1. Models
  2. Anthropic
  3. Software engineering SWE-bench Verified
AnthropicX · Oct 15, 2025 · official

Software engineering SWE-bench Verified

Anthropic's bar chart drew 1.3M views on X: 3.1x its median post and #89 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Software engineering benchmark accuracy comparison

XDataBar chartClaude Haiku 4All Anthropic modelsGPT-5Gemini 2.5 ProSonnet 4.5Haiku 4.5Sonnet 4GPT-5 Codex
Published by Anthropic on X, Oct 15, 2025. 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.

#74 of 1,162 AI chart posts we hold · #9 of 56 Anthropic 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

It lands in the Wide but thin quadrant, with a score rank of #74 of 1,162 AI chart posts.

Its score of 78 sits at #74 of 1,162 AI chart posts and #9 of 56 Anthropic posts.

The post's 1.3M views are 3.1x Anthropic's median of 431K, ranking #18 of 56 Anthropic posts.

The bar chart's 1.3M views are 52x the 25.6K median for the 241 chart posts of this type.

52xthe median bar chart post

Across 241 bar chart posts we hold, the median gets 25.6K views.

3.1xAnthropic's median post

1.3M views, where Anthropic's typical post gets 431K.

0.70views per follower

1.3M views from an account with 1.9M followers.

bottom 42%save rate

0.064% of viewers bookmarked it to come back to. The median post gets 0.076%.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 56 from Anthropic.

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 #74 of 1,162

Views1.3M#89top 8%
Likes6.9K#45top 4%
Engagement rate0.64%#671bottom 42%
Save rate0.064%#676bottom 42%

Among 56 Anthropic posts

Score #9 of 56

Views1.3M#18top 31%
Likes6.9K#13top 22%
Engagement rate0.64%#22top 38%
Save rate0.064%#19top 33%

Growth

Our reads cover 27 hours

Views1.3M
Age at our read363 days
Views per day of life3.7Kviews divided by days since it was posted
Gained between our reads+33views over 27 hours, about 30 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.

Anthropic'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 · Oct 15, 2025

Anthropic's SWE-bench bar chart draws 1.3M views

The October 15, 2025 bar chart reached 1.3M views, 3.1x Anthropic's median, while its 0.64% engagement rate fell below the 0.79% median for this chart type.

What happened

Anthropic posted a bar chart on October 15, 2025, comparing software engineering benchmark accuracy. It was the account's only post that day.

The numbers

The post drew 1.3M views, ranking #89 of 1,162 AI chart posts and #18 of 56 Anthropic posts. Its score of 78 ranked #74 of 1,162 AI chart posts.

The lesson

A bar chart with 6 models drew 1.3M views, 52x the 25.6K median for the 241 chart posts of this type. Its 0.64% engagement rate still trailed the 0.79% median for that type.

What it means

At #9 of 56 Anthropic posts by score, this chart sits below the account's top posts despite 3.1x its median views. The 0.64% engagement rate against the 0.79% type median shows wide reach with below-median engagement.

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

Updates: what Anthropic posted next

  1. Model Detection Performance Comparison24.1K views
  2. AI Model Benchmark Comparison7.8M views
  3. Software engineering SWE-bench Verified2M views
  4. Estimating Claude's productivity impacts225.8K views
  5. AI Performance Metrics Comparison6.3K views
  6. AI Model Benchmark Comparison751.8K views

Data and API

6 points read off this chart

Estimated from the image 97%
SeriesGroupValueRead
Sonnet 4.577.2 %printed
Haiku 4.573.3 %printed
Sonnet 472.7 %printed
GPT-5 Codex74.5 %printed
GPT-572.8 %printed
Gemini 2.5 Pro67.2 %printed

Max plan · API

GET https://viral-chart.com/api/posts/34bf88e62a13.json
GET https://viral-chart.com/api/charts/34bf88e62a13.json
GET https://viral-chart.com/api/charts/34bf88e62a13.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 34bf88e62a13.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/34bf88e62a13Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/34bf88e62a13/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/34bf88e62a13/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/34bf88e62a13/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 Claude Haiku 4

Claude Haiku 4: Agentic computer use performance by effort level
OfficialX · AnthropicOct 7, 2026
Agentic computer use performance by effort level270.3K views · 2.4K likes
Data
Claude Haiku 4: Real-world knowledge GDPval-AA tasks by effort level
OfficialX · AnthropicOct 7, 2026
Real-world knowledge GDPval-AA tasks by effort level270.3K views · 2.4K likes
Data
Claude Haiku 4: Multidisciplinary reasoning by effort level
OfficialX · AnthropicOct 7, 2026
Multidisciplinary reasoning by effort level270.3K views · 2.4K likes
Data
Claude Haiku 4: Overall misaligned behavior
OfficialBlog · AnthropicFeb 5, 2026
Overall misaligned behavior
Claude Haiku 4: Concerning behavior
OfficialBlog · AnthropicNov 24, 2025
Concerning behavior
Claude Haiku 4: Susceptibility to prompt-injection style attacks
OfficialBlog · AnthropicNov 24, 2025
Susceptibility to prompt-injection style attacks

More from Anthropic

Anthropic stacked bar chart: Firefox Security Vulnerabilities4.7x
Anthropic·Mar 2026
Firefox Security Vulnerabilities
3.2M views14.8K likes0.5% eng.
Data
Anthropic line chart: US GDP AI scenarios0.4x
Anthropic·Sep 2026
US GDP AI scenarios
856.3K views1.2K likes0.2% eng.
Data
Anthropic bar chart: RL reward hacking risks1.0x
Anthropic·Sep 2026
RL reward hacking risks
806.5K views3.2K likes0.5% eng.
Data
Claude Opus 4: Opus 4.8 benchmark comparison
OfficialX · AnthropicMay 28, 2026
Opus 4.8 benchmark comparison15.5M views · 66.3K likes
Data
Claude Mythos: Opus 4.7 Benchmark Comparison
OfficialX · AnthropicApr 16, 2026
Opus 4.7 Benchmark Comparison14.1M views · 79.6K likes
Data
Claude agents and computer use: AI Model Benchmark Comparison
OfficialX · AnthropicNov 24, 2025
AI Model Benchmark Comparison7.8M views · 18.8K likes
Data
Claude Fable 5: Claude Mythos 5 and Fable 5 Benchmark Comparison
OfficialX · AnthropicJun 9, 2026
Claude Mythos 5 and Fable 5 Benchmark Comparison6.3M views · 15.4K likes
Data
Claude Fable 5: AI Model Benchmark Comparison
OfficialX · AnthropicJul 24, 2026
AI Model Benchmark Comparison5.8M views · 10.7K likes
Data
Claude Opus 4.6: Long context MRCR v2 retrieval
OfficialX · AnthropicMar 13, 2026
Long context MRCR v2 retrieval5.7M views · 24.6K likes
Data

Questions people ask

Where does this chart come from?

Anthropic published it on Oct 15, 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.