Models
Anthropic
Agentic coding runs on cache

@SemiAnalysis_X · Jul 8, 2026

Agentic coding runs on cache

@SemiAnalysis_'s benchmark bar chart drew 51.3K views on X: 1.3x @semianalysis_'s median post and #528 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

XData Benchmark bar chart Claude Code All Anthropic modelsHaiku 4.5Sonnet 4.6Opus 4.6Opus 4.7Fable 5

@SemiAnalysis_: Agentic coding runs on cache — Published by @SemiAnalysis_ on X, Jul 8, 2026. Source: x.com

57/ 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.

#511 of 1,162 AI chart posts we hold · #9 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

It sits in the Wide but thin quadrant, at #511 of 1,162 AI chart posts.

Its 0.24% save rate sits in the 94th percentile among AI chart posts, against a 0.076% median.

At 51.3K views it runs 1.3x @SemiAnalysis_'s 40.3K company median, #10 of 24 @SemiAnalysis_ posts.

A score of 57 lands at #511 of 1,162 AI chart posts and #9 of 24 @SemiAnalysis_ posts.

top 6%save rate

0.236% of viewers bookmarked it to come back to. The median post gets 0.076%.

bottom 40%engagement rate

0.62% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

1.3x@semianalysis_'s median post

51.3K views, where @semianalysis_'s typical post gets 40.3K.

1.2xthe median benchmark bar chart post

Across 215 benchmark bar chart posts we hold, the median gets 44.4K views.

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 #511 of 1,162

Views	51.3K	#528	top 45%
Likes	286	#586	bottom 50%
Engagement rate	0.62%	#698	bottom 40%
Save rate	0.236%	#72	top 6%

Among 24 @semianalysis_ posts

Score #9 of 24

Views	51.3K	#10	top 40%
Likes	286	#9	top 35%
Engagement rate	0.62%	#14	bottom 44%
Save rate	0.236%	#2	top 6%

Growth

One read so far

Views51.3K

Age at our read96 days

Views per day of life534views 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 · Jul 8, 2026

@SemiAnalysis_ charts agentic coding cache on July 8, 2026

A benchmark bar chart on cache hit, cache reads and cost per request drew 51.3K views and a 0.24% save rate.

What happened

@SemiAnalysis_ posted a benchmark bar chart on agentic coding runs on cache on July 8, 2026. It was the account's only post that day.

The numbers

The post reached 51.3K views, #528 of 1,162 AI chart posts, and scored 57, #511 of 1,162 AI chart posts. Among @SemiAnalysis_ posts it ranks #10 of 24 by views and #9 of 24 by score.

The lesson

A 0.24% save rate, 94th percentile among AI chart posts, shows readers bookmark this benchmark bar chart at a rate above the 0.076% median. The chart shows cache hit and cache reads printed per model.

What it means

The 0.24% save rate sits far above the 0.076% median among AI chart posts, while the 0.62% engagement rate keeps it below the median and the score at #511 of 1,162. For @SemiAnalysis_, the #9 of 24 score rank trails its #10 of 24 views rank.

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

18 points read off this chart

Estimated from the image 97%

Series	Group	Value	Read
CACHE HIT · % OF TOKENS	Haiku 4.5	80.3	printed
CACHE READS · % OF COST	Haiku 4.5	27	printed
COST / REQ	Haiku 4.5	0.008	printed
CACHE HIT · % OF TOKENS	Sonnet 4.6	93.5	printed
CACHE READS · % OF COST	Sonnet 4.6	54	printed
COST / REQ	Sonnet 4.6	0.033	printed
CACHE HIT · % OF TOKENS	Opus 4.6	95.3	printed
CACHE READS · % OF COST	Opus 4.6	62	printed
COST / REQ	Opus 4.6	0.112	printed
CACHE HIT · % OF TOKENS	Opus 4.7	95.8	printed
CACHE READS · % OF COST	Opus 4.7	65	printed
COST / REQ	Opus 4.7	0.147	printed

Showing 12 of 18. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/0220334f378f.json
GET https://viral-chart.com/api/charts/0220334f378f.json
GET https://viral-chart.com/api/charts/0220334f378f.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 0220334f378f.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/0220334f378f`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/0220334f378f/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/0220334f378f/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/0220334f378f/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.