Models
Google
GPQA Diamond accuracy comparison

@EpochAIResearchX · Jan 31, 2025

GPQA Diamond accuracy comparison

@EpochAIResearch's benchmark bar chart drew 376 views on X: 0.1x @epochairesearch's median post and #1,158 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

GPQA Diamond accuracy for Mistral Small 3 compared to other models

XData Benchmark bar chart Gemma specialist models All Google modelsLlama 3.3 70BQwen 2.5 32BMistral Small 3GPT-4o mini (2024-07-18)Gemma 2 27B

@EpochAIResearch: GPQA Diamond accuracy comparison — Published by @EpochAIResearch on X, Jan 31, 2025. Source: x.com

16/ 100

ViralChart score

Small but loved

Fewer views than the median post but a higher engagement rate: a smaller crowd that acted on it.

#1,111 of 1,162 AI chart posts we hold · #57 of 59 @epochairesearch 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 Small but loved quadrant, at #1,111 of 1,162 AI chart posts.

Its 376 views sit at 0.07x @EpochAIResearch's median post, ranking #57 of 59 @EpochAIResearch posts.

The 2.39% engagement rate lands in the 99th percentile among AI chart posts, against a 0.73% median.

A score of 16 places it #1,111 of 1,162 AI chart posts and #57 of 59 @EpochAIResearch posts.

0.0xthe median benchmark bar chart post

Across 215 benchmark bar chart posts we hold, the median gets 44.4K views.

0.1x@epochairesearch's median post

376 views, where @epochairesearch's typical post gets 5.3K.

top 1%engagement rate

2.39% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

bottom 2%save rate

0.000% of viewers bookmarked it to come back to. The median post gets 0.076%.

Public X numbers from our read on Oct 12, 2026. Peers: 1,162 AI chart posts we hold and 59 from @epochairesearch.

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 #1,111 of 1,162

Views	376	#1,158	bottom 1%
Likes	8	#1,138	bottom 2%
Engagement rate	2.39%	#11	top 1%
Save rate	0.000%	#1,159	bottom 2%

Among 59 @epochairesearch posts

Score #57 of 59

Views	376	#57	bottom 4%
Likes	8	#57	bottom 4%
Engagement rate	2.39%	#7	top 11%
Save rate	0.000%	#58	bottom 3%

Growth

One read so far

Age at our read620 days

Views per day of life1views 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.

@epochairesearch'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 · Jan 31, 2025

@EpochAIResearch posts GPQA Diamond accuracy comparison for Mistral Small 3

The benchmark bar chart drew 376 views and a 2.39% engagement rate, with a 0.000% save rate.

What happened

@EpochAIResearch published a benchmark bar chart on January 31, 2025, comparing GPQA Diamond accuracy for Mistral Small 3 against other models. It was one of 3 posts from the account that day, alongside a Mistral Small 3 benchmark accuracy chart at 4.9K views and a MATH Level 5 pass@1 comparison at 366 views.

The numbers

The post reached 376 views, ranking #1,158 of 1,162 AI chart posts and #57 of 59 @EpochAIResearch posts. Its score of 16 ranks #1,111 of 1,162 AI chart posts.

The lesson

A 2.39% engagement rate at the 99th percentile among AI chart posts came with a 0.000% save rate: readers engaged without saving the 5-model comparison.

What it means

At 0.07x @EpochAIResearch's median views, this post ranks #57 of 59 @EpochAIResearch posts, while its 2.39% engagement rate sits above the 1.37% median for this account.

Written by ViralChart from public numbers read on Oct 12, 2026. Every number is checked against our data before it is shown.

Updates: what @epochairesearch posted next

Data and API

5 points read off this chart

Estimated from the image 65%

Group	Value	Read
Llama 3.3 70B	44.25 %	estimated
Qwen 2.5 32B	43.25 %	estimated
Mistral Small 3	41.75 %	estimated
GPT-4o mini (2024-07-18)	36.75 %	estimated
Gemma 2 27B	33.25 %	estimated

Max plan · API

GET https://viral-chart.com/api/posts/2eafff64e4f3.json
GET https://viral-chart.com/api/charts/2eafff64e4f3.json
GET https://viral-chart.com/api/charts/2eafff64e4f3.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 2eafff64e4f3.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/2eafff64e4f3`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/2eafff64e4f3/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/2eafff64e4f3/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/2eafff64e4f3/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 Gemma specialist models

Gemma specialist models: Model Benchmark Comparison

OfficialX · GoogleFeb 21, 2024

Model Benchmark Comparison147.2K views · 335 likes

Data

OfficialBlog · GoogleJul 8, 2026

Performance of medium-sized LLMs

OfficialBlog · GoogleJul 8, 2026

FunctionGemma accuracy on Mobile Actions tasks

OfficialBlog · GoogleJul 8, 2026

FunctionGemma accuracy before and after fine-tuning

OfficialBlog · GoogleJan 13, 2026

MedGemma 1.5 4B performance comparison

OfficialBlog · GoogleJan 13, 2026

MedGemma medical text task performance

More from Google

Google table chart: Gemini 4 Argon benchmark comparison

5.7x

Google·Sep 2026

Gemini 4 Argon benchmark comparison

3.9M views25.9K likes0.8% eng.

Data

Google annotated chart: Alphabet Q2 metrics

2.8x

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-ever

3.2x

Google·Oct 2025

Just posted Q3 earnings. We delivered our first-ever

2.9M views14.6K likes0.6% eng.

Data

OfficialX · GoogleSep 30, 2026

AI Model Benchmark Comparison9M views · 43K likes

Data

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?

@EpochAIResearch published it on Jan 31, 2025 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.