Models
Meta
AI Benchmark Comparison

MetaX · Apr 8, 2026 · official

AI Benchmark Comparison

Meta's table chart drew 76.3K views on X: 2.1x its median post and #437 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

AI model benchmark scores comparison table

XData Table chart Muse Spark All Meta modelsMuse ContemplatingGemini 3.1 Deep ThinkGPT 5.4 Pro

Meta: AI Benchmark Comparison — Published by Meta on X, Apr 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.

#500 of 1,162 AI chart posts we hold · #10 of 31 Meta 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 #500 of 1,162 AI chart posts by score.

Its 76.3K views sit 2.1x above Meta's median post, at #11 of 31 Meta posts.

The post landed #2 of 3 from this account that day, with 3 posts from this account that day.

At 0.088 views per follower against a 0.20 median, it sits at the 35th percentile among posts with known followers.

0.09views per follower

76.3K views from an account with 865.4K followers.

3posts from Meta that day

Part of a run of 3 posts on Apr 8, 2026. This one was #2 of 3 by views that day.

2.1xMeta's median post

76.3K views, where Meta's typical post gets 36.4K.

0.6xthe median table chart post

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

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 31 from Meta.

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 #500 of 1,162

Views	76.3K	#437	top 38%
Likes	494	#446	top 38%
Engagement rate	0.71%	#603	bottom 48%
Save rate	0.063%	#696	bottom 40%

Among 31 Meta posts

Score #10 of 31

Views	76.3K	#11	top 34%
Likes	494	#9	top 27%
Engagement rate	0.71%	#19	bottom 40%
Save rate	0.063%	#20	bottom 37%

Growth

One read so far

Views76.3K

Age at our read187 days

Views per day of life408views 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.

Meta'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 · Apr 8, 2026

Meta posts AI benchmark table with 3 models

The table chart drew 76.3K views against a 39.9K median among AI chart posts, with a 0.71% engagement rate.

What happened

Meta published a table chart on April 8, 2026, comparing AI model benchmark scores. It came with Terence posts from this account that day, including Held Out Codebase Perplexity and Humanity's Last Exam (With Tools).

The numbers

It reached 76.3K views, #437 of 1,162 AI chart posts by views and #11 of 31 Meta posts. Its score rank is #500 of 1,162 AI chart posts.

The lesson

A table chart with 3 models drew 76.3K views, 2.1x Meta's median, but a 0.063% save rate. The views came without the saves.

What it means

At #10 of 31 Meta posts by score, this chart sits below the account's own top posts. The 0.088 views per follower against a 0.20 median marks the gap.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what Meta posted next

Data and API

13 points read off this chart

Estimated from the image 93%

Series	Group	Value	Read
Muse Contemplating	Humanity's Last Exam (Multidisciplinary Reasoning (No Tools))	50.2 score	printed
Gemini 3.1 Deep Think	Humanity's Last Exam (Multidisciplinary Reasoning (No Tools))	48.4 score	printed
GPT 5.4 Pro	Humanity's Last Exam (Multidisciplinary Reasoning (No Tools))	43.9 score	printed
GPT 5.4 Pro (Self-Reported)	Humanity's Last Exam (Multidisciplinary Reasoning (No Tools))	42.7 score	printed
Muse Contemplating	Humanity's Last Exam (Multidisciplinary Reasoning (With Tools))	58.4 score	printed
Gemini 3.1 Deep Think	Humanity's Last Exam (Multidisciplinary Reasoning (With Tools))	53.4 score	printed
GPT 5.4 Pro	Humanity's Last Exam (Multidisciplinary Reasoning (With Tools))	58.7 score	printed
Muse Contemplating	IPhO 2025 (Theory) (Physics Olympiad)	82.6 score	printed
Gemini 3.1 Deep Think	IPhO 2025 (Theory) (Physics Olympiad)	87.7 score	printed
GPT 5.4 Pro	IPhO 2025 (Theory) (Physics Olympiad)	93.5 score	printed
Muse Contemplating	FrontierScience Research (Scientific Research)	38.3 score	printed
Gemini 3.1 Deep Think	FrontierScience Research (Scientific Research)	23.3 score	printed

Showing 12 of 13. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/f2262aa9c5a7.json
GET https://viral-chart.com/api/charts/f2262aa9c5a7.json
GET https://viral-chart.com/api/charts/f2262aa9c5a7.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 f2262aa9c5a7.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/f2262aa9c5a7`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/f2262aa9c5a7/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/f2262aa9c5a7/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/f2262aa9c5a7/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.