Models
Z.ai
AI model cyber safety benchmark scores

@ArtificialAnlysX · Oct 6, 2026

AI model cyber safety benchmark scores

@ArtificialAnlys's benchmark bar chart drew 7.8K views on X: 0.7x @artificialanlys's median post and #859 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

MiniMax-M2.2-Pro leads the Artificial Analysis Cyber Index with 56% success, while most models score below 50%.

XData Benchmark bar chart GLM-5.3 All Z.ai models Gemini 3.1 (Pro)Grok 4.1 (Think)MiniMax-M2.2-ProGPT-5.2 (Luma)GLM-4.5-AirGLM-4.5-SearchMiniMax-M2.1-ProMiniMax-M2.1 (Luma)

@ArtificialAnlys: AI model cyber safety benchmark scores — Published by @ArtificialAnlys on X, Oct 6, 2026. Source: x.com

35/ 100

ViralChart score

Small but loved

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

#828 of 1,162 AI chart posts we hold · #257 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, at #828 of 1,162 AI chart posts.

Its #5 of 5 rank by views that day sits against 5 posts from this account on October 6, 2026.

At #828 of 1,162 AI chart posts, the score of 35 lands below the median.

The 0.89% engagement rate is above the 0.73% median among AI chart posts, at the 66th percentile.

0.2xthe median benchmark bar chart post

Across 215 benchmark bar chart posts we hold, the median gets 44.4K views.

5posts from @artificialanlys that day

Part of a run of 5 posts on Oct 6, 2026. This one was #5 of 5 by views that day.

top 34%engagement rate

0.89% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.7x@artificialanlys's median post

7.8K views, where @artificialanlys's typical post gets 11.4K.

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 #828 of 1,162

Views	7.8K	#859	bottom 26%
Likes	60	#836	bottom 28%
Engagement rate	0.89%	#401	top 34%
Save rate	0.064%	#683	bottom 41%

Among 491 @artificialanlys posts

Score #257 of 491

Views	7.8K	#287	bottom 42%
Likes	60	#266	bottom 46%
Engagement rate	0.89%	#206	top 42%
Save rate	0.064%	#285	bottom 42%

Growth

Our reads cover 26 hours

Views7.8K

Age at our read7 days

Views per day of life1.1Kviews divided by days since it was posted

Gained between our reads+42views over 26 hours, about 38 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 · Oct 6, 2026

@ArtificialAnlys posts AI model cyber safety benchmark scores

A benchmark bar chart of AI model cyber safety scores drew 7.8K views and a 0.89% engagement rate.

What happened

@ArtificialAnlys posted a benchmark bar chart on October 6, 2026, showing AI model cyber safety benchmark scores. It was one of 5 posts from the account that day, alongside posts on the Artificial Analysis Intelligence Index v4.3.2, Frontier AI Intelligence Index by Country Over Time, and Cost per Intelligence Index Task.

The numbers

The post reached 7.8K views, ranking #859 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 35 ranks #828 of 1,162 AI chart posts and #257 of 491 @ArtificialAnlys posts.

The lesson

The chart shows printed values from 29% to 56%, and the post drew a 0.89% engagement rate against a 0.73% median among AI chart posts. A benchmark bar chart with 18 models shown can hold above-median engagement even when views rank #859 of 1,162 AI chart posts.

What it means

At #257 of 491 @ArtificialAnlys posts, this chart post trails the account's own body of work, and its 7.8K views sit far below the 39.9K median among AI chart posts. The 0.89% engagement rate, above the account's 0.82% median, shows the gap is in reach, not in how the chart is received.

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

62 points read off this chart

Estimated from the image 55%

Series	Group	Value	Read
CWE-Bench-AA	Grok 4 (Fast)	56 %	printed
	MiniMax-M2.2-Pro	56 %	estimated
CWE-Bench-AA	GPT-5.2 (Lite)	53 %	printed
CWE-Bench-AA	GLM-4.5-Air	50 %	printed
CWE-Bench-AA	MiniMax-M2	50 %	printed
	Mistral Large 2	44 %	estimated
	Kimi K2 (Instruct)	41 %	estimated
CWE-Bench-AA	DeepSeek-V4.1 (Fast)	41 %	estimated
DeepseekBench-AA	GPT-5.2 (High)	37 %	estimated
CWE-Bench-AA	GLM-4.5 (High)	36 %	printed
CWE-Bench-AA	Gemini 3.1 (Flash)	33 %	estimated
CWE-Bench-AA	Claude Opus 4.5 (High)	29 %	printed

Showing 12 of 62. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/82f6c5fc7bb1.json
GET https://viral-chart.com/api/charts/82f6c5fc7bb1.json
GET https://viral-chart.com/api/charts/82f6c5fc7bb1.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 82f6c5fc7bb1.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/82f6c5fc7bb1`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/82f6c5fc7bb1/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/82f6c5fc7bb1/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/82f6c5fc7bb1/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 GLM-5.3

OfficialX · Z.aiOct 12, 2026

LLM Performance on Harvey LAB533.2K views · 6.3K likes

Data

OfficialBlog · Z.ai

Pareto frontier of the Artificial Analysis Intelligence Index

GLM-5.3: AI Model Intelligence vs Cost Pareto

X · @ArtificialAnlysAug 26, 2026

AI Model Intelligence vs Cost Pareto167.5K views · 1.9K likes

Data

GLM-5.3: Pareto Frontier for Code Arena: WebDev

X · @arenaAug 26, 2026

Pareto Frontier for Code Arena: WebDev76.1K views · 645 likes

Data

X · @arenaAug 26, 2026

Code Arena WebDev Top 159.6K views · 61 likes

Data

GLM-5.3: Output Tokens Used to Run Evaluations in the

X · @ArtificialAnlysAug 26, 2026

Output Tokens Used to Run Evaluations in the6.2K views · 51 likes

Data

More from Z.ai

GLM-5: Agentic Coding Performance by Effort Level

OfficialX · Z.aiJun 16, 2026

Agentic Coding Performance by Effort Level7.7M views · 13.1K likes

Data

GLM-5: LLM performance across six benchmarks

OfficialX · Z.aiAug 26, 2026

LLM performance across six benchmarks7M views · 23.8K likes

Data

GLM-5: LLM benchmark performance across nine tasks

OfficialX · Z.aiAug 14, 2026

LLM benchmark performance across nine tasks5.9M views · 19.3K likes

Data

OfficialX · Z.aiApr 7, 2026

Coding Performance Evaluation4.4M views · 10.7K likes

Data

GLM-4: LLM Benchmarks Performance Evaluation

OfficialX · Z.aiJan 19, 2026

LLM Benchmarks Performance Evaluation1.7M views · 5.3K likes

Data

OfficialX · Z.aiFeb 11, 2026

LLM Performance on 8 Benchmarks1.5M views · 5.3K likes

Data

Questions people ask

Where does this chart come from?

@ArtificialAnlys published it on Oct 6, 2026 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Can I make a chart like this?

Use the format, not the picture. Open its data page and use Make one like this: it starts from this chart's numbers and takes yours.