Models
Meta
Improvement With Self-Refinement

MetaX · Jul 7, 2026 · official

Improvement With Self-Refinement

Meta's benchmark bar chart drew 10K views on X: 0.3x its median post and #816 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

XData Benchmark bar chart Muse Image All Meta modelsWith Self-RefinementWithout Self-Refinement

Meta: Improvement With Self-Refinement — Published by Meta on X, Jul 7, 2026. Source: x.com

28/ 100

ViralChart score

Quiet

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

#937 of 1,162 AI chart posts we hold · #30 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 #937 of 1,162 AI chart posts.

Its 0.012 views per follower sits at 0.06x the median across posts with known followers, a 5th percentile mark.

The post's 10K views land at 0.28x Meta's 36.4K company median, ranking #26 of 31 Meta posts.

Engagement of 0.37% is 0.50x the AI chart median of 0.73%, at the 15th percentile.

0.01views per follower

10K views from an account with 865.4K followers.

0.3xMeta's median post

10K views, where Meta's typical post gets 36.4K.

bottom 15%engagement rate

0.37% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

0.2xthe 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 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 #937 of 1,162

Views	10K	#816	bottom 30%
Likes	30	#952	bottom 18%
Engagement rate	0.37%	#987	bottom 15%
Save rate	0.090%	#497	top 43%

Among 31 Meta posts

Score #30 of 31

Views	10K	#26	bottom 18%
Likes	30	#28	bottom 10%
Engagement rate	0.37%	#28	bottom 11%
Save rate	0.090%	#13	top 40%

Growth

One read so far

Views10K

Age at our read97 days

Views per day of life103views 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 · Jul 7, 2026

Meta posts self-refinement benchmark chart on July 7, 2026

A single benchmark bar chart comparing With Self-Refinement and Without Self-Refinement drew 10K views and a 0.37% engagement rate.

What happened

Meta published one benchmark bar chart on July 7, 2026, on Improvement With Self-Refinement. The account posted 2 items that day, including one on Improvement With Test-Time Compute at 1.6K views.

The numbers

The post reached 10K views, ranking #816 of 1,162 AI chart posts by views and #26 of 31 Meta posts. Its score rank is #937 of 1,162 AI chart posts.

The lesson

A single benchmark bar chart with 2 models shown drew 10K views against a 39.9K median among AI chart posts. The 0.37% engagement rate, at 0.50x the AI median, shows the chart format did not convert views into likes or saves.

What it means

At #30 of 31 Meta posts by score, this chart sits near the bottom of the account's own output. The 0.28x gap to Meta's 36.4K company median views shows the post travelled well below the publisher's typical chart reach.

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

6 points read off this chart

Estimated from the image 97%

Series	Group	Value	Read
With Self-Refinement	Text-to-Image	57.1 %	printed
Without Self-Refinement	Text-to-Image	42.9 %	printed
With Self-Refinement	Single-Image Edit	56.3 %	printed
Without Self-Refinement	Single-Image Edit	43.7 %	printed
With Self-Refinement	Multi-Image Edit	56.6 %	printed
Without Self-Refinement	Multi-Image Edit	43.4 %	printed

Max plan · API

GET https://viral-chart.com/api/posts/01667e1e52f4.json
GET https://viral-chart.com/api/charts/01667e1e52f4.json
GET https://viral-chart.com/api/charts/01667e1e52f4.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 01667e1e52f4.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/01667e1e52f4`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/01667e1e52f4/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/01667e1e52f4/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/01667e1e52f4/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 Image

Muse Image: Improvement With Test-Time Compute

OfficialX · MetaJul 7, 2026

Improvement With Test-Time Compute1.6K views · 16 likes

Data

Muse Image: Muse Image: Gap to Use Case Frontier

X · @ArtificialAnlysSep 4, 2026

Muse Image: Gap to Use Case Frontier4.9K views · 5 likes

Data

Muse Image: Muse Image: Gap to Use Case Frontier (Image

X · @ArtificialAnlysSep 4, 2026

Muse Image: Gap to Use Case Frontier (Image4.9K views · 5 likes

Data

Muse Image: Muse Image: Gap to Editing Action Frontier

X · @ArtificialAnlysSep 4, 2026

Muse Image: Gap to Editing Action Frontier1.5K views · 6 likes

Data

Muse Image: Muse Image: Gap to Capability Frontier

X · @ArtificialAnlysSep 4, 2026

Muse Image: Gap to Capability Frontier1.5K views · 6 likes

Data

More from Meta

Meta table chart: AI model benchmark comparison

Meta·Sep 2026

AI model benchmark comparison

3.8M views19.9K likes0.6% eng.

Data

Meta line chart: SAM 3.1 vs SAM 3 Performance

17x

Meta·Mar 2026

SAM 3.1 vs SAM 3 Performance

344.6K views2.2K likes0.8% eng.

Data

Meta annotated chart: APhO 2026 AI Model Results

3.0x

Meta·Jul 2026

APhO 2026 AI Model Results

196.6K views404 likes0.3% eng.

Data

OfficialX · MetaApr 5, 2025

LM Arena ELO score vs. cost1.5M views · 2.3K likes

Data

Muse Glimmer: AI Model Benchmark Comparison

OfficialX · MetaAug 10, 2026

AI Model Benchmark Comparison1.4M views · 8.2K likes

Data

Muse Spark: AI Model Benchmark Comparison

OfficialX · MetaSep 2, 2026

AI Model Benchmark Comparison435.2K views · 3.1K likes

Data

Meta AI app: Hiera Model Performance Comparison

OfficialX · MetaJun 5, 2023

Hiera Model Performance Comparison173.2K views · 567 likes

Data

Meta speech models: Diariazation Error Rate Comparison

OfficialX · MetaSep 1, 2026

Diariazation Error Rate Comparison142.8K views · 1.5K likes

Data

Meta speech models: AA-WER Streaming Index - Final Transcription

OfficialX · MetaSep 1, 2026

AA-WER Streaming Index - Final Transcription142.8K views · 1.5K likes

Data

Questions people ask

Where does this chart come from?

Meta published it on Jul 7, 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.