1. Models
  2. Meta
  3. Humanity's Last Exam (With Tools)
MetaX · Apr 8, 2026 · official

Humanity's Last Exam (With Tools)

Meta's line chart drew 17.2K views on X: 0.5x its median post and #733 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Accuracy vs latency for multi-agent systems

XDataLine chartMuse SparkAll Meta models1 agent2 agents4 agents16 agents
Published by Meta on X, Apr 8, 2026. Source: x.com
33/ 100

ViralChart score

Quiet

Fewer views and a lower engagement rate than the median post.

#853 of 1,162 AI chart posts we hold · #26 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

The post sits in the Quiet quadrant, with a score rank of #853 of 1,162 AI chart posts.

Its 0.020 views per follower sits at 0.10x the 0.20 median across posts with known followers, an 11th percentile mark.

It landed at #3 of 3 posts from this account that day, with 17.2K views against 78.7K and 76.3K for the other posts.

A score of 33 places it at #853 of 1,162 AI chart posts and #26 of 31 Meta posts.

0.02views per follower

17.2K views from an account with 865.4K followers.

0.2xthe median line chart post

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

3posts from Meta that day

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

0.5xMeta's median post

17.2K views, where Meta's typical post gets 36.4K.

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 #853 of 1,162

Views17.2K#733bottom 37%
Likes70#813bottom 30%
Engagement rate0.49%#850bottom 27%
Save rate0.052%#790bottom 32%

Among 31 Meta posts

Score #26 of 31

Views17.2K#20bottom 37%
Likes70#26bottom 18%
Engagement rate0.49%#24bottom 24%
Save rate0.052%#23bottom 27%

Growth

One read so far

Views17.2K
Age at our read187 days
Views per day of life92views 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 a line chart on Humanity's Last Exam with tools

The chart plots accuracy against latency for multi-agent systems, and the post reached 17.2K views with a 0.49% engagement rate.

What happened

Meta published a line chart on April 8, 2026, covering Humanity's Last Exam (With Tools) and accuracy versus latency for multi-agent systems. It was 1 of 3 posts from the account that day, alongside posts on Held Out Codebase Perplexity and an AI Benchmark Comparison.

The numbers

The post reached 17.2K views, ranking #733 of 1,162 AI chart posts, against a median of 39.9K views among AI chart posts. Its score of 33 ranks #853 of 1,162 AI chart posts and #26 of 31 Meta posts.

The lesson

The chart shows 57.5% and 58% accuracy for 16 agents, and the post drew 70 likes on 17.2K views. A 0.052% save rate against a 0.49% engagement rate marks this as a chart people liked but did not keep.

What it means

At #26 of 31 Meta posts and #853 of 1,162 AI chart posts, this chart sits below the account's own body of work. The 0.020 views per follower against a 0.20 median across posts with known followers shows the gap to the wider field.

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

Data and API

10 points read off this chart

Estimated from the image 70%
SeriesGroupValueRead
1 agent50.2 %estimated
1 agent51.9 %estimated
1 agent54 %estimated
1 agent54.3 %estimated
2 agents56 %estimated
2 agents56.5 %estimated
4 agents56.5 %estimated
4 agents57 %estimated
16 agents57.5 %printed
16 agents58 %printed

Max plan · API

GET https://viral-chart.com/api/posts/e229720b93c2.json
GET https://viral-chart.com/api/charts/e229720b93c2.json
GET https://viral-chart.com/api/charts/e229720b93c2.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 e229720b93c2.

PathReturnsPlan
GET/api/v1/charts/e229720b93c2Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/e229720b93c2/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/e229720b93c2/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/e229720b93c2/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 Muse Spark

More from Meta

Questions people ask

Where does this chart come from?

Meta published it on Apr 8, 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.