
AI model task horizon
METR's scatter plot drew 1.4M views on X: 8.9x its typical post and #4 of 26 METR charts we track by views. Read Oct 10, 2026.
We estimate that, on our tasks, Claude Opus 4.5 has a 50%-time horizon of around 4 hrs 49 mins (95% confidence interval of 1 hr 49 mins to 20 hrs 25 mins). While we're still working through evaluations for other recent models, this is our h
Why it spread
This post spread because it announced the highest published time horizon to date, with 1,354,394 views, 1,997 likes, 265 reposts, 200 quotes, and 546 saves, driven by many quotes and an independent author.
What worked
- The post leads with a concrete, headline-friendly result: a fifty percent time horizon of around four hours forty-nine minutes, with a confidence interval from one hour forty-nine minutes to twenty hours twenty-five minutes.
- The chart type is a scatter plot showing task time horizon growing exponentially with model release date, which makes the exponential trend easy to grasp at a glance.
- The post is self-labelling and branded, includes a source line, and comes from consequence-free independent author status, which together support trust and sharing.
What to borrow
We could use the same form by pairing a single striking horizon estimate with a scatter plot that shows exponential growth over release dates, and by clearly labelling the chart and source line.
Careful
Do not copy the specific numbers or treat the confidence interval as precise, and do not over-read the quote rate or source reach as proof of universal agreement.
Written by our analysis model from the measured numbers above, not by METR.
Make it yours
We have not read this chart's numbers yet
Its own maker appears here once its numbers are read. Until then, these are other real charts in a similar format: each data page starts from that chart's numbers and takes yours.
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 44e8ba0e6c7b.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/44e8ba0e6c7b | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/44e8ba0e6c7b/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/44e8ba0e6c7b/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 |
curl -s https://viral-chart.com/api/v1/charts/44e8ba0e6c7b/data \
-H "Authorization: Bearer $VIRALCHART_KEY"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 from METR
All 26Other giants using a scatter plot
All 78Questions people ask
How far did METR's "AI model task horizon" chart travel?
1,354,394 views, 1,997 likes, 265 reposts and 546 saves on X, read Oct 10, 2026. A normal post from @METR_Evals gets about 153K views.
What kind of chart is it?
A scatter plot. Task time horizon grows exponentially with model release date.
Can I use METR's chart?
Use the format, not the picture. The chart, logo and design belong to METR. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.



