Models
Qwen
AI Model Benchmark Performance Comparison

QwenX · May 21, 2026 · official

AI Model Benchmark Performance Comparison

Qwen's small multiples drew 1.2M views on X: 4.2x its median post and #97 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

AI model performance across multiple benchmarks

XData Small multiples Qwen app and Qwen Chat All Qwen models GLM-5.1Qwen3.7-MaxQwen3.6-PlusDS-V4-Pro MaxKimi K2.6Claude Opus-4.6 Max

Qwen: AI Model Benchmark Performance Comparison — Published by Qwen on X, May 21, 2026. Source: x.com

78/ 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.

#75 of 1,162 AI chart posts we hold · #24 of 55 Qwen 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, at #75 of 1,162 AI chart posts by score.

Its score of 78 lands at #75 of 1,162 AI chart posts and #24 of 55 Qwen posts.

At 3.91 views per follower, it sits in the top decile, against a median of 0.20 across posts with known followers.

Its 1.2M views are 4.2x the company median of 275K, ranking #12 of 55 Qwen posts by views.

43xthe median small multiples post

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

4.2xQwen's median post

1.2M views, where Qwen's typical post gets 275.3K.

3.91views per follower

1.2M views from an account with 296.6K followers.

3posts from Qwen that day

Part of a run of 3 posts on May 21, 2026. This one was #1 of 3 by views that day.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 55 from Qwen.

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 #75 of 1,162

Views	1.2M	#97	top 8%
Likes	4.9K	#67	top 6%
Engagement rate	0.52%	#810	bottom 30%
Save rate	0.090%	#499	top 43%

Among 55 Qwen posts

Score #24 of 55

Views	1.2M	#12	top 21%
Likes	4.9K	#14	top 25%
Engagement rate	0.52%	#37	bottom 34%
Save rate	0.090%	#40	bottom 28%

Growth

Our reads cover 3 days

Views1.2M

Age at our read145 days

Views per day of life8Kviews divided by days since it was posted

Gained between our reads+91views over 3 days, about 32 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.

Qwen'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 · May 21, 2026

Qwen posts small multiples of AI model benchmark scores

A 1.2M-view chart of benchmark scores lands in the Wide but thin quadrant, with a 0.52% engagement rate.

What happened

Qwen, an official account, posted a small multiples chart on May 21, 2026, showing AI model performance across multiple benchmarks. That day the account posted 3 posts, including ones on Average Ranking vs. Environment Scaling and Cross-Harness Generalization Performance.

The numbers

The post reached 1.2M views, ranking #97 of 1,162 AI chart posts by views and #12 of 55 Qwen posts. Its score of 78 ranks #75 of 1,162 AI chart posts.

The lesson

At 0.090%, the save rate trails the 0.52% engagement rate, so the small multiples chart drew views without matching saves. A 6-model comparison at 3.91 views per follower shows reach can outrun what readers keep.

What it means

At #24 of 55 Qwen posts by score, this chart sits below the account's own top ranks despite 4.2x the company median views. The 1.2M views against a 0.52% engagement rate mark a wide but thin result for this publisher.

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

Updates: what Qwen posted next

Data and API

78 points read off this chart

Estimated from the image 89%

Series	Group	Value	Read
Qwen3.7-Max	Terminal-Bench 2.0	69.7 score	printed
Qwen3.6-Plus	Terminal-Bench 2.0	61.6 score	printed
DS-V4-Pro Max	Terminal-Bench 2.0	67.9 score	printed
GLM-5.1	Terminal-Bench 2.0	63.5 score	printed
Kimi K2.6	Terminal-Bench 2.0	66.7 score	printed
Claude Opus-4.6 Max	Terminal-Bench 2.0	65.4 score	printed
Qwen3.7-Max	SWE-bench Pro	60.6 score	printed
Qwen3.6-Plus	SWE-bench Pro	56.6 score	printed
DS-V4-Pro Max	SWE-bench Pro	59 score	printed
GLM-5.1	SWE-bench Pro	58.8 score	printed
Kimi K2.6	SWE-bench Pro	59.5 score	printed
Claude Opus-4.6 Max	SWE-bench Pro	57.3 score	printed

Showing 12 of 78. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/707f29fceed5.json
GET https://viral-chart.com/api/charts/707f29fceed5.json
GET https://viral-chart.com/api/charts/707f29fceed5.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 707f29fceed5.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/707f29fceed5`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/707f29fceed5/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/707f29fceed5/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/707f29fceed5/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.