Long answers were cut off
The ranked run capped answers at 512 to 4,096 tokens. Many long answers stopped mid-sentence and were scored as written.
AI & Home Lab · Bench
Eight open models ran on one ASUS GX10 that sits on a desk. Five paid cloud models ran the same nine jobs, with the same limits, and a judge that never saw a name. Here is who did the work best, who was fastest, and what it cost.
Best on the desk
–
Best in the cloud
–
Quality out of 100: the middle of 19 judged answers per model.
1 · Quality
The top two are cloud models. Right behind them are two open models running at home, ahead of three paid cloud models. Pick any model to see where its points came from.
2 · Nine jobs
Stronger color means a higher score. A ring marks the best score on each job.
3 · Time
Log scale. Every model wrote the same 57 answers under the same length limits.
Tokens written per second once the answer starts. A token is about three quarters of a word. Green is DeepSeek split across two GX10s. It has not been judged yet, so it is not in the ranking.
4 · Cost
And the desk?
No bill per answer. The GX10 draws wall power, and that has not been measured under load yet.
An idle reading would flatter it, so there is no local dollar figure on this page. When the meter is on, it will appear here.
What the desk gives you instead
Your prompts never leave the room, and the model files (7 to 104 GiB here) are yours to keep.
5 · The pictures
Two of the jobs ask for a picture. For these, every model got room to finish: up to 100,000 tokens. Each picture is exactly what the model wrote, drawn in a browser. Nothing was touched up.
Desk models: their one uncapped pass. Cloud models: the first of three runs. Tap a picture to see it larger.
6 · Fine print
The ranked run capped answers at 512 to 4,096 tokens. Many long answers stopped mid-sentence and were scored as written.
Grok 4.7 scored the text. It never opened a page or ran the code. At the old limit, no model's Mustang page showed a car on screen.
Thinking was off where a model allowed it. GPT-6.1 Sol, Claude Sonnet 5.5 and Claude Opus 5.5 cannot turn it fully off, so they used their lowest setting.
Gemini 4 Hydrogen and the two-GX10 DeepSeek have answers but no judge score. Power draw under load is not measured.
Room to finish (100,000 tokens for the picture jobs, 30,000 for the rest), checks that run the code and open the pages, a scored DeepSeek on two GX10s, Gemini judged, and a watt meter on the desk.