1. Models
  2. Google
  3. Gemini 3.6 Flash performance across agentic benchmarks
GoogleX · Jul 21, 2026 · official

Gemini 3.6 Flash performance across agentic benchmarks

Google's grouped bar chart drew 21.9K views on X: 0.3x its median post and #699 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

Gemini 3.6 Flash outperforms prior generations

XDataGrouped bar chartGemini CLI, Jules and AntigravityAll Google models3.1 Pro3.5 Flash3.6 Flash
Published by Google on X, Jul 21, 2026. Source: x.com
35/ 100

ViralChart score

Quiet

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

#817 of 1,162 AI chart posts we hold · #20 of 22 Google 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 #817 of 1,162 AI chart posts.

Its 0.014 views per follower sits at 0.07x the median across posts with known followers, the 8th percentile.

At 21.9K views it runs 0.30x Google's company median of 73.2K, ranking #19 of 22 Google posts.

On a day with 2 posts from this account, it ranked #2 of 2 by views.

0.01views per follower

21.9K views from an account with 1.6M followers.

0.3xGoogle's median post

21.9K views, where Google's typical post gets 73.2K.

0.3xthe median grouped bar chart post

Across 108 grouped bar chart posts we hold, the median gets 87.5K views.

2posts from Google that day

Part of a run of 2 posts on Jul 21, 2026. This one was #2 of 2 by views that day.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 22 from Google.

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 #817 of 1,162

Views21.9K#699bottom 40%
Likes93#769bottom 34%
Engagement rate0.50%#835bottom 28%
Save rate0.050%#824bottom 29%

Among 22 Google posts

Score #20 of 22

Views21.9K#19bottom 16%
Likes93#20bottom 11%
Engagement rate0.50%#15bottom 34%
Save rate0.050%#14bottom 39%

Growth

One read so far

Views21.9K
Age at our read83 days
Views per day of life263views 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.

Google'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 21, 2026

Google posts Gemini 3.6 Flash agentic benchmark chart

A grouped bar chart of Gemini 3.6 Flash against 3.5 Flash and 3.1 Pro drew 21.9K views, below the 39.9K median among AI chart posts.

What happened

Google published a grouped bar chart on July 21, 2026, showing Gemini 3.6 Flash performance across agentic benchmarks. That day the account posted 2 times, including Gemini 3.5 Flash-Lite vs 3.1 Flash-Lite Benchmarks.

The numbers

The post reached 21.9K views, ranking #699 of 1,162 AI chart posts and #19 of 22 Google posts. Its score rank is #817 of 1,162 AI chart posts.

The lesson

A grouped bar chart with 3 models drew 21.9K views against a 39.9K median among AI chart posts. The save rate of 0.050% and engagement rate of 0.50% sit below the median.

What it means

At #20 of 22 Google posts by score, this chart trails the account's own median. The 0.30x gap to Google's 73.2K company median views shows the post landed below the publisher's typical 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 Google posted next

  1. Gemini 3.5 Flash-Lite vs 3.1 Flash-Lite Benchmarks23.6K views
  2. Production FrontierCode 1.1 Main205.1K views
  3. FLEURS speech recognition accuracy across languages23.4K views
  4. Agentic video understanding on accuracy and cost26.4K views
  5. Gemini 3.8 Flash Cyber vulnerability discovery78.7K views
  6. AI Model Benchmark Comparison9M views

Data and API

12 points read off this chart

Estimated from the image 97%
SeriesGroupValueRead
3.1 ProLong-horizon software engineering (DeepSWE v1.1)12printed
3.5 FlashLong-horizon software engineering (DeepSWE v1.1)37printed
3.6 FlashLong-horizon software engineering (DeepSWE v1.1)49printed
3.1 ProMachine Learning Engineering (MLE-Bench)42.6printed
3.5 FlashMachine Learning Engineering (MLE-Bench)49.7printed
3.6 FlashMachine Learning Engineering (MLE-Bench)63.9printed
3.1 ProKnowledge Work (GDPval-AA v2)965printed
3.5 FlashKnowledge Work (GDPval-AA v2)1349printed
3.6 FlashKnowledge Work (GDPval-AA v2)1421printed
3.1 ProComputer Use (OSWorld-Verified)76.2printed
3.5 FlashComputer Use (OSWorld-Verified)78.4printed
3.6 FlashComputer Use (OSWorld-Verified)83printed

Max plan · API

GET https://viral-chart.com/api/posts/554e85f0cdd1.json
GET https://viral-chart.com/api/charts/554e85f0cdd1.json
GET https://viral-chart.com/api/charts/554e85f0cdd1.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 554e85f0cdd1.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/554e85f0cdd1Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/554e85f0cdd1/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/554e85f0cdd1/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/554e85f0cdd1/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 from Google

Google table chart: Gemini 4 Argon benchmark comparison5.7x
Google·Sep 2026
Gemini 4 Argon benchmark comparison
3.9M views25.9K likes0.8% eng.
Data
Google annotated chart: Alphabet Q2 metrics2.8x
Google·Jul 2026
Alphabet Q2 metrics
3.9M views12.6K likes0.4% eng.
Data
Google annotated chart: Just posted Q3 earnings. We delivered our first-ever3.2x
Google·Oct 2025
Just posted Q3 earnings. We delivered our first-ever
2.9M views14.6K likes0.6% eng.
Data
Gemini 4: AI Model Benchmark Comparison
OfficialX · GoogleSep 30, 2026
AI Model Benchmark Comparison9M views · 43K likes
Data
Gemma 4: Model Performance vs Size
OfficialX · GoogleApr 9, 2026
Model Performance vs Size886.1K views · 1.7K likes
Data
Gemini 3: Codeforces Coding and Algorithms
OfficialX · GoogleFeb 12, 2026
Codeforces Coding and Algorithms695.4K views · 1.9K likes
Data
Gemini 3: Gemini 3 Deep Think on Humanity's Last Exam
OfficialX · GoogleFeb 12, 2026
Gemini 3 Deep Think on Humanity's Last Exam695.4K views · 1.9K likes
Data
Gemini 3: MMMU-Pro Multimodal Understanding and Reasoning
OfficialX · GoogleFeb 12, 2026
MMMU-Pro Multimodal Understanding and Reasoning695.4K views · 1.9K likes
Data
Gemini 3: ARC-AGI-2 Reasoning & Knowledge
OfficialX · GoogleFeb 12, 2026
ARC-AGI-2 Reasoning & Knowledge695.4K views · 1.9K likes
Data

Questions people ask

Where does this chart come from?

Google published it on Jul 21, 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.