Models
Anthropic
SWE-bench Verified accuracy for Claude models

@EpochAIResearchX · May 28, 2025

SWE-bench Verified accuracy for Claude models

@EpochAIResearch's benchmark bar chart drew 3.1K views on X: 0.6x @epochairesearch's median post and #1,029 of 1,162 AI chart posts we hold by views. Read Oct 12, 2026.

SWE-bench Verified accuracy for Claude Sonnet 4 and Opus 4 compared to other models

XData Benchmark bar chart Claude Opus 4 All Anthropic models GPT-4.1Claude Sonnet 3.7 SonnetClaude 3.5 Sonnet (New)Grok 3 Betao3-mini (medium)o4-mini (medium)GPT-4.1 Mini

@EpochAIResearch: SWE-bench Verified accuracy for Claude models — Published by @EpochAIResearch on X, May 28, 2025. Source: x.com

37/ 100

ViralChart score

Small but loved

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

#801 of 1,162 AI chart posts we hold · #35 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

The post sits in the Small but loved quadrant, at #801 of 1,162 AI chart posts by score.

Its 1.60% engagement rate sits in the 94th percentile among AI chart posts, against a 0.73% median.

It ranked #3 of 4 by views among @EpochAIResearch posts that day.

Benchmark bar charts drew 3.1K views here against a 44.4K median for the type, a 0.07x ratio.

0.1xthe median benchmark bar chart post

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

top 6%engagement rate

1.60% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

4posts from @epochairesearch that day

Part of a run of 4 posts on May 28, 2025. This one was #3 of 4 by views that day.

top 26%save rate

0.128% 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 #801 of 1,162

Views	3.1K	#1,029	bottom 11%
Likes	45	#885	bottom 24%
Engagement rate	1.60%	#76	top 6%
Save rate	0.128%	#301	top 26%

Among 59 @epochairesearch posts

Score #35 of 59

Views	3.1K	#38	bottom 36%
Likes	45	#35	bottom 42%
Engagement rate	1.60%	#22	top 36%
Save rate	0.128%	#31	bottom 48%

Growth

One read so far

Views3.1K

Age at our read502 days

Views per day of life6views 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 SWE-bench Verified accuracy for Claude models

A single benchmark bar chart with 9 models drew 3.1K views and a 1.60% engagement rate, above the 0.73% median among AI chart posts.

What happened

@EpochAIResearch posted a benchmark bar chart on May 28, 2025, covering SWE-bench Verified accuracy for Claude models. It was one of 4 posts from the account that day, alongside 3 others.

The numbers

The post reached 3.1K views, ranking #1,029 of 1,162 AI chart posts. Its score of 37 ranked #801 of 1,162 AI chart posts and #35 of 59 @EpochAIResearch posts.

The lesson

A benchmark bar chart with 9 models drew 3.1K views against a 44.4K median for the type, a 0.07x ratio. Its 1.60% engagement rate beat the 0.75% median for the type.

What it means

At #35 of 59 @EpochAIResearch posts by score, this chart sits below the account's own median engagement rate of 1.37%. The 3.1K views against the 39.9K median among AI chart posts show the gap.

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

18 points read off this chart

Estimated from the image 30%

Group	Value	Read
Claude Opus 4	57 %	estimated
Claude Opus 4	60 %	estimated
Claude Sonnet 3.7 Sonnet	53 %	estimated
Claude Sonnet 3.7 Sonnet	56 %	estimated
Claude 3.5 Sonnet	49 %	estimated
Claude 3.5 Sonnet	51 %	estimated
GPT-4.1	38 %	estimated
GPT-4.1	40 %	estimated
Grok 3 Beta	36 %	estimated
Grok 3 Beta	38 %	estimated
o3-mini (medium)	35 %	estimated
o3-mini (medium)	37 %	estimated

Showing 12 of 18. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/4d4db571600a.json
GET https://viral-chart.com/api/charts/4d4db571600a.json
GET https://viral-chart.com/api/charts/4d4db571600a.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 4d4db571600a.

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/4d4db571600a`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/4d4db571600a/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/4d4db571600a/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/4d4db571600a/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.