1. Models
  2. Z.ai
  3. LLM benchmark performance across nine tasks
Z.aiX · Aug 14, 2026 · official

LLM benchmark performance across nine tasks

Z.ai's small multiples drew 5.9M views on X: 29x its median post and #26 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

GLM-5.2 leads most benchmarks, with GPT-5.6 Sol leading in some.

XDataSmall multiplesGLM-5All Z.ai modelsKimi K3GLM-5.2Mythos / Fable 5GPT-5.6 Sol
Published by Z.ai on X, Aug 14, 2026. Source: x.com
77/ 100

ViralChart score

Wide but thin

More views than the median post but a lower engagement rate: many saw it, few acted. Common for big accounts.

#91 of 1,162 AI chart posts we hold · #9 of 34 Z.ai 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

It lands in the Wide but thin quadrant, at #91 of 1,162 AI chart posts.

Its 5.9M views are 29x Z.ai's median post, ranking #3 of 34 Z.ai posts by views.

At 36 views per follower, it sits in the top decile, the 99th percentile among posts with known followers.

A score of 77 places it at #91 of 1,162 AI chart posts and #9 of 34 Z.ai posts.

219xthe median small multiples post

Across 43 small multiples posts we hold, the median gets 27K views.

29xZ.ai's median post

5.9M views, where Z.ai's typical post gets 201.2K.

36views per follower

5.9M views from an account with 165.3K followers.

bottom 19%engagement rate

0.41% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 34 from Z.ai.

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 #91 of 1,162

Views5.9M#26top 2%
Likes19.3K#15top 1%
Engagement rate0.41%#945bottom 19%
Save rate0.055%#760bottom 35%

Among 34 Z.ai posts

Score #9 of 34

Views5.9M#3top 7%
Likes19.3K#2top 4%
Engagement rate0.41%#28bottom 19%
Save rate0.055%#24bottom 31%

Growth

Our reads cover 27 hours

Views5.9M
Age at our read61 days
Views per day of life97.7Kviews divided by days since it was posted
Gained between our reads+785views over 27 hours, about 701 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.

Z.ai'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 14, 2026 · Lead story

Z.ai posts GLM-5.2 benchmark small multiples

The August 14, 2026 post drew 5.9M views and 19.3K likes, a 0.41% engagement rate and a 0.055% save rate.

What happened

Z.ai published one small multiples chart on August 14, 2026, covering LLM benchmark performance across nine tasks. It was the account's only post that day.

The numbers

It reached 5.9M views, #26 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 77 ranks #91 of 1,162 AI chart posts and #9 of 34 Z.ai posts.

The lesson

One small multiples chart with 4 models shown drew 5.9M views but a 0.41% engagement rate and a 0.055% save rate. The chart shows printed values from 4.6 to 66.9 across nine tasks.

What it means

At #9 of 34 Z.ai posts by score and #3 of 34 by views, this post sits far above the account's 201K median views. Its 0.41% engagement rate against 5.9M views is the gap that keeps it out of a higher quadrant.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what Z.ai posted next

  1. Frontier models intelligence versus cost per task532.1K views
  2. LLM performance across six benchmarks7M views
  3. Agentic Code Bench performance by effort level201.2K views
  4. LLM Performance on Harvey LAB533.2K views

Data and API

47 points read off this chart

Partly publisher's numbers 94%
SeriesGroupValueRead
GLM-5.3Terminal Bench 3.028.3printed
GLM-5.2Terminal Bench 3.04.6printed
Kimi K3Terminal Bench 3.017.4printed
Mythos / Fable 5Terminal Bench 3.033.7printed
GPT-5.6 SolTerminal Bench 3.034.6printed
GLM-5.3DeepSWE66.9printed
GLM-5.2DeepSWE46.2printed
Kimi K3DeepSWE67.5printed
Mythos / Fable 5DeepSWE69.7printed
GPT-5.6 SolDeepSWE72.7printed
GLM-5.3Agents' Last Exam28.5printed
GLM-5.2Agents' Last Exam23.8printed

Showing 12 of 47. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/25bc551a8400.json
GET https://viral-chart.com/api/charts/25bc551a8400.json
GET https://viral-chart.com/api/charts/25bc551a8400.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI 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 25bc551a8400.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/25bc551a8400Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/25bc551a8400/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/25bc551a8400/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/25bc551a8400/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

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: Coding Evaluation
OfficialX · Z.aiMar 27, 2026
Coding Evaluation1.3M views · 5.4K likes
Data
GLM-5: Frontier models intelligence versus cost per task
OfficialX · Z.aiAug 18, 2026
Frontier models intelligence versus cost per task532.1K views · 3.8K likes
Data
GLM-5: LLM Performance on 8 Benchmarks
OfficialX · Z.aiJun 16, 2026
LLM Performance on 8 Benchmarks253.9K views · 1.2K likes
Data
GLM-5: Agentic Code Bench performance by effort level
OfficialX · Z.aiAug 26, 2026
Agentic Code Bench performance by effort level201.2K views · 1K likes
Data

More from Z.ai

GLM-5.1: Coding Performance Evaluation
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
GLM-4: LLM Performance on 8 Benchmarks
OfficialX · Z.aiFeb 11, 2026
LLM Performance on 8 Benchmarks1.5M views · 5.3K likes
Data
GLM-4: LLM Benchmarks Performance Evaluation
OfficialX · Z.aiDec 22, 2025
LLM Benchmarks Performance Evaluation1.4M views · 3.3K likes
Data
GLM-4: LLM Performance Evaluation: Agentic, Reasoning, and Coding Benchmarks
OfficialX · Z.aiJul 28, 2025
LLM Performance Evaluation: Agentic, Reasoning, and Coding Benchmarks1.3M views · 3K likes
Data
GLM-4: LLM Performance on 8 Benchmarks
OfficialX · Z.aiSep 30, 2025
LLM Performance on 8 Benchmarks907.8K views · 1.8K likes
Data

Questions people ask

Where does this chart come from?

Z.ai published it on Aug 14, 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.