1. Models
  2. Z.ai
  3. GLM-4.5's Experience with Agentic Coding in Real-world Devel
Z.aiX · Jul 28, 2025 · official

GLM-4.5's Experience with Agentic Coding in Real-world Development

Z.ai's stacked bar chart drew 38K views on X: 0.2x its median post and #591 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

GLM-4.5 performance in agentic coding scenarios

XDataStacked bar chartGLM-4All Z.ai modelsKimi K2GLM-4.5Claude 4 SonnetQwen3-Coder
Published by Z.ai on X, Jul 28, 2025. Source: x.com
65/ 100

ViralChart score

Small but loved

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

#338 of 1,162 AI chart posts we hold · #19 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

In the Small but loved quadrant, this post ranks #338 of 1,162 AI chart posts.

At 38K views, this post sits at 0.19x Z.ai's median of 201K, ranking #26 of 34 Z.ai posts.

Its 0.24% save rate lands in the 94th percentile among AI chart posts, against a 0.076% median.

A score of 65 puts it at #338 of 1,162 AI chart posts and #19 of 34 Z.ai posts.

0.2xZ.ai's median post

38K views, where Z.ai's typical post gets 201.2K.

top 6%save rate

0.245% of viewers bookmarked it to come back to. The median post gets 0.076%.

top 10%engagement rate

1.38% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.23views per follower

38K views from an account with 165.3K followers.

Public X numbers from our read on Oct 12, 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 #338 of 1,162

Views38K#591bottom 49%
Likes460#465top 40%
Engagement rate1.38%#122top 10%
Save rate0.245%#68top 6%

Among 34 Z.ai posts

Score #19 of 34

Views38K#26bottom 25%
Likes460#22bottom 37%
Engagement rate1.38%#3top 7%
Save rate0.245%#3top 7%

Growth

One read so far

Views38K
Age at our read441 days
Views per day of life86views 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.

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 · Jul 28, 2025

Z.ai posts GLM-4.5 agentic coding stacked bar chart

The chart shows win, tie and lose rates for GLM-4.5 against Claude 4 Sonnet and Kimi K2, with saves in the top decile.

What happened

Z.ai published a stacked bar chart on July 28, 2025, titled GLM-4.5's Experience with Agentic Coding in Real-world Development. It came with 2 other posts from the account that day, including one on LLM performance evaluation that reached 1.3M views.

The numbers

The post reached 38K views, ranking #591 of 1,162 AI chart posts by views. Its score of 65 ranks #338 of 1,162 AI chart posts and #19 of 34 Z.ai posts.

The lesson

A 0.24% save rate, in the 94th percentile among AI chart posts, shows readers bookmark this stacked bar chart at more than 3x the 0.076% median. The chart's win, tie and lose values for GLM-4.5 against Claude 4 Sonnet and Kimi K2 are what people keep.

What it means

At #26 of 34 Z.ai posts by views, this chart reaches 0.19x the company's 201K median, while its save rate sits in the top decile. The gap between 38K views and the 39.9K median among AI chart posts is narrow, but the score rank of #338 of 1,162 shows the engagement carries it.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what Z.ai posted next

  1. GLM-4.5 ARC Benchmark Performance153.3K views
  2. Open-source LLMs Benchmarks299.8K views
  3. Accuracy Comparison60.3K views
  4. CC-Bench: GLM-4.5's Experience with Agentic Coding in Real-world32.8K views
  5. LLM Performance on 8 Benchmarks907.8K views
  6. GLM-4.6 Agentic Coding Performance vs Competitors13.7K views

Data and API

9 points read off this chart

Estimated from the image 97%
SeriesGroupValueRead
WinGLM-4.5 vs Claude 4 Sonnet40.4 %printed
TieGLM-4.5 vs Claude 4 Sonnet9.6 %printed
LoseGLM-4.5 vs Claude 4 Sonnet50 %printed
WinGLM-4.5 vs Kimi K253.9 %printed
TieGLM-4.5 vs Kimi K217.3 %printed
LoseGLM-4.5 vs Kimi K228.8 %printed
WinGLM-4.5 vs Qwen3-Coder80.8 %printed
TieGLM-4.5 vs Qwen3-Coder7.7 %printed
LoseGLM-4.5 vs Qwen3-Coder11.5 %printed

Max plan · API

GET https://viral-chart.com/api/posts/df8011b7a3c7.json
GET https://viral-chart.com/api/charts/df8011b7a3c7.json
GET https://viral-chart.com/api/charts/df8011b7a3c7.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 df8011b7a3c7.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/df8011b7a3c7Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/df8011b7a3c7/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/df8011b7a3c7/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/df8011b7a3c7/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-4

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
GLM-4: Open-source LLMs Benchmarks Comparison
OfficialX · Z.aiDec 8, 2025
Open-source LLMs Benchmarks Comparison364.4K views · 1.8K 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
GLM-5.1: Coding Performance Evaluation
OfficialX · Z.aiApr 7, 2026
Coding Performance Evaluation4.4M views · 10.7K likes
Data
GLM-5: Coding Evaluation
OfficialX · Z.aiMar 27, 2026
Coding Evaluation1.3M views · 5.4K likes
Data
GLM-5.3: LLM Performance on Harvey LAB
OfficialX · Z.aiOct 12, 2026
LLM Performance on Harvey LAB533.2K views · 6.3K likes
Data

Questions people ask

Where does this chart come from?

Z.ai published it on Jul 28, 2025 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.