1. Models
  2. Meta
  3. Llama 3.1 405B Human Evaluation
MetaX · Jul 23, 2024 · official

Llama 3.1 405B Human Evaluation

Meta's stacked bar chart drew 50.7K views on X: 1.4x its median post and #532 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Llama 3.1 405B human evaluation win rates

XDataStacked bar chartLlama 3All Meta modelsGPT-4oLlama 3.1 405BGPT-4-0125-PreviewClaude 3.5 Sonnet
Published by Meta on X, Jul 23, 2024. Source: x.com
53/ 100

ViralChart score

Reached and resonated

More views and a higher engagement rate than the median post: it travelled and people acted on it.

#571 of 1,162 AI chart posts we hold · #11 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 Reached and resonated quadrant, at #571 of 1,162 AI chart posts.

Its #1 of 2 rank by views that day sits above the account's other July 23, 2024 post.

At 0.059 views per follower against a 0.20 median, it lands in the 29th percentile.

The 0.84% engagement rate clears the 0.73% median among AI chart posts, at the 61st percentile.

0.06views per follower

50.7K views from an account with 865.4K followers.

2posts from Meta that day

Part of a run of 2 posts on Jul 23, 2024. This one was #1 of 2 by views that day.

1.4xMeta's median post

50.7K views, where Meta's typical post gets 36.4K.

top 39%engagement rate

0.84% 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 #571 of 1,162

Views50.7K#532top 46%
Likes353#532top 46%
Engagement rate0.84%#454top 39%
Save rate0.063%#691bottom 41%

Among 31 Meta posts

Score #11 of 31

Views50.7K#15top 47%
Likes353#12top 37%
Engagement rate0.84%#15top 47%
Save rate0.063%#19bottom 40%

Growth

One read so far

Views50.7K
Age at our read811 days
Views per day of life63views 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 23, 2024

Meta posts Llama 3.1 405B human evaluation chart

A stacked bar chart of Llama 3.1 405B win, tie and loss rates against GPT-4-0125-Preview and GPT-4o drew 50.7K views.

What happened

Meta published a stacked bar chart on July 23, 2024, covering Llama 3.1 405B human evaluation win rates. The account's other post that day was a Llama context window comparison.

The numbers

It reached 50.7K views, #532 of 1,162 AI chart posts, against a 39.9K median among AI chart posts. Its score of 53 ranks #571 of 1,162 AI chart posts and #11 of 31 Meta posts.

The lesson

The chart shows win, tie and loss rates against GPT-4-0125-Preview and GPT-4o, with ties at 52.2% and 51.7%. A 0.063% save rate against a 0.84% engagement rate marks a post read and liked more than kept.

What it means

At #11 of 31 Meta posts, this chart sits mid-pack for the account, and its 0.059 views per follower against a 0.20 median shows reach well short of the follower base.

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

  1. Llama context window comparison10.2K views
  2. AI Model Performance Trend91.8K views
  3. LM Arena ELO score vs. cost1.5M views
  4. Net Win Rate of SAM Audio vs. SoTA36.4K views
  5. SAM 3.1 vs SAM 3 Performance344.6K views
  6. AI Benchmark Comparison76.3K views

Data and API

9 points read off this chart

Estimated from the image 97%
SeriesGroupValueRead
WinLlama 3.1 405B vs GPT-4-0125-Preview23.3 %printed
TieLlama 3.1 405B vs GPT-4-0125-Preview52.2 %printed
LossLlama 3.1 405B vs GPT-4-0125-Preview24.5 %printed
WinLlama 3.1 405B vs GPT-4o19.1 %printed
TieLlama 3.1 405B vs GPT-4o51.7 %printed
LossLlama 3.1 405B vs GPT-4o29.2 %printed
WinLlama 3.1 405B vs Claude 3.5 Sonnet24.9 %printed
TieLlama 3.1 405B vs Claude 3.5 Sonnet50.8 %printed
LossLlama 3.1 405B vs Claude 3.5 Sonnet24.2 %printed

Max plan · API

GET https://viral-chart.com/api/posts/01b172777bbc.json
GET https://viral-chart.com/api/charts/01b172777bbc.json
GET https://viral-chart.com/api/charts/01b172777bbc.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 01b172777bbc.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/01b172777bbcTitle, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/01b172777bbc/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/01b172777bbc/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/01b172777bbc/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 Llama 3

Llama 3: Llama context window comparison
OfficialX · MetaJul 23, 2024
Llama context window comparison10.2K views · 163 likes
Data
Llama 3: Output Tokens per Second: Llama 3.1 8B Providers
X · @ArtificialAnlysApr 10, 2025
Output Tokens per Second: Llama 3.1 8B Providers12.6K views · 176 likes
Data
Llama 3: GPQA Accuracies for Leading Models
X · @EpochAIResearchJul 31, 2024
GPQA Accuracies for Leading Models6.9K views · 76 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 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 23, 2024 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.