Models
Qwen
SWE-bench Verified Performance vs Model Size

QwenX · Jul 22, 2025 · official

SWE-bench Verified Performance vs Model Size

Qwen's scatter plot drew 80.5K views on X: 0.3x its median post and #427 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

AI model performance and size comparison on SWE-bench

XData Scatter plot Qwen Coder All Qwen models Claude-Sonnet-4 Kimi-K2 GPT-4.1Qwen3-CoderDevstral-Small-2507Gemini-2.5-Pro-Preview-0506DeepSeek-R1-0528DeepSeek-V3-0324

Qwen: SWE-bench Verified Performance vs Model Size — Published by Qwen on X, Jul 22, 2025. Source: x.com

55/ 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.

#538 of 1,162 AI chart posts we hold · #40 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

Wide but thin: views at or above the AI chart median, engagement below it, scoring #538 of 1,162.

80.5K views is 0.29x the company median of 275K, ranking #39 of 55 Qwen posts.

On July 22, 2025, this post ranked #2 of 2 Qwen posts that day, below the other post.

Its save rate of 0.061% sits at the 39th percentile, below the 0.076% median for AI chart posts.

0.3xQwen's median post

80.5K views, where Qwen's typical post gets 275.3K.

0.27views per follower

80.5K views from an account with 296.6K followers.

3.6xthe median scatter plot post

Across 187 scatter plot posts we hold, the median gets 22.4K views.

2posts from Qwen that day

Part of a run of 2 posts on Jul 22, 2025. This one was #2 of 2 by views that day.

Public X numbers from our read on Oct 12, 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 #538 of 1,162

Views	80.5K	#427	top 37%
Likes	446	#478	top 41%
Engagement rate	0.62%	#697	bottom 40%
Save rate	0.061%	#711	bottom 39%

Among 55 Qwen posts

Score #40 of 55

Views	80.5K	#39	bottom 30%
Likes	446	#39	bottom 30%
Engagement rate	0.62%	#30	bottom 46%
Save rate	0.061%	#48	bottom 14%

Growth

One read so far

Views80.5K

Age at our read447 days

Views per day of life180views 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.

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 · Jul 22, 2025

Qwen's SWE-bench scatter ranks #538 of 1,162 AI chart posts

A 9-model scatter on SWE-bench performance drew 80.5K views but a 0.62% engagement rate.

What happened

Qwen posted a scatter plot on July 22, 2025, comparing 9 models on SWE-bench Verified. It was one of 2 posts that day, the other being Qwen3-Coder Benchmarks with 2.3M views.

The numbers

80.5K views, #427 of 1,162 AI chart posts. Engagement rate 0.62%, save rate 0.061%, #711 of 1,162 for saves.

The lesson

With 9 models in one scatter, the chart's save rate was 0.061%, below the 0.076% median. Fewer models might have focused attention.

What it means

At 0.29x the company median, this post underperformed Qwen's typical reach. Its rank of #40 of 55 Qwen posts shows a gap to the publisher's own norm.

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

Updates: what Qwen posted next

Data and API

11 points read off this chart

Estimated from the image 91%

Group	Value	Read
Qwen3-Coder	69.6 %	printed
Qwen3-Coder	67 %	printed
Claude-Sonnet-4	70.4 %	printed
Claude-Sonnet-4	68 %	printed
Kimi-K2	65.4 %	printed
GPT-4.1	54.6 %	printed
Gemini-2.5-Pro-Preview-0506	49 %	printed
DeepSeek-R1-0528	41.4 %	printed
DeepSeek-V3-0324	38.8 %	printed
Qwen3-235B-A22B	34.4 %	printed
Devstral-Small-2507	53.6 %	printed

Max plan · API

GET https://viral-chart.com/api/posts/4dd09db32559.json
GET https://viral-chart.com/api/charts/4dd09db32559.json
GET https://viral-chart.com/api/charts/4dd09db32559.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 4dd09db32559.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/4dd09db32559`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/4dd09db32559/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/4dd09db32559/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/4dd09db32559/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.