Models
Anthropic
GPQA Diamond accuracy for Claude models

@EpochAIResearchX · May 28, 2025

GPQA Diamond accuracy for Claude models

@EpochAIResearch's benchmark bar chart drew 3.3K views on X: 0.6x @epochairesearch's median post and #1,018 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

GPQA Diamond accuracy for Claude Sonnet 4 and Opus 4

XData Benchmark bar chart Claude Opus 4 All Anthropic modelsGemini 2.5 Pro reasoning_effort = higho3 o4-mini reasoning_effort = highClaude Sonnet 4 thinking budget = 59KClaude 3.7 Sonnet thinking budget = 16KGrok 3.5 Mini BetaClaude 3.5 Sonnet

@EpochAIResearch: GPQA Diamond accuracy for Claude models — Published by @EpochAIResearch on X, May 28, 2025. Source: x.com

23/ 100

ViralChart score

Small but loved

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

#1,032 of 1,162 AI chart posts we hold · #55 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 Small but loved, at #1,032 of 1,162 AI chart posts.

Its score of 23 lands at #1,032 of 1,162 AI chart posts, below the field.

Saves came in at 0.030%, the 15th percentile among AI chart posts against a 0.076% median.

It was #2 of 4 posts from this account that day, level with the day's own output.

0.1xthe median benchmark bar chart post

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

bottom 15%save rate

0.030% of viewers bookmarked it to come back to. The median post gets 0.076%.

4posts from @epochairesearch that day

Part of a run of 4 posts on May 28, 2025. This one was #2 of 4 by views that day.

top 27%engagement rate

0.99% 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 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 #1,032 of 1,162

Views	3.3K	#1,018	bottom 12%
Likes	30	#959	bottom 18%
Engagement rate	0.99%	#320	top 27%
Save rate	0.030%	#992	bottom 15%

Among 59 @epochairesearch posts

Score #55 of 59

Views	3.3K	#37	bottom 38%
Likes	30	#47	bottom 20%
Engagement rate	0.99%	#43	bottom 28%
Save rate	0.030%	#55	bottom 8%

Growth

One read so far

Views3.3K

Age at our read502 days

Views per day of life7views 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 · May 28, 2025

@EpochAIResearch charts GPQA Diamond accuracy for Claude models

The post drew 3.3K views and a 0.99% engagement rate, with saves at 0.030%.

What happened

@EpochAIResearch posted a benchmark bar chart on May 28, 2025 covering GPQA Diamond accuracy for Claude models. It was one of 4 posts from the account that day, alongside SWE-bench Verified and OTIS Mock AIME 2024-2025 charts.

The numbers

It reached 3.3K views, ranking #1,018 of 1,162 AI chart posts, against a median of 39.9K. Its score of 23 ranks #1,032 of 1,162 AI chart posts and #55 of 59 @EpochAIResearch posts.

The lesson

A save rate of 0.030%, the 15th percentile among AI chart posts, sits below the 0.076% median: this 7-model comparison gave readers little to bookmark. The 0.99% engagement rate sits at or above the AI chart median while views stay below it.

What it means

At #55 of 59 @EpochAIResearch posts, this chart trails the account's own output, and its 3.3K views sit far under the 39.9K median among AI chart posts. The 0.030% save rate, against a 0.076% median, marks a wide gap on the measure that keeps a chart citable.

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

9 points read off this chart

Estimated from the image 30%

Group	Value	Read
Gemini 2.5 Pro reasoning_effort = high	79.5 %	estimated
o3 reasoning_effort = high	79 %	estimated
o4-mini reasoning_effort = high	76.5 %	estimated
Claude Sonnet 4 thinking budget = 59K	75.5 %	estimated
Claude 3.7 Sonnet thinking budget = 64K	74.5 %	estimated
Claude Opus 4 thinking budget = 16K	73.5 %	estimated
Grok 3.5 Mini (New)	73 %	estimated
Claude 3.5 Sonnet	54.5 %	estimated
Claude 3.5 Sonnet (New)	54 %	estimated

Max plan · API

GET https://viral-chart.com/api/posts/2a72683364a0.json
GET https://viral-chart.com/api/charts/2a72683364a0.json
GET https://viral-chart.com/api/charts/2a72683364a0.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 2a72683364a0.

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/2a72683364a0`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/2a72683364a0/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/2a72683364a0/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/2a72683364a0/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.