Models
Z.ai
QPS Optimization Iterations

Z.aiX · Apr 7, 2026 · official

QPS Optimization Iterations

Q: Where does this chart come from?

Z.ai published it on Apr 7, 2026 on X (x.com). We keep it here, with the publisher and date credited as text, so you can study it without leaving.

Q: 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.

Z.ai's line chart drew 81.7K views on X: 0.4x its median post and #424 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

QPS improvement over optimization iterations with key milestones

XData Line chart GLM-5.1 All Z.ai modelsNo ImprovementImproved Debug RunNew Best QPSRecall < 95%Frontier

Z.ai: QPS Optimization Iterations — Published by Z.ai on X, Apr 7, 2026. Source: x.com

58/ 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.

#481 of 1,162 AI chart posts we hold · #22 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

The post sits in the Wide but thin quadrant, with a score rank of #481 of 1,162 AI chart posts.

Its 81.7K views rank #3 of 3 Z.ai posts from that day, with 3 posts from this account that day.

At 0.41x the company median of 201K views, this post ranks #21 of 34 Z.ai posts by views.

At 0.50 views per follower against a 0.20 median, it sits at 2.5x that median and the 66th percentile.

0.4xZ.ai's median post

81.7K views, where Z.ai's typical post gets 201.2K.

3posts from Z.ai that day

Part of a run of 3 posts on Apr 7, 2026. This one was #3 of 3 by views that day.

0.49views per follower

81.7K views from an account with 165.3K followers.

bottom 36%engagement rate

0.57% 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 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 #481 of 1,162

Views	81.7K	#424	top 36%
Likes	449	#474	top 41%
Engagement rate	0.57%	#742	bottom 36%
Save rate	0.098%	#439	top 38%

Among 34 Z.ai posts

Score #22 of 34

Views	81.7K	#21	bottom 40%
Likes	449	#23	bottom 34%
Engagement rate	0.57%	#16	top 46%
Save rate	0.098%	#11	top 31%

Growth

One read so far

Views81.7K

Age at our read188 days

Views per day of life434views 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 · Apr 7, 2026

Z.ai posts QPS optimization line chart

The chart shows QPS across optimization iterations, and the post reached 81.7K views with a 0.57% engagement rate.

What happened

Z.ai posted a line chart on April 7, 2026, titled QPS Optimization Iterations. It came with 2 other posts from this account that day: Coding Performance Evaluation and Agentic Coding: SWE-Bench Pro.

The numbers

It reached 81.7K views, ranking #424 of 1,162 AI chart posts by views and #21 of 34 Z.ai posts. Its score rank is #481 of 1,162 AI chart posts.

The lesson

The chart shows QPS values from 6400 to 20300 across 5 models, and the post drew 449 likes against 81.7K views. A 0.098% save rate against a 0.57% engagement rate shows saves lagged likes.

What it means

At #22 of 34 Z.ai posts by score, this post trails the company median of 201K views by 0.41x. For a publisher whose posts reach 81.7K views, the 0.098% save rate against a 0.57% engagement rate marks a wide but thin result.

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

Data and API

7 points read off this chart

Estimated from the image 50%

Group	Value	Read
IVF Cutover	6400 QPS	printed
IVF Cutover	10400 QPS	printed
Two-stage Search	13400 QPS	printed
Nested Parallelism Removed	15500 QPS	printed
Two-level Routing	18400 QPS	printed
Budget Tri	20300 QPS	printed
u8 Routing + Probe	21500 QPS	printed

Max plan · API

GET https://viral-chart.com/api/posts/2631bdfc4a5b.json
GET https://viral-chart.com/api/charts/2631bdfc4a5b.json
GET https://viral-chart.com/api/charts/2631bdfc4a5b.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 2631bdfc4a5b.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/2631bdfc4a5b`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/2631bdfc4a5b/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/2631bdfc4a5b/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/2631bdfc4a5b/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-5.1

OfficialX · Z.aiApr 7, 2026

Coding Performance Evaluation4.4M views · 10.7K likes

Data

OfficialX · Z.aiApr 7, 2026

Agentic Coding: SWE-Bench Pro201.3K views · 953 likes

Data

X · @arenaMay 26, 2026

Code Arena Overall Ranking457.1K views · 1.3K likes

Data

GLM-5.1: Intelligence vs. Cost to Run Artificial Analysis Index

X · @ArtificialAnlysApr 8, 2026

Intelligence vs. Cost to Run Artificial Analysis Index1.3K views · 10 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-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

OfficialX · Z.aiDec 22, 2025

LLM Benchmarks Performance Evaluation1.4M views · 3.3K likes

Data

Questions people ask

Where does this chart come from?

Z.ai published it on Apr 7, 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.