AI model task time scaling
METR's scatter plot drew 125.3K views on X: 0.8x its typical post and #16 of 26 METR charts we track by views. Read Oct 10, 2026.
We’ve started to measure time horizons for recent models using our updated methodology. On this expanded suite of software tasks, we estimate that Gemini 3 Pro has a 50%-time-horizon of around 4 hrs (95% CI of 2 hr 10 mins to 7 hrs 20 mins)
Why it spread
This post spread because it explains itself and landed at launch timing, with 438 likes, 44 reposts, 18 quotes, 88 saves, and 125,271 views, even though the account typically gets 523 likes.
What worked
- The chart explains itself: a scatter plot showing AI model task time growing exponentially with release date, with high self labelling and a source line.
- The post text gives a concrete measured number, a 50 percent time horizon of around 4 hrs with a 95 percent confidence interval of 2 hr 10 mins to 7 hrs 20 mins, which makes the claim easy to repeat.
- Launch timing helped: the post is dated 2026-02-03 and is branded, with above average quote rate and top quarter source reach.
What to borrow
We could use the same self explaining scatter form and launch timing framing for our own data, pairing one clear measured number with a confidence interval and a visible source line.
Careful
Do not copy the exact numbers talents or over read the spread as proof of quality, since the account got fewer likes than its typical 523 and the chart is only medium design polish with low unusual form.
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 (at a 50%-success-time-horizon)" 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 a2048c23d4e2.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/a2048c23d4e2 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/a2048c23d4e2/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/a2048c23d4e2/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/a2048c23d4e2/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 model task time scaling" chart travel?
125,271 views, 438 likes, 44 reposts and 88 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 model task time grows exponentially with 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.