1. Chart data
  2. Complex often was easier to detect in CoT
METRGrouped bar chart · 14 points · METR

Complex often was easier to detect in CoT

The numbers behind a chart METR published, redrawn natively. Check the original, study the data, then make your own.

Estimated from the image 83%All chart data
Chart by METR. Source: x.com

Simplified redraw

Drawn by us from the numbers below. Hover, tap or use the arrow keys.

A simplified redraw: it shows the numbers in our own look, not the look of the original. One accent marks what the chart is about. Values marked with ~ in the table are estimates.

The numbers

First 10 of 14 points are free
GroupSeriesValueSourceConf.
Reasoning that can occur in a forward passClaude 3.7 Sonnet10.93%Estimate0.97
Reasoning that can occur in a forward passClaude Opus 412.93%Estimate0.97
Reasoning that can occur in a forward passQwen 3-235B~0.59%Estimate0.50
Reasoning that must use the CoTClaude 3.7 Sonnet0.225%Estimate0.90
Reasoning that must use the CoTClaude Opus 40.055%Estimate0.97
Reasoning that must use the CoTQwen 3-235B0.37%Estimate0.97
Reasoning that can occur in a forward passClaude 3.7 Sonnet1.58%Estimate0.97
Reasoning that can occur in a forward passClaude Opus 42.03%Estimate0.97
Reasoning that can occur in a forward passQwen 3-235B~0.4%Estimate0.50
Reasoning that must use the CoTClaude 3.7 Sonnet0.535%Estimate0.97

Max data, free with your email for now

See all 14 points and download the files

The full table, the JSON, a CSV and the agent skill file for this chart. These are Max in the plan; while this is a prototype your email unlocks them.

Unlocks all 35 giants. One email a week, leave any time. What you get · Log in

Reasoning that must use the CoTClaude Opus 40.43%Estimate0.97
Reasoning that must use the CoTQwen 3-235B0.74%Estimate0.97
Reasoning that must use the CoTQwen 3-235B~0.06%Estimate0.50
Reasoning that must use the CoTQwen 3-235B~0.38%Estimate0.50
Download this chart's data

Max subscribers get the same data by API. API docs

JSONAgent skill file

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 ab142ec03b93.

See the Max planAPI docs
PathReturnsPlan
GET/api/v1/charts/ab142ec03b93Title, publisher, date, form, point count; with a Max key, the data linkOpen
GET/api/v1/charts/ab142ec03b93/dataEvery point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSVMax
GET/api/v1/charts/ab142ec03b93/render?view=1The draw-only view this page usesOpen
POST/mcpTool get_chart_data with this id, for Claude, Cursor and other agentsMax
curlMax
curl -s https://viral-chart.com/api/v1/charts/ab142ec03b93/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.

Make one like this

This chart's shape, your numbers.

Live preview. Everything stays on your device.

Pick the form

A simplified form: our own look, not the look of the original. Your numbers start from this chart's data.

More data from METR

All chart data
Estimated from the imageTask length (at 50% tasks success Als can do) is doubling every 7 monthsMETR · Scatter plot · 7 pointsEstimated from the imageAverage speedup on kernel optimization tasks, by model and elicitation methodMETR · Line chart · 12 pointsEstimated from the imageOn 3.7 Sonnet real software writes code engineering that passes test cases, Claude but is not mergeableMETR · Bar chart · 2 pointsEstimated from the imageTask length (at 50% success-time horizon)METR · Scatter plot · 14 pointsEstimated from the imageTask length (at 50% success-time-horizon)METR · Scatter plot · 19 pointsEstimated from the imageTask-5.4 (xhigh) has a 50% success-time-horizon of about 5.7 hours (95% CI: 3 hrs to 13.5 hrs)METR · Scatter plot · 11 points

Questions people ask

How accurate are these numbers?

They are estimated from the image by two independent passes, with confidence 0.83 on a 0 to 1 scale. Printed numbers read well; values read off an axis can be a few percent off.

Can I reuse this data?

The numbers describe a chart that METR published. The image, layout and styling belong to them. Use the numbers with a credit to the publisher, and make your picture from your own data.

How do I get the file?

The JSON, CSV and agent skill file are under the email gate on this page. In this prototype they are static files at /api/charts/ab142ec03b93.json and /api/charts/ab142ec03b93.skill.md.