Models
Google
DeepSWE v1.1 Model Cost vs Performance

@SemiAnalysis_X · Sep 8, 2026

DeepSWE v1.1 Model Cost vs Performance

@SemiAnalysis_'s scatter plot drew 31.5K views on X: 0.8x @semianalysis_'s median post and #635 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Model efficiency and cost comparison for DeepSWE v1.1

XData Scatter plot Gemini 3 All Google models claude-opus-5 glm-5.3 kimi-k3 deepseek-v4-progemini-3.8-flashgrok-4.6gemini-3.7-flashgpt-5.6-sol

@SemiAnalysis_: DeepSWE v1.1 Model Cost vs Performance — Published by @SemiAnalysis_ on X, Sep 8, 2026. Source: x.com

50/ 100

ViralChart score

Small but loved

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

#625 of 1,162 AI chart posts we hold · #12 of 24 @semianalysis_ 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 Small but loved quadrant, at #625 of 1,162 AI chart posts.

Its #2 of 2 rank by views that day sits below the other post from @SemiAnalysis_ on September 8, 2026.

The 0.80% engagement rate lands at the 58th percentile among AI chart posts, above the 0.73% median.

At 31.5K views against a 40.3K company median, the ratio is 0.78x, ranked #14 of 24 @SemiAnalysis_ posts.

2posts from @semianalysis_ that day

Part of a run of 2 posts on Sep 8, 2026. This one was #2 of 2 by views that day.

0.8x@semianalysis_'s median post

31.5K views, where @semianalysis_'s typical post gets 40.3K.

1.4xthe median scatter plot post

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

top 42%engagement rate

0.80% 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 24 from @semianalysis_.

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 #625 of 1,162

Views	31.5K	#635	bottom 45%
Likes	249	#608	bottom 48%
Engagement rate	0.80%	#494	top 42%
Save rate	0.089%	#503	top 43%

Among 24 @semianalysis_ posts

Score #12 of 24

Views	31.5K	#14	bottom 44%
Likes	249	#11	top 44%
Engagement rate	0.80%	#4	top 15%
Save rate	0.089%	#15	bottom 40%

Growth

One read so far

Views31.5K

Age at our read35 days

Views per day of life902views 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.

@semianalysis_'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 · Sep 8, 2026

@SemiAnalysis_ scatter plot on DeepSWE v1.1 cost and performance

A 10-model scatter plot from @SemiAnalysis_ drew 31.5K views and a 0.80% engagement rate, above the 0.73% median among AI chart posts.

What happened

@SemiAnalysis_ posted a scatter plot on DeepSWE v1.1 model cost versus performance on September 8, 2026. It was 1 of 2 posts from the account that day, alongside a post on Google bench 2.1 vs 4.0 performance.

The numbers

The post reached 31.5K views, ranked #635 of 1,162 AI chart posts and #14 of 24 @SemiAnalysis_ posts. Its 0.80% engagement rate ranked #494 of 1,162 AI chart posts.

The lesson

A 10-model scatter plot at a 0.80% engagement rate against a 0.73% median among AI chart posts shows that dense model comparisons can hold engagement above the median even when views land below it.

What it means

At #12 of 24 @SemiAnalysis_ posts by score and 0.78x the company median views, this chart post trails the account's own reach while its 0.80% engagement rate sits above the 0.62% median for this account.

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

Updates: what @semianalysis_ posted next

Data and API

10 points read off this chart

Estimated from the image 75%

Group	Value	Read
claude-opus-5	72 %	printed
grok-4.6	67.5 %	printed
kimi-k3	67 %	estimated
glm-5.3	70 %	printed
gemini-3.8-flash	73 %	estimated
deepseek-v4-pro	66 %	printed
gemini-3.7-flash	68 %	estimated
gpt-5.6-sol	60.5 %	printed
qwen3.8-max	55 %	printed
muse-spark-1.2	54.5 %	printed

Max plan · API

GET https://viral-chart.com/api/posts/5f27d2e33af2.json
GET https://viral-chart.com/api/charts/5f27d2e33af2.json
GET https://viral-chart.com/api/charts/5f27d2e33af2.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 5f27d2e33af2.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/5f27d2e33af2`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/5f27d2e33af2/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/5f27d2e33af2/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/5f27d2e33af2/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 Gemini 3

Gemini 3: Codeforces Coding and Algorithms

OfficialX · GoogleFeb 12, 2026

Codeforces Coding and Algorithms695.4K views · 1.9K likes