1. Models
  2. Anthropic
  3. Software engineering SWE-bench Verified
AnthropicX · May 22, 2025 · official

Software engineering SWE-bench Verified

Anthropic's bar chart drew 131.2K views on X: 0.3x its median post and #336 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Software engineering SWE-bench Verified accuracy comparison

XDataBar chartClaude 3.7 SonnetAll Anthropic modelsOpus 4Sonnet 4Sonnet 3.7OpenAI Codex-1OpenAI o3OpenAI GPT-4.1Gemini 2.5 Pro Preview (05-06)
Published by Anthropic on X, May 22, 2025. Source: x.com
62/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#412 of 1,162 AI chart posts we hold · #38 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

The post sits in the Reached and resonated quadrant, with a score rank of #412 of 1,162 AI chart posts.

Its 131K views sit at 0.30x Anthropic's 431K median, ranking #39 of 56 Anthropic posts.

The 0.046% save rate lands at the 26th percentile among AI chart posts, below the 0.076% median.

It ranked #2 of 2 posts from this account that day, against 2 posts total.

0.07views per follower

131.2K views from an account with 1.8M followers.

0.3xAnthropic's median post

131.2K views, where Anthropic's typical post gets 431K.

5.1xthe median bar chart post

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

2posts from Anthropic that day

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

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 #412 of 1,162

Views131.2K#336top 29%
Likes860#301top 26%
Engagement rate0.73%#581top 50%
Save rate0.046%#866bottom 26%

Among 56 Anthropic posts

Score #38 of 56

Views131.2K#39bottom 31%
Likes860#38bottom 33%
Engagement rate0.73%#18top 31%
Save rate0.046%#38bottom 33%

Growth

Our reads cover 28 hours

Views131.2K
Age at our read509 days
Views per day of life258views divided by days since it was posted
Gained between our reads+1views over 28 hours, about 1 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 · May 22, 2025

Anthropic posts SWE-bench Verified bar chart with 7 models

The chart shows SWE-bench Verified accuracy for Opus 4, Sonnet 4 and Sonnet 3.7 with and without parallel test-time compute.

What happened

Anthropic published a bar chart on May 22, 2025 comparing SWE-bench Verified accuracy across 7 models. It was one of 2 posts from the account that day, alongside a Claude 4 benchmarks post with 4.3M views.

The numbers

The post reached 131K views, ranking #336 of 1,162 AI chart posts. Its score of 62 ranked #412 of 1,162 AI chart posts and #38 of 56 Anthropic posts.

The lesson

A 7-model bar chart with a 0.046% save rate, at the 26th percentile among AI chart posts, shows that a dense comparison did not become a keepable reference. The 0.076% median save rate is the bar this chart type missed.

What it means

At #38 of 56 Anthropic posts by score and 0.30x the company's 431K median views, this chart post trails the account's own output. The 0.046% save rate against the 0.076% AI chart median leaves a gap in bookmark value.

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. Software Engineering Benchmark Comparison4.1M views
  2. SWE-bench Verified Accuracy159.7K views
  3. Plan usage limits159.7K views
  4. Software engineering SWE-bench Verified1.3M views
  5. Model Detection Performance Comparison24.1K views
  6. AI Model Benchmark Comparison7.8M views

Data and API

10 points read off this chart

Estimated from the image 97%
SeriesGroupValueRead
with parallel test-time computeOpus 479.4 %printed
without parallel test-time computeOpus 472.5 %printed
with parallel test-time computeSonnet 480.2 %printed
without parallel test-time computeSonnet 472.7 %printed
with parallel test-time computeSonnet 3.770.3 %printed
without parallel test-time computeSonnet 3.762.3 %printed
without parallel test-time computeOpenAI Codex-172.1 %printed
without parallel test-time computeOpenAI o369.1 %printed
without parallel test-time computeOpenAI GPT-4.154.6 %printed
without parallel test-time computeGemini 2.5 Pro63.2 %printed

Max plan · API

GET https://viral-chart.com/api/posts/2e221d19192d.json
GET https://viral-chart.com/api/charts/2e221d19192d.json
GET https://viral-chart.com/api/charts/2e221d19192d.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 2e221d19192d.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/2e221d19192dTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/2e221d19192d/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/2e221d19192d/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/2e221d19192d/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 3.7 Sonnet

Claude 3.7 Sonnet: Claude 4 benchmarks
OfficialX · AnthropicMay 22, 2025
Claude 4 benchmarks4.3M views · 20.5K likes
Data
Claude 3.7 Sonnet: Computer Use Scores Over Time
OfficialX · AnthropicFeb 17, 2026
Computer Use Scores Over Time615.6K views · 2K likes
Data
Claude 3.7 Sonnet: Claude Sonnet OSWorld and OSWorld-Verified scores over time
OfficialBlog · AnthropicFeb 17, 2026
Claude Sonnet OSWorld and OSWorld-Verified scores over time
Claude 3.7 Sonnet: Software engineering SWE-bench Verified
OfficialBlog · AnthropicAug 5, 2025
Software engineering SWE-bench Verified
Claude 3.7 Sonnet: Mistral Wins vs Competitor Wins for Coding
Blog · mistral.aiMay 7, 2025
Mistral Wins vs Competitor Wins for Coding

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 May 22, 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.