Models
Google
GPQA Diamond accuracy comparison of AI models

@EpochAIResearchX · Apr 18, 2025

GPQA Diamond accuracy comparison of AI models

@EpochAIResearch's benchmark bar chart drew 8.8K views on X: 1.7x @epochairesearch's median post and #840 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

GPQA Diamond accuracy for OpenAI's o3 and o4-mini compared to leading models

XData Benchmark bar chart Gemini 2 All Google models Gemini 2.5 Pro o3 o4-mini Claude 3.7 Sonnet o3-mini o1 DeepSeek-R1Grok-3 mini

@EpochAIResearch: GPQA Diamond accuracy comparison of AI models — Published by @EpochAIResearch on X, Apr 18, 2025. Source: x.com

40/ 100

ViralChart score

Small but loved

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

#755 of 1,162 AI chart posts we hold · #27 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

Small but loved: views below the AI chart median, engagement at or above it, score rank #755.

Its 1.00% engagement rate sits above the 0.73% median for all AI chart posts, ranking #310 of 1,162.

On launch day, this post ranked #3 of 4 by views among the account's posts that day.

Its score of 40 ranks #755 of 1,162 AI chart posts, below the median.

0.2xthe median benchmark bar chart post

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

4posts from @epochairesearch that day

Part of a run of 4 posts on Apr 18, 2025. This one was #3 of 4 by views that day.

top 27%engagement rate

1.00% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

1.7x@epochairesearch's median post

8.8K views, where @epochairesearch's typical post gets 5.3K.

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 #755 of 1,162

Views	8.8K	#840	bottom 28%
Likes	83	#786	bottom 32%
Engagement rate	1.00%	#310	top 27%
Save rate	0.080%	#565	top 49%

Among 59 @epochairesearch posts

Score #27 of 59

Views	8.8K	#23	top 38%
Likes	83	#25	top 42%
Engagement rate	1.00%	#41	bottom 31%
Save rate	0.080%	#47	bottom 21%

Growth

One read so far

Views8.8K

Age at our read542 days

Views per day of life16views 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 · Apr 18, 2025

@EpochAIResearch GPQA Diamond accuracy chart draws modest views

A benchmark bar chart comparing 8 AI models on GPQA Diamond accuracy, posted April 18, 2025.

What happened

On April 18, 2025, @EpochAIResearch posted a benchmark bar chart comparing GPQA Diamond accuracy for 8 models. It was one of 4 posts that day, alongside charts on FrontierMath, MATH Level 5, and OTIS Mock AIME.

The numbers

The post drew 8.8K views, ranking #840 of 1,162 AI chart posts, below the 39.9K median. Its engagement rate was 1.00%, ranking #310 of 1,162.

The lesson

With 8 models shown in a single chart, the post's save rate was 0.080%, below the account's median engagement of 1.37%. A clean table of many models may not drive saves.

What it means

This post's score of 40 ranks #27 of 59 for @EpochAIResearch, below the account's median engagement rate of 1.37%. It shows that even with above-median engagement, low views cap overall performance.

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

7 points read off this chart

Estimated from the image 30%

Group	Value	Read
Gemini 2.5 Pro	76 %	estimated
o3 (high)	77.5 %	estimated
Claude 3.7 Sonnet (high, 64K)	73.5 %	estimated
o3-mini (high)	74.5 %	estimated
o1 (high)	73.5 %	estimated
Grok-3 mini (high)	71.5 %	estimated
DeepSeek-R1	68.5 %	estimated

Max plan · API

GET https://viral-chart.com/api/posts/3f1639f8a8d8.json
GET https://viral-chart.com/api/charts/3f1639f8a8d8.json
GET https://viral-chart.com/api/charts/3f1639f8a8d8.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 3f1639f8a8d8.

Approximate values. Our two readings of this chart agreed only in part (confidence 0.30 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/3f1639f8a8d8`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/3f1639f8a8d8/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/3f1639f8a8d8/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/3f1639f8a8d8/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 Gemini 2

Gemini 2: Gemini 2.5 Flash Native Audio Benchmarks

OfficialX · GoogleDec 16, 2025

Gemini 2.5 Flash Native Audio Benchmarks212.3K views · 1.7K likes