1. Models
  2. Anthropic
  3. Opus 4.8 benchmark comparison
AnthropicX · May 28, 2026 · official

Opus 4.8 benchmark comparison

Anthropic's table chart drew 15.5M views on X: 36x its median post and #6 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Opus 4.8 benchmark performance comparison

Published by Anthropic on X, May 28, 2026. Source: x.com
79/ 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.

#57 of 1,162 AI chart posts we hold · #7 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 sits in the Wide but thin quadrant, at #57 of 1,162 AI chart posts by score.

Its 15.5M views are 36x Anthropic's 431K median, the #1 of 56 Anthropic posts by views.

At 8.16 views per follower against a 0.20 median, it sits in the 96th percentile and the top decile.

A score of 79 places it #57 of 1,162 AI chart posts and #7 of 56 Anthropic posts.

36xAnthropic's median post

15.5M views, where Anthropic's typical post gets 431K.

116xthe median table chart post

Across 95 table chart posts we hold, the median gets 133.2K views.

8.15views per follower

15.5M views from an account with 1.9M followers.

bottom 28%save rate

0.050% 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 #57 of 1,162

Views15.5M#6top 1%
Likes66.3K#2top 1%
Engagement rate0.54%#790bottom 32%
Save rate0.050%#832bottom 28%

Among 56 Anthropic posts

Score #7 of 56

Views15.5M#1top 1%
Likes66.3K#2top 3%
Engagement rate0.54%#31bottom 46%
Save rate0.050%#34bottom 40%

Growth

Our reads cover 26 hours

Views15.5M
Age at our read138 days
Views per day of life112.3Kviews divided by days since it was posted
Gained between our reads+706views over 26 hours, about 649 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 28, 2026 · Lead story

Anthropic posts Opus 4.8 benchmark table chart

The table chart reached 15.5M views on a 0.54% engagement rate, landing in the Wide but thin quadrant.

What happened

Anthropic published a table chart comparing Opus 4.8 benchmark performance on May 28, 2026. It was the account's only post that day.

The numbers

The post drew 15.5M views, #6 of 1,162 AI chart posts, and ranked #1 of 56 Anthropic posts by views. Its score of 79 ranked #57 of 1,162 AI chart posts.

The lesson

A table chart with 4 models shown drew 15.5M views but a 0.54% engagement rate and a 0.050% save rate, both below the AI chart medians. The 1 chart in this post carried the reach while saves stayed thin.

What it means

At #7 of 56 Anthropic posts by score, this chart sits well behind its #1 of 56 rank by views. The 36x gap over Anthropic's 431K median views came with a 0.54% engagement rate below the AI chart median.

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

Data and API

28 points read off this chart

Estimated from the image 95%
SeriesGroupValueRead
Opus 4.8Agentic coding (SWE-Bench Pro)69.2printed
Opus 4.7Agentic coding (SWE-Bench Pro)64.3printed
GPT-5.5Agentic coding (SWE-Bench Pro)58.6printed
Gemini 3.1 ProAgentic coding (SWE-Bench Pro)54.2printed
Opus 4.8Agentic terminal coding (Terminal-Bench 2.1)74.6printed
Opus 4.7Agentic terminal coding (Terminal-Bench 2.1)66.1printed
GPT-5.5Agentic terminal coding (Terminal-Bench 2.1)78.2printed
Gemini 3.1 ProAgentic terminal coding (Terminal-Bench 2.1)70.3printed
Opus 4.8Multidisciplinary reasoning (Humanity's Last Exam) - no tools49.8printed
Opus 4.7Multidisciplinary reasoning (Humanity's Last Exam) - no tools46.9printed
GPT-5.5Multidisciplinary reasoning (Humanity's Last Exam) - no tools41.4printed
Gemini 3.1 ProMultidisciplinary reasoning (Humanity's Last Exam) - no tools44.4printed

Showing 12 of 28. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/e457fc8922a1.json
GET https://viral-chart.com/api/charts/e457fc8922a1.json
GET https://viral-chart.com/api/charts/e457fc8922a1.skill.md

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 e457fc8922a1.

PathReturnsPlan
GET/api/v1/charts/e457fc8922a1Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/e457fc8922a1/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/e457fc8922a1/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/e457fc8922a1/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 Opus 4

More from Anthropic

Questions people ask

Where does this chart come from?

Anthropic published it on May 28, 2026 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.