AI model task time trends
METR's scatter plot drew 113.1K views on X: 1.0x @metr_evals's median post and #358 of 1,162 AI chart posts we hold by views. Read Oct 10, 2026.
METR tested pre-release versions of o3 + o4-mini on tasks involving autonomy and AI R&D. For each model, we examined how capable it is on our tasks & how often it tries to “hack” them. We detail our findings in a new report, a summa
Why it spread
The post spread because it paired a timely OpenAI model release with a scatter chart showing that o3 may be above-trend for software task time horizons, drawing 438 likes, 60 reposts, 32 quotes, 160 saves and 113,083 views.
What worked
- The chart makes a single clear claim about o3 being above-trend for software task time horizons, which is easy to grasp and repeat.
- The post ties the chart to a new report and to OpenAI's system card, giving readers a credible source and a reason to save or share it.
- The account is an independent author in the ai-bench category, and the post earned a top quarter quote rate, so the framing invited discussion rather than just passive likes.
What to borrow
We could take one timely model or product release, plot our own task results as a scatter with a visible trend line, and label the one point that stands out, then link it to a fuller report.
Careful
Do not copy the exact claim that o3 is above-trend, and do not over-read the quote rate as proof of quality, since many quotes can also mean disagreement.
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 "OpenAI's o3 may be above-trend for software task time horizons" 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 8747d675e2b4.
Approximate values. Our two readings of this chart agreed only in part (confidence 0.39 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/8747d675e2b4 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/8747d675e2b4/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/8747d675e2b4/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/8747d675e2b4/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 trends" chart travel?
113,083 views, 438 likes, 60 reposts and 160 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. OpenAI o3 may be above-trend for software task time horizons.
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.