- Giants
- Artificial Analysis
- AI model output speed
AI model output speed
Artificial Analysis's benchmark bar chart drew 80K views on X: 1.5x its typical post and #44 of 123 Artificial Analysis charts we track by views. Read Oct 10, 2026.
Inception Labs has launched the first production-ready Diffusion LLMs. Mercury Coder Mini achieves >1,000 output tokens/s on coding tasks while running on NVIDIA H100s - over 5x faster than competitive autoregressive LLMs on similar hardwar
Why it spread
This chart post spread because it rode a hot topic that week, the launch of the first production-ready Diffusion LLMs, and came from an independent author, @ArtificialAnlys, reaching 79,954 views, 366 likes, 53 reposts, 9 quotes and 130 saves.
What worked
- The post leads with a concrete, striking claim: Mercury Coder Mini achieves over 1,000 output tokens per second on coding tasks while running on NVIDIA H100s, over 5x faster than competitive autoregressive LLMs on similar hardware.
- The chart is a benchmark-bars ranking of output speed across AI models, showing smaller models as faster, which makes the comparison easy to grasp at a glance.
- It is branded, carries a source line, and comes from an independent author, which supports credibility even though the quote rate is below average.
What to borrow
We could use the same benchmark-bars ranking form and lead with one clear speed or performance claim, then show our own models ranked against competitors on similar hardware, keeping a visible source line and brand mark.
Careful
Do not over-read the spread as proof of design quality, since design polish and self-labelling are only medium and the quote rate is below average; the lift likely came mostly from the hot topic and the independent author, not from the chart alone.
Written by our analysis model from the measured numbers above, not by Artificial Analysis.
Make it yours
Your numbers, in this bar chart.
Starts from the real numbers of "Output Tokens per Second: Smaller models" by Artificial Analysis. 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 d7be269b6054.
| Path | Returns | Plan | |
|---|---|---|---|
| GET | /api/v1/charts/d7be269b6054 | Title, publisher, date, form, point count; with a Max key, the data link | Open |
| GET | /api/v1/charts/d7be269b6054/data | Every point with its provenance and confidence, plus the redraw spec. Add ?format=csv for CSV | Max |
| GET | /api/v1/charts/d7be269b6054/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/d7be269b6054/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 Artificial Analysis
All 123
Other giants using a benchmark bar chart
All 136
Questions people ask
How far did Artificial Analysis's "AI model output speed" chart travel?
79,954 views, 366 likes, 53 reposts and 130 saves on X, read Oct 10, 2026. A normal post from @ArtificialAnlys gets about 54.2K views.
What kind of chart is it?
A benchmark bar chart. Output speed ranking of AI models, smaller models faster.
Can I use Artificial Analysis's chart?
Use the format, not the picture. The chart, logo and design belong to Artificial Analysis. ViralChart redraws the chart type with your numbers and words, and credits the original publisher.