Claude 3.7 Sonnet code success
METR's bar chart drew 153K views on X: 1.0x its typical post and #13 of 26 METR charts we track by views. Read Oct 10, 2026.
We tested how autonomous AI agents perform on real software tasks from our recent developer productivity RCT.
Why it spread
It spread because the post paired a striking real-world gap between passing tests and mergeable code with strong quote activity and an independent author, drawing 152,963 views, 550 likes, 72 reposts, 30 quotes, and 256 saves.
What worked
- The bar chart makes a single contrast easy to grasp: Claude passes tests but is not mergeable on real tasks.
- The post text frames the finding as a gap between algorithmic scoring and real-world usability, which invites discussion and quoting.
- The chart is branded, shows a source line, and is self-labelling, so viewers can trust and share it without extra context.
What to borrow
We could use the same form by taking one of our own benchmark results and showing a simple bar contrast between a test score and a real-world outcome, then framing it as a gap that explains why benchmarks feel disconnected.
Careful
Do not over-read the quote rate or source reach as proof of universal agreement, and do not copy the exact framing without checking whether our own data actually shows a similar test-versus-reality gap.
Written by our analysis model from the measured numbers above, not by METR.
Make it yours
Your numbers, in this bar chart.
Starts from the real numbers of "On 3.7 Sonnet real software writes code engineering that passes test cases, Claude but is " 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 30ec9547a68e.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/30ec9547a68e | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/30ec9547a68e/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/30ec9547a68e/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/30ec9547a68e/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 bar chart
All 152
Questions people ask
How far did METR's "Claude 3.7 Sonnet code success" chart travel?
152,963 views, 550 likes, 72 reposts and 256 saves on X, read Oct 10, 2026. A normal post from @METR_Evals gets about 153K views.
What kind of chart is it?
A bar chart. Claude passes tests but not mergeable on real tasks.
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.