Models
Anthropic
Claude 3.5 Sonnet benchmarks

AnthropicX · Jun 20, 2024 · official

Claude 3.5 Sonnet benchmarks

Anthropic's table chart drew 2.5M views on X: 5.9x its median post and #54 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Claude 3.5 Sonnet benchmark comparison table

XData Table chart Claude 3 All Anthropic models GPT-4oClaude 3.5 SonnetClaude 3 OpusGemini 1.5 ProLlama-400b (early snapshot)

Anthropic: Claude 3.5 Sonnet benchmarks — Published by Anthropic on X, Jun 20, 2024. Source: x.com

75/ 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.

#114 of 1,162 AI chart posts we hold · #14 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 #114 of 1,162 AI chart posts.

Its 2.5M views sit 5.9x above Anthropic's 431K median, at #12 of 56 Anthropic posts.

A score of 75 places it #114 of 1,162 AI chart posts and #14 of 56 Anthropic posts.

Engagement lands at 0.39%, the 17th percentile among AI chart posts and #965 of 1,162.

19xthe median table chart post

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

5.9xAnthropic's median post

2.5M views, where Anthropic's typical post gets 431K.

bottom 17%engagement rate

0.39% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

bottom 34%save rate

0.055% 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 #114 of 1,162

Views	2.5M	#54	top 5%
Likes	7K	#44	top 4%
Engagement rate	0.39%	#965	bottom 17%
Save rate	0.055%	#763	bottom 34%

Among 56 Anthropic posts

Score #14 of 56

Views	2.5M	#12	top 21%
Likes	7K	#12	top 21%
Engagement rate	0.39%	#42	bottom 26%
Save rate	0.055%	#28	top 49%

Growth

Our reads cover 26 hours

Views2.5M

Age at our read845 days

Views per day of life3Kviews divided by days since it was posted

Gained between our reads+20views over 26 hours, about 18 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 · Jun 20, 2024

Anthropic posts Claude 3.5 Sonnet benchmark table

The June 20, 2024 table chart drew 2.5M views but a 0.39% engagement rate, the 17th percentile among AI chart posts.

What happened

Anthropic posted a table chart on Claude 3.5 Sonnet benchmarks on June 20, 2024. It was the account's only post that day.

The numbers

It reached 2.5M views, #54 of 1,162 AI chart posts and #12 of 56 Anthropic posts. Its score of 75 ranks #114 of 1,162 AI chart posts.

The lesson

At 0.39% engagement against a 0.73% median among AI chart posts, this 5-model table drew views without matching the median save-and-reply rate.

What it means

For Anthropic, 2.5M views at #12 of 56 Anthropic posts came with a 0.39% engagement rate, below the account's own 0.56% median.

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

Data and API

34 points read off this chart

Estimated from the image 97%

Series	Group	Value	Read
Claude 3.5 Sonnet	Graduate level reasoning GPQA, Diamond	59.4 %	printed
Claude 3 Opus	Graduate level reasoning GPQA, Diamond	50.4 %	printed
GPT-4o	Graduate level reasoning GPQA, Diamond	53.6 %	printed
Claude 3.5 Sonnet	Undergraduate level knowledge MMLU	88.7 %	printed
Claude 3 Opus	Undergraduate level knowledge MMLU	86.8 %	printed
Gemini 1.5 Pro	Undergraduate level knowledge MMLU	85.9 %	printed
Llama-400b (early snapshot)	Undergraduate level knowledge MMLU	86.1 %	printed
Claude 3.5 Sonnet	Code HumanEval	92 %	printed
Claude 3 Opus	Code HumanEval	84.9 %	printed
GPT-4o	Code HumanEval	90.2 %	printed
Gemini 1.5 Pro	Code HumanEval	84.1 %	printed
Llama-400b (early snapshot)	Code HumanEval	84.1 %	printed

Showing 12 of 34. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/32703271ad90.json
GET https://viral-chart.com/api/charts/32703271ad90.json
GET https://viral-chart.com/api/charts/32703271ad90.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 32703271ad90.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/32703271ad90`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/32703271ad90/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/32703271ad90/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/32703271ad90/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.