697e/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/3c17edbf697e/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.