Models
Anthropic
AI Model Benchmark Comparison

AnthropicX · Feb 5, 2026 · official

AI Model Benchmark Comparison

Anthropic's table chart drew 751.8K views on X: 1.7x its median post and #115 of 1,162 AI chart posts we hold by views. Read Oct 13, 2026.

AI model performance comparison across multiple benchmarks

XData Table chart Claude Code All Anthropic models Gemini 3 ProOpus 4.6Opus 4.5Sonnet 4.5GPT-5.2

Anthropic: AI Model Benchmark Comparison — Published by Anthropic on X, Feb 5, 2026. Source: x.com

77/ 100

ViralChart score

Wide but thin

More views than the median post but a lower engagement rate: many saw it, few acted. Common for big accounts.

#97 of 1,162 AI chart posts we hold · #13 of 56 Anthropic 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 Wide but thin quadrant, with a score rank of #97 of 1,162 AI chart posts.

Its score of 77 ranks #97 of 1,162 AI chart posts and #13 of 56 Anthropic posts.

The post's 752K views are 1.7x Anthropic's 431K median, ranking #21 of 56 Anthropic posts.

Table charts have a 133K median; this one drew 752K, a 5.6x gap, with 0.62% engagement against a 0.61% median.

5.6xthe median table chart post

Across 95 table chart posts we hold, the median gets 133.2K views.

0.40views per follower

751.8K views from an account with 1.9M followers.

1.7xAnthropic's median post

751.8K views, where Anthropic's typical post gets 431K.

bottom 40%engagement rate

0.62% of viewers liked, reposted, quoted or replied. The median post gets 0.73%.

Public X numbers from our read on Oct 13, 2026. Peers: 1,162 AI chart posts we hold and 56 from Anthropic.

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 #97 of 1,162

Views	751.8K	#115	top 10%
Likes	4.1K	#73	top 6%
Engagement rate	0.62%	#695	bottom 40%
Save rate	0.072%	#610	bottom 48%

Among 56 Anthropic posts

Score #13 of 56

Views	751.8K	#21	top 37%
Likes	4.1K	#17	top 29%
Engagement rate	0.62%	#23	top 40%
Save rate	0.072%	#12	top 21%

Growth

Our reads cover 27 hours

Views751.8K

Age at our read250 days

Views per day of life3Kviews divided by days since it was posted

Gained between our reads+11views over 27 hours, about 10 a day now

Dots are our reads. The dotted line from the day it was posted to our first read is a gap, not data.

Anthropic'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 · Feb 5, 2026 · Lead story

Anthropic posts AI model benchmark comparison table chart

Anthropic's February 5, 2026 table chart drew 752K views, 1.7x its own median, but engagement stayed below the AI chart median.

What happened

Anthropic, an official account, posted a table chart on February 5, 2026, comparing AI model performance across benchmarks. It was the account's only post that day.

The numbers

The post reached 752K views, ranking #115 of 1,162 AI chart posts and #21 of 56 Anthropic posts. Its score of 77 ranks #97 of 1,162 AI chart posts.

The lesson

A table chart with 5 models shown drew 752K views against a 133K median for table charts, a 5.6x gap, while engagement of 0.62% sat near the 0.61% median for the type.

What it means

For Anthropic, 752K views is 1.7x its 431K median, but the 0.62% engagement rate places the post below the AI chart median, so wide reach did not carry engagement.

Written by ViralChart from public numbers read on Oct 13, 2026. Every number is checked against our data before it is shown.

Updates: what Anthropic posted next

Data and API

77 points read off this chart

Estimated from the image 82%

Series	Group	Value	Read
Opus 4.6	Agentic terminal coding (Terminal-Bench 2.0)	65.4 %	printed
Opus 4.5	Agentic terminal coding (Terminal-Bench 2.0)	59.8 %	printed
Sonnet 4.5	Agentic terminal coding (Terminal-Bench 2.0)	51 %	printed
Gemini 3 Pro	Agentic terminal coding (Terminal-Bench 2.0)	56.2 %	printed
GPT-5 (all models)	Agentic terminal coding (Terminal-Bench 2.0)	64.7 %	printed
Opus 4.6	Agentic coding (SWE-bench Verified)	80.8 %	printed
Opus 4.5	Agentic coding (SWE-bench Verified)	80.9 %	printed
Sonnet 4.5	Agentic coding (SWE-bench Verified)	77.2 %	printed
Gemini 3 Pro	Agentic coding (SWE-bench Verified)	76.2 %	printed
GPT-5 (all models)	Agentic coding (SWE-bench Verified)	80 %	printed
Opus 4.6	Agentic computer use (OSWorld)	72.7 %	printed
Opus 4.5	Agentic computer use (OSWorld)	66.3 %	printed

Showing 12 of 77. All points, the redraw and the maker

Max plan · API

GET https://viral-chart.com/api/posts/99900de8b864.json
GET https://viral-chart.com/api/charts/99900de8b864.json
GET https://viral-chart.com/api/charts/99900de8b864.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 99900de8b864.

See the Max plan API docs

	Path	Returns	Plan
GET	`/api/v1/charts/99900de8b864`	Title, publisher, date, form, point count; with a Max key, the data link	Open
GET	`/api/v1/charts/99900de8b864/data`	Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV	Max
GET	`/api/v1/charts/99900de8b864/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/99900de8b864/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.