AI Coding
Sailing course control test, four models — Gemini 4 Argon vs GPT-6 Astra vs Claude Opus 5.5
Scoreboard3
- Gemini 4 ArgonGoogleAuthor’s pick
- GPT-6 AstraOpenAI
- Claude Opus 5.5Anthropic
Prompt
Sailing course control test, four modelsThe post doesn’t quote the prompt wording.
Gemini 4 Argon finished first, GPT-6 Astra made it just under the limit, and Claude Opus 5.5 timed out short of mark 1.
@HarshithLucky3’s view (paraphrased)
Gemini 4 Argon, GPT-6 Astra, Claude Opus 5.5 and Qwen3.5-9B each sail the same course, upwind to mark 1 and back to mark 2, within 15 minutes, shown together on one map.
The post, itemised
- Kind
- Side-by-side
- Task
- Sailing course control test, four models
- Category
- Simulations
- Mode
- Not stated
- Posted
- Video length
- 37.5 s
- Likes
- 36
- Views
- 3,842
- Bookmarks
- 9
- Sponsored
- No
NotesThe Qwen3.5-9B run is not tagged here. Per the video, Argon finished in 783 s, Astra in 899 s, Opus ran out of time and Qwen ran aground.
Related
Posted by @HarshithLucky3 on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
