1. Models
  2. Anthropic
  3. Terminal-Bench 4.0: Accuracy vs Cost
AnthropicX · Sep 1, 2026 · official

Terminal-Bench 4.0: Accuracy vs Cost

Anthropic's line chart drew 483K views on X: 1.1x its median post and #153 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Terminal-Bench 4.0 accuracy vs cost comparison

Published by Anthropic on X, Sep 1, 2026. Source: x.com
70/ 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.

#220 of 1,162 AI chart posts we hold · #27 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 Wide but thin, with a score rank of #220 of 1,162 AI chart posts.

Its score of 70 sits at #220 of 1,162 AI chart posts and #27 of 56 Anthropic posts.

The post carries 4 charts, and every chart in the post shares the post's numbers.

Its save rate of 0.039% is 0.50x the AI chart median of 0.076%, at #930 of 1,162 AI chart posts.

4charts in this one post

The numbers belong to the post, so every chart in it shares them and it is ranked once.

6.6xthe median line chart post

Across 68 line chart posts we hold, the median gets 73.7K views.

0.25views per follower

483K views from an account with 1.9M followers.

bottom 20%save rate

0.039% 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 #220 of 1,162

Views483K#153top 13%
Likes2.5K#120top 10%
Engagement rate0.55%#771bottom 34%
Save rate0.039%#930bottom 20%

Among 56 Anthropic posts

Score #27 of 56

Views483K#27top 47%
Likes2.5K#24top 42%
Engagement rate0.55%#29bottom 49%
Save rate0.039%#41bottom 28%

Growth

Our reads cover 28 hours

Views483K
Age at our read42 days
Views per day of life11.5Kviews divided by days since it was posted
Gained between our reads+55views over 28 hours, about 48 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 · Sep 1, 2026

Anthropic posts Terminal-Bench 4.0 accuracy vs cost line chart

The September 1, 2026 post drew 483K views and a 0.55% engagement rate, with saves at 0.039%.

What happened

Anthropic published a Terminal-Bench 4.0 accuracy vs cost line chart on September 1, 2026, one of 4 charts in the post. That day the account also posted Claude Fable 5.1 Benchmark Comparison and Indexed cost of Fable usage.

The numbers

It reached 483K views, #153 of 1,162 AI chart posts, against a median of 39.9K among AI chart posts. Its score of 70 ranks #220 of 1,162 AI chart posts and #27 of 56 Anthropic posts.

The lesson

At 4 charts in one post, every chart shares the post's numbers, and this post's save rate of 0.039% sits at 0.50x the AI chart median. A line chart of 3 models drew 483K views but a 0.039% save rate, below the 0.076% median among AI chart posts.

What it means

For Anthropic, this post's #27 of 56 Anthropic posts sits below its own top chart posts, and its 0.039% save rate is 0.50x the AI chart median. The 483K views against a 39.9K median among AI chart posts show reach without the saves that mark a reference chart.

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

15 points read off this chart

Estimated from the image 79%
SeriesGroupValueRead
Mythos 5.1low41 %estimated
Mythos 5.1med47 %estimated
Mythos 5.1high56 %estimated
Mythos 5.1xhigh59 %estimated
Mythos 5.1max61 %estimated
Fable 5.1low40 %estimated
Fable 5.1med44 %estimated
Fable 5.1high49 %estimated
Fable 5.1xhigh51 %estimated
Fable 5.1max55 %estimated
Mythos 5low21 %estimated
Mythos 5med31.5 %estimated

Showing 12 of 15. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/ea1e8544d95e.json
GET https://viral-chart.com/api/charts/ea1e8544d95e.json
GET https://viral-chart.com/api/charts/ea1e8544d95e.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 ea1e8544d95e.

PathReturnsPlan
GET/api/v1/charts/ea1e8544d95eTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/ea1e8544d95e/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/ea1e8544d95e/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/ea1e8544d95e/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 Fable 5

More from Anthropic

Questions people ask

Where does this chart come from?

Anthropic published it on Sep 1, 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.