aivs.tv

AI Coding

The Lighthouse benchmark, four frontier models — Gemini 4 Argon vs Claude Sonnet 5.5 vs Claude Opus 5.5 vs GPT-6 Astra

0:00 / 0:25
Gemini 4 Argon (top left)
Posted byTony@EnvolDev · on X
View post on X

12 likes599 views

Scoreboard4

  1. Gemini 4 ArgonGoogle
    Author’s pick
    Time
    1 h 48 min
    Cost
    $6.30
    • Top left; labelled “Gemini Argon 4” on screen
  2. Claude Sonnet 5.5Anthropic
    Time
    2 h 42 min
    Cost
    $29.90
    • Top right
  3. Claude Opus 5.5Anthropic
    Time
    2 h 44 min
    Cost
    $53.57
    • Bottom left
  4. GPT-6 AstraOpenAI
    Time
    2 h 29 min
    Cost
    $42.28
    • Bottom right

Prompt

The Lighthouse benchmark, four frontier modelsThe post doesn’t quote the prompt wording.

Author’s verdict
Gemini 4 Argon blew the author away again: the glowing lantern and turquoise waves for $6.30, about 8 times cheaper than Opus.

@EnvolDev’s view (paraphrased)

Gemini 4 Argon (top left), Claude Sonnet 5.5 (top right), Claude Opus 5.5 (bottom left) and GPT-6 Astra (bottom right) run the author’s Lighthouse benchmark with the same prompt at XHigh effort, shown in a 2×2 grid.

The post, itemised

Kind
Side-by-side
Task
The Lighthouse benchmark, four frontier models
Category
3D & Shaders
Mode
Not stated
Posted
Video length
25 s
Likes
12
Views
599
Bookmarks
1
Sponsored
No

Cost & time, as stated in the postAs stated: Gemini 4 Argon $6.30 and 1 h 47 min; Claude Sonnet 5.5 $29.90 and 2 h 41 min; Claude Opus 5.5 $53.57 and 2 h 44 min; GPT-6 Astra $42.28 and 2 h 29 min.

Related

Gemini 4 ArgonClaude Sonnet 5.5Claude Opus 5.5GPT-6 AstraCompare all 4 modelsClaude Opus 5.5 vs Claude Sonnet 5.5Claude Opus 5.5 vs Gemini 4 ArgonClaude Opus 5.5 vs GPT-6 AstraClaude Sonnet 5.5 vs Gemini 4 ArgonClaude Sonnet 5.5 vs GPT-6 AstraGemini 4 Argon vs GPT-6 Astra

Posted by @EnvolDev 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