AI task length scaling
METR's scatter plot drew 141.6K views on X: 1.3x @metr_evals's median post and #326 of 1,162 AI chart posts we hold by views. Read Oct 10, 2026.
We estimate that Kimi K2 Thinking has a 50%-time-horizon of around 54 minutes (95% confidence interval of 25 to 100 minutes) on our agentic SWE tasks. Note that we conducted this evaluation through a third-party inference provider, which re
Why it spread
This post spread because it paired a hot topic that week with a chart that explains itself, reaching 141,614 views, 281 likes, 25 reposts, 12 quotes, and 44 saves, though likes stayed below the account's typical 523.
What worked
- The post explains itself, so viewers could grasp the exponential growth of AI task time horizon with model release without extra context.
- It rode a hot topic that week, which drove a quote rate above average and a source reach in the top quarter.
- It was branded, showed a source line, and used high self labelling, which made the estimate easy to trust and share.
What to borrow
We could frame our own chart around a timely topic and let the chart explain itself, with clear self labelling and a visible source line, so the audience can read the trend without a long caption.
Careful
Do not over-read the like count as a win, since 281 likes came in below the account's typical 523, and do not treat the estimate as fully certain because it came through a third-party inference provider.
Written by our analysis model from the measured numbers above, not by METR.
Make it yours
Your numbers, the bar chart way.
Starts from the real numbers of "Task length Thinking (at 50% success rate)" by METR. Replace every number with yours before you post. Make one like this, step by step
Free pictures carry a small "Made with ViralChart" line. That line is how other people find us.
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 a5be200001c0.
Approximate values. Our two readings of this chart agreed only in part (confidence 0.43 of 1), so check the original before you quote a number. The API marks it lowConfidence, and ?min_confidence=0.5 leaves it out.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/a5be200001c0 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/a5be200001c0/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/a5be200001c0/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/a5be200001c0/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 26
Other giants using a scatter plot
All 78
Questions people ask
How far did METR's "AI task length scaling" chart travel?
141,614 views, 281 likes, 25 reposts and 44 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. AI task time horizon grows exponentially with model release.
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.