aivs.tv

AI Coding

Mechanical watch assembly video, three models — GPT-6.1 Terra vs GPT-6.1 Sol vs Claude Opus 5.5

0:00 / 1:20
Posted by@kupi_fx@kupi_fx · on X
View post on X

0 likes65 views

Scoreboard3

  1. GPT-6.1 TerraOpenAI
    Time
    12.2 min
    • Effort Max
  2. GPT-6.1 SolOpenAI
    Time
    38.5 min
    • Effort Max
  3. Claude Opus 5.5Anthropic
    Time
    1 h 25 min
    • Effort Max

Prompt

Mechanical watch assembly video, three modelsThe post doesn’t quote the prompt wording.

GPT-6.1 Terra, GPT-6.1 Sol and Claude Opus 5.5, all at Max, get the exact same instruction: a 20-second video of a mechanical watch assembling from loose parts and starting to run, as close to a real watch as possible.

The post, itemised

Kind
Side-by-side
Task
Mechanical watch assembly video, three models
Mode
Not stated
Posted
Video length
80 s
Likes
0
Views
65
Bookmarks
0
Sponsored
No

NotesThe poster re-ran the test in clean folders after Sol built on Terra's files in the first attempt, and asks watch experts which mechanism is most accurate; no winner named.

Cost & time, as stated in the postAs stated: GPT-6.1 Terra 12 min 13 s, GPT-6.1 Sol 38 min 29 s, Claude Opus 5.5 about 1 h 25 min.

Related

GPT-6.1 TerraGPT-6.1 SolClaude Opus 5.5Compare all 3 modelsClaude Opus 5.5 vs GPT-6.1 SolClaude Opus 5.5 vs GPT-6.1 TerraGPT-6.1 Sol vs GPT-6.1 Terra

Posted by @kupi_fx on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal

More with these models