Models
Google
Output Answer vs Reasoning Tokens for AI Models

@ArtificialAnlysX · Dec 17, 2025

Output Answer vs Reasoning Tokens for AI Models

@ArtificialAnlys's bar chart drew 3.2K views on X: 0.3x @artificialanlys's median post and #1,026 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Output tokens dominate reasoning tokens across AI models

XData Bar chart Gemini 2 All Google models Kimi K2 Thinking Grok 4 MiniMax-M2 DeepSeek-R1 Gemini 3.1 ProGemini 3.1 (Reasoning)gpt-oss-120bQwen3-235B-A22B

@ArtificialAnlys: Output Answer vs Reasoning Tokens for AI Models — Published by @ArtificialAnlys on X, Dec 17, 2025. Source: x.com

36/ 100

ViralChart score

Small but loved

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

#815 of 1,162 AI chart posts we hold · #251 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 #815 of 1,162 AI chart posts.

Its 3.2K views sit at 0.28x @ArtificialAnlys's median post, ranking #397 of 491 @ArtificialAnlys posts.

Engagement of 1.26% lands in the 86th percentile among AI chart posts, 1.7x the AI chart median of 0.73%.

It was one of 5 posts from this account that day, ranking #4 of 5 by views.

0.1xthe median bar chart post

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

0.3x@artificialanlys's median post

3.2K views, where @artificialanlys's typical post gets 11.4K.

5posts from @artificialanlys that day

Part of a run of 5 posts on Dec 17, 2025. This one was #4 of 5 by views that day.

top 14%engagement rate

1.26% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

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 #815 of 1,162

Views	3.2K	#1,026	bottom 12%
Likes	37	#929	bottom 20%
Engagement rate	1.26%	#160	top 14%
Save rate	0.158%	#201	top 17%

Among 491 @artificialanlys posts

Score #251 of 491

Views	3.2K	#397	bottom 19%
Likes	37	#329	bottom 33%
Engagement rate	1.26%	#80	top 16%
Save rate	0.158%	#105	top 21%

Growth

One read so far

Views3.2K

Age at our read299 days

Views per day of life11views 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 · Dec 17, 2025

@ArtificialAnlys charts output tokens against reasoning tokens

A bar chart on output versus reasoning tokens drew 3.2K views and a 1.26% engagement rate, above the AI chart median.

What happened

@ArtificialAnlys posted a bar chart on Output Answer vs Reasoning Tokens for AI Models on December 17, 2025. It was one of 5 posts from this account that day, alongside Speech Reasoning (Big Bench Audio) at 3.3M views.

The numbers

The post reached 3.2K views, ranking #1,026 of 1,162 AI chart posts and #397 of 491 @ArtificialAnlys posts. Its engagement rate of 1.26% ranked #160 of 1,162 AI chart posts.

The lesson

With 15 models shown in a single bar chart, the post drew 3.2K views against a company median of 11.4K. Its 1.26% engagement rate, 1.7x the AI chart median, shows that a dense model comparison can hold attention even when views stay low.

What it means

At #251 of 491 @ArtificialAnlys posts by score, this chart sits below the account's own median views of 11.4K. The 1.26% engagement rate against a 0.73% AI chart median shows the gap is in reach, not in how the chart is received.

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

90 points read off this chart

Estimated from the image 43%

Series	Group	Value	Read
Answer Tokens	Gemini 3 (Reasoning)	160 M	printed
Reasoning Tokens	Gemini 3 (Reasoning)	160 M	estimated
Answer Tokens	Flash (high)	140 M	estimated
Reasoning Tokens	Flash (high)	130 M	estimated
Answer Tokens	Kimi K2 Thinking	120 M	estimated
Reasoning Tokens	Kimi K2 Thinking	120 M	estimated
Answer Tokens	Kimi K2 Thinking	120 M	estimated
Reasoning Tokens	Kimi K2 Thinking	110 M	estimated
Answer Tokens	MiniMax-M2	110 M	estimated
Reasoning Tokens	MiniMax-M2	110 M	estimated
Answer Tokens	gpt-oss-120b (high)	110 M	printed
Reasoning Tokens	gpt-oss-120b (high)	100 M	estimated

Showing 12 of 90. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/d323b906331e.json
GET https://viral-chart.com/api/charts/d323b906331e.json
GET https://viral-chart.com/api/charts/d323b906331e.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 d323b906331e.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.43 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/d323b906331e`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/d323b906331e/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/d323b906331e/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/d323b906331e/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