Models
Kimi (Moonshot AI)
Output Tokens Used to Run Evaluations in the

@ArtificialAnlysX · Jan 27, 2026

Output Tokens Used to Run Evaluations in the

@ArtificialAnlys's bar chart drew 7.2K views on X: 0.6x @artificialanlys's median post and #874 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Token usage varies widely across AI models in evaluations

XData Bar chart Kimi K2 All Kimi (Moonshot AI) models Gemini 3.1 Pro Kimi K2 Thinking MiniMax-M2GPT-5.2 (High)Claude Opus 4.5Falcon-HTR 7BNemotron Nano 9BNVIDIA Llama 3.1 Nemotron Nano

@ArtificialAnlys: Output Tokens Used to Run Evaluations in the — Published by @ArtificialAnlys on X, Jan 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.

#911 of 1,162 AI chart posts we hold · #306 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 #911 of 1,162 AI chart posts.

Its score of 30 sits at #911 of 1,162 AI chart posts, below the field.

A save rate of 0.042% is 0.55x the AI chart median of 0.076%, at the 23rd percentile.

On launch day the account posted 2 times, and this post ranked #2 of 2 by views.

0.3xthe median bar chart post

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

bottom 23%save rate

0.042% of viewers bookmarked it to come back to. The median post gets 0.076%.

2posts from @artificialanlys that day

Part of a run of 2 posts on Jan 27, 2026. This one was #2 of 2 by views that day.

0.6x@artificialanlys's median post

7.2K views, where @artificialanlys's typical post gets 11.4K.

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 #911 of 1,162

Views	7.2K	#874	bottom 25%
Likes	55	#852	bottom 27%
Engagement rate	0.79%	#512	top 44%
Save rate	0.042%	#899	bottom 23%

Among 491 @artificialanlys posts

Score #306 of 491

Views	7.2K	#296	bottom 40%
Likes	55	#275	bottom 44%
Engagement rate	0.79%	#257	bottom 48%
Save rate	0.042%	#367	bottom 25%

Growth

One read so far

Views7.2K

Age at our read258 days

Views per day of life28views 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 · Jan 27, 2026

@ArtificialAnlys charts output tokens used to run evaluations

A bar chart of token usage across models drew 7.2K views and a 0.79% engagement rate, with saves below the AI chart median.

What happened

@ArtificialAnlys posted a bar chart on January 27, 2026 showing output tokens used to run evaluations. It came with 1 other post from the account that day, on Artificial Analysis Intelligence Index v4.0.

The numbers

The post reached 7.2K views, ranking #874 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 30 ranks #911 of 1,162 AI chart posts and #306 of 491 @ArtificialAnlys posts.

The lesson

A save rate of 0.042% against the AI chart median of 0.076% shows this 27-model bar chart was not kept for citation. The chart shows Answer Tokens (GPT-5.2 (high)) at 200 and Kimi K2.5 at 98.5, but the printed values did not travel.

What it means

At #306 of 491 @ArtificialAnlys posts, this chart sits below the account's own body of work, and its 7.2K views fall short of the 39.9K median among AI chart posts.

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

87 points read off this chart

Estimated from the image 45%

Series	Group	Value	Read
Answer Tokens	GPT-5.2 (high)	200 M	printed
Reasoning Tokens	GPT-5.2 (high)	2.25 M	estimated
Answer Tokens	GEM-4.7	170 M	estimated
Reasoning Tokens		5.2 M	estimated
Answer Tokens	Falcon-HR-7B	140 M	estimated
Reasoning Tokens		8.2 M	estimated
Answer Tokens	NVIDIA Nemotron Nano	140 M	estimated
Reasoning Tokens		23 M	estimated
Answer Tokens	GPT-5.2 (high)	140 M	estimated
Reasoning Tokens	GPT-5.2 (High)	130 M	estimated
Answer Tokens	Kimi K2	130 M	estimated
Reasoning Tokens	Kimi K2	0 M	estimated

Showing 12 of 87. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/fae1f713bc19.json
GET https://viral-chart.com/api/charts/fae1f713bc19.json
GET https://viral-chart.com/api/charts/fae1f713bc19.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 fae1f713bc19.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.45 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/fae1f713bc19`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/fae1f713bc19/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/fae1f713bc19/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/fae1f713bc19/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 Kimi K2

Kimi K2: Kimi K2 Thinking vs GPT-5 vs Claude Sonnet

OfficialX · Kimi (Moonshot AI)Nov 6, 2025

Kimi K2 Thinking vs GPT-5 vs Claude Sonnet4.9M views · 9.5K likes