AI model task time
METR's scatter plot drew 82.8K views on X: 0.5x its typical post and #21 of 26 METR charts we track by views. Read Oct 10, 2026.
We found that Grok 4’s 50%-time-horizon on our agentic multi-step software engineering tasks is about 1hr 50min (with a 95% CI of 48min to 3hr 52min) compared to o3 (previous SOTA) at about 1hr 30min. However, Grok 4’s time horizon is below
Why it spread
It spread because the post paired a timely Grok 4 launch with a striking time-horizon claim of about 1hr 50min against o3 at about 1hr 30min, drawing 311 likes, 22 reposts, 21 quotes, 91 saves and 82,802 views, with quotes landing in the top quarter of the account's posts.
What worked
- The headline number is concrete and easy to repeat: about 1hr 50min with a 95% CI of 48min to 3hr 52min, set against o3 at about 1hr 30min.
- The post adds a caveat that Grok 4 falls below SOTA at higher success rate thresholds, which invites discussion and quoting rather than a simple cheer.
- The chart is a branded scatter showing AI model task time growing exponentially with release date, with a source line and medium design polish, so it reads as evidence rather than a bare claim.
What to borrow
We can frame our own chart around one headline time or threshold, show the previous best beside it, state the uncertainty range plainly, and add one honest limitation so people have something to quote.
Careful
Do not over-read the spread as proof the chart design caused it, since launch timing and many quotes are listed as main reasons, and do not treat the account's typical likes as a baseline the post beat, because it drew fewer likes than that typical level.
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 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 a481f599f742.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/a481f599f742 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/a481f599f742/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/a481f599f742/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/a481f599f742/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" chart travel?
82,802 views, 311 likes, 22 reposts and 91 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.