1. Models
  2. Meta
  3. AI Model Benchmark Comparison
MetaX · Aug 10, 2026 · official

AI Model Benchmark Comparison

Meta's table chart drew 1.4M views on X: 39x its median post and #82 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

Benchmark performance comparison of three AI models

XDataTable chartMuse GlimmerAll Meta modelsMuse Glimmer-30BGemma3-31BQwen3.6-27B
Published by Meta on X, Aug 10, 2026. Source: x.com
87/ 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.

#4 of 1,162 AI chart posts we hold · #1 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 lands in the Wide but thin quadrant, at #4 of 1,162 AI chart posts by score.

Its 1.4M views sit 39x Meta's median post of 36.4K, the #2 of 31 Meta posts by views.

A score of 87 puts it #4 of 1,162 AI chart posts and #1 of 31 Meta posts.

Saves run at 0.20%, the 90th percentile among AI chart posts and 2.6x their 0.076% median.

39xMeta's median post

1.4M views, where Meta's typical post gets 36.4K.

11xthe median table chart post

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

top 10%save rate

0.200% of viewers bookmarked it to come back to. The median post gets 0.076%.

2posts from Meta that day

Part of a run of 2 posts on Aug 10, 2026. This one was #1 of 2 by views that day.

Public X numbers from our read on Oct 13, 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 #4 of 1,162

Views1.4M#82top 7%
Likes8.2K#37top 3%
Engagement rate0.71%#608bottom 48%
Save rate0.200%#117top 10%

Among 31 Meta posts

Score #1 of 31

Views1.4M#2top 5%
Likes8.2K#1top 2%
Engagement rate0.71%#20bottom 37%
Save rate0.200%#4top 11%

Growth

Our reads cover 3 days

Views1.4M
Age at our read64 days
Views per day of life22.3Kviews divided by days since it was posted
Gained between our reads+435views over 3 days, about 153 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.

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 10, 2026 · Lead story

Meta posts a three-model benchmark table chart

The table chart drew 1.4M views and a 0.20% save rate, but its 0.71% engagement rate sits below the AI chart median.

What happened

Meta published a table chart comparing benchmark performance of three AI models on August 10, 2026. That day the account posted 2 posts, the other on DFlash Speculative Decoding Performance at 52.2K views.

The numbers

It reached 1.4M views, #82 of 1,162 AI chart posts by views and #2 of 31 Meta posts. Its score of 87 ranks #4 of 1,162 AI chart posts.

The lesson

A single table chart with 3 models drew 1.4M views and a 0.20% save rate, the 90th percentile among AI chart posts. The 0.71% engagement rate sits below the AI chart median, so the reach and the saves do not carry the same weight.

What it means

At #1 of 31 Meta posts by score, this chart sits far above the account's 36.4K median views. Its 0.71% engagement rate against a 0.20% save rate shows the gap between views and interaction for this publisher's chart posts.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what Meta posted next

  1. DFlash Speculative Decoding Performance52.2K views
  2. Model Performance on SimpleVQA, ZeroBench, and CharXiv Reasoning10.1K views
  3. Multimodal Intelligence2.9K views
  4. AA-WER Streaming Index - Final Transcription142.8K views
  5. AI Model Benchmark Comparison435.2K views
  6. AIRA3 - NVIDIA Nemotron Model Reasoning Challenge25.8K views

Data and API

98 points read off this chart

Estimated from the image 57%
SeriesGroupValueRead
Muse Glimmer-3B (Thinking High)MCP Atlas75.5printed
Gemma3-31B (Thinking Mode)MCP Atlas54.2printed
Qwen3.6-27B (Thinking Mode)MCP Atlas62.5printed
Muse Glimmer-3B (Thinking High)Deep3-Banking74.6printed
Gemma3-31B (Thinking Mode)Deep3-Banking61.7printed
Qwen3.6-27B (Thinking Mode)Deep3-Banking71.1printed
Muse Glimmer-3B (Thinking High)GDPval-AA95.3printed
Gemma3-31B (Thinking Mode)GDPval-AA81.1printed
Qwen3.6-27B (Thinking Mode)GDPval-AA114.1printed
Muse Glimmer-3B (Thinking High)SkillsBench (With Skills)44.3printed
Gemma3-31B (Thinking Mode)SkillsBench (With Skills)32.4printed
Qwen3.6-27B (Thinking Mode)SkillsBench (With Skills)40printed

Showing 12 of 98. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/b62b4efec99b.json
GET https://viral-chart.com/api/charts/b62b4efec99b.json
GET https://viral-chart.com/api/charts/b62b4efec99b.skill.md
Make one like thisOpen the post JSONChart data JSONSkill fileAPI 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 b62b4efec99b.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/b62b4efec99bTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/b62b4efec99b/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/b62b4efec99b/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/b62b4efec99b/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 Glimmer

Muse Glimmer: DFlash Speculative Decoding Performance
OfficialX · MetaAug 10, 2026
DFlash Speculative Decoding Performance52.2K views · 456 likes
Data
Muse Glimmer: Code Muse Arena - Open Weight Rank #26
X · @arenaAug 11, 2026
Code Muse Arena - Open Weight Rank #2657.8K views · 414 likes
Data
Muse Glimmer: Artificial Analysis Openness Index: Components
X · @ArtificialAnlysAug 10, 2026
Artificial Analysis Openness Index: Components8.5K views · 51 likes
Data
Muse Glimmer: AA Omniscience Index and Accuracy Benchmarks
X · @ArtificialAnlysAug 10, 2026
AA Omniscience Index and Accuracy Benchmarks7.1K views · 34 likes
Data
Muse Glimmer: Text Muse Arena - Open Weight Rank #24
X · @arenaAug 11, 2026
Text Muse Arena - Open Weight Rank #246.3K views · 26 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 Performance17x
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 Results3.0x
Meta·Jul 2026
APhO 2026 AI Model Results
196.6K views404 likes0.3% eng.
Data
Llama 4: LM Arena ELO score vs. cost
OfficialX · MetaApr 5, 2025
LM Arena ELO score vs. cost1.5M views · 2.3K 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
Muse Spark: High-dimensional ellipsoid fit threshold
OfficialX · MetaOct 2, 2026
High-dimensional ellipsoid fit threshold95.2K views · 154 likes
Data

Questions people ask

Where does this chart come from?

Meta published it on Aug 10, 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.