Models
Meta
AI Model Benchmarks Comparison

MetaX · Aug 5, 2026 · official

AI Model Benchmarks Comparison

Meta's grouped bar chart drew 56.7K views on X: 1.6x its median post and #505 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

AI model performance across three coding benchmarks

XData Grouped bar chart Muse Spark All Meta models GPT 5.6Opus 5Muse Spark 1.2Grok 4.5Gemini 3.6Muse Spark 1.1Terra

Meta: AI Model Benchmarks Comparison — Published by Meta on X, Aug 5, 2026. Source: x.com

40/ 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.

#748 of 1,162 AI chart posts we hold · #24 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 Wide but thin quadrant, at #748 of 1,162 AI chart posts.

Its 0.025% save rate sits at the 12th percentile among AI chart posts, against a 0.076% median.

The post carries 2 charts, and every chart in the post shares the post's numbers.

At 0.066 views per follower it lands in the 31st percentile, against a 0.20 median across posts with known followers.

0.07views per follower

56.7K views from an account with 865.4K followers.

2charts in this one post

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

bottom 12%save rate

0.025% of viewers bookmarked it to come back to. The median post gets 0.076%.

bottom 16%engagement rate

0.38% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

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 #748 of 1,162

Views	56.7K	#505	top 43%
Likes	191	#657	bottom 43%
Engagement rate	0.38%	#979	bottom 16%
Save rate	0.025%	#1,022	bottom 12%

Among 31 Meta posts

Score #24 of 31

Views	56.7K	#13	top 40%
Likes	191	#16	top 50%
Engagement rate	0.38%	#27	bottom 15%
Save rate	0.025%	#30	bottom 5%

Growth

One read so far

Views56.7K

Age at our read68 days

Views per day of life833views 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 · Aug 5, 2026

Meta posts AI model benchmarks comparison chart

A grouped bar chart of AI model performance across three coding benchmarks drew 56.7K views and a 0.38% engagement rate.

What happened

Meta published a grouped bar chart on August 5, 2026, covering AI model performance across three coding benchmarks. The post carried 2 charts, the other being MCP Atlas vs GDPval-AA V2 Model Scores, and it was the account's only post that day.

The numbers

It reached 56.7K views, ranking #505 of 1,162 AI chart posts, and scored #748 of 1,162 AI chart posts. Among Meta's own posts it ranks #24 of 31 Meta posts.

The lesson

A 0.025% save rate, at the 12th percentile among AI chart posts, is the number to start from: this grouped bar chart of 7 models was kept at a fraction of the 0.076% median.

What it means

At #24 of 31 Meta posts and 0.066 views per follower against a 0.20 median, this chart post trails both the account's own body of work and 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.

Updates: what Meta posted next

Data and API

17 points read off this chart

Estimated from the image 97%

Series	Group	Value	Read
Terminal-Bench 2.1	Opus 5 (max) Claude Code	86.7 %	printed
Terminal-Bench 2.1	Muse Spark 1.2 Muse Code	82.9 %	printed
Terminal-Bench 2.1	GPT 5.6 (high) Codex	81.8 %	printed
Terminal-Bench 2.1	Grok 4.5 (high) Grok Build	81.6 %	printed
Terminal-Bench 2.1	Gemini 3.6 (high) Antigravity CLI	78.9 %	printed
Terminal-Bench 2.1	Muse Spark 1.1 mini-agent	76.2 %	printed
DeepSWE 1.1	Opus 5 (max) Claude Code	65 %	printed
DeepSWE 1.1	GPT 5.6 (high) Codex	64.8 %	printed
DeepSWE 1.1	Muse Spark 1.2 Muse Code	59.3 %	printed
DeepSWE 1.1	Grok 4.5 (high) Grok Build	56.6 %	printed
DeepSWE 1.1	Muse Spark 1.1 mini-agent	53 %	printed
DeepSWE 1.1	Gemini 3.6 (high) Antigravity CLI	40 %	printed

Showing 12 of 17. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/71083a711cf2.json
GET https://viral-chart.com/api/charts/71083a711cf2.json
GET https://viral-chart.com/api/charts/71083a711cf2.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 71083a711cf2.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/71083a711cf2`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/71083a711cf2/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/71083a711cf2/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/71083a711cf2/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.