aivs.tv

Harness comparisonAI Coding

Ink-wash landscape, three agents blind guess — OpenAI Codex (GPT-6.1 Sol) vs Pi (Gemini 4 Argon) vs Claude Code (Claude Opus 5.5)

0:00 / 0:15
Posted byAgentSky@agentsky_dev · on X
View post on X

0 likes80 views

Scoreboard3

  1. GPT-6.1 SolOpenAIOpenAI Codex
    Time
    106 s
    Cost
    $0.08
  2. Gemini 4 ArgonGooglePi
    Time
    4.6 min
    Cost
    $0.52
  3. Claude Opus 5.5AnthropicClaude Code
    Time
    7.6 min
    Cost
    $1.20

Prompt

Ink-wash landscape, three agents blind guessThe post doesn’t quote the prompt wording.

Codex with GPT-6.1 Sol, pi with Gemini 4 Argon and Claude Code with Opus 5.5 get the same ink-wash landscape prompt, shown as A, B and C before a reveal with time and cost.

Each side pairs a coding harness with its own model, so harness and model differences are mixed. More Claude Code vs OpenAI Codex. More OpenAI Codex vs Pi. More Claude Code vs Pi. All harness comparisons.

The post, itemised

Task
Ink-wash landscape, three agents blind guess
Mode
Not stated
Posted
Video length
15 s
Likes
0
Views
80
Bookmarks
0
Sponsored
No

Cost & time, as stated in the postAs stated: Codex (GPT-6.1 Sol) 1 min 46 s, $0.08; pi (Gemini 4 Argon) 4 min 36 s, $0.52; Claude Code (Opus 5.5) 7 min 36 s, $1.20.

Related

GPT-6.1 SolGemini 4 ArgonClaude Opus 5.5Compare all 3 modelsClaude Opus 5.5 vs Gemini 4 ArgonClaude Opus 5.5 vs GPT-6.1 SolGemini 4 Argon vs GPT-6.1 Sol

Posted by @agentsky_dev 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