aivs.tv

Harness comparisonAI Coding

Animated short made in code, three agents — OpenAI Codex (GPT-6.1 Sol) vs Pi (Gemini 4 Argon) vs Claude Code (Claude Opus 5.5)

0:00 / 0:16
Posted byAgentSky@agentsky_dev · on X
View post on X

1 likes112 views

Scoreboard3

  1. GPT-6.1 SolOpenAIOpenAI Codex
    Time
    3.4 min
  2. Gemini 4 ArgonGooglePi
    Time
    4 min
  3. Claude Opus 5.5AnthropicClaude Code
    Time
    38.5 min

Prompt

Animated short made in code, three agentsThe post doesn’t quote the prompt wording.

One prompt for a 24-second animated short made entirely in code, run in three agents: Codex with GPT-6.1 Sol, pi with Gemini 4 Argon and Claude Code with Claude Opus 5.5.

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
Animated short made in code, three agents
Mode
Not stated
Posted
Video length
16 s
Likes
1
Views
112
Bookmarks
0
Sponsored
No

NotesThe poster asks viewers to pick; no winner named.

Cost & time, as stated in the postAs stated: Codex (GPT-6.1 Sol) 3 min 24 s, 6,810 tokens; pi (Gemini 4 Argon) 3 min 59 s, 14,552 tokens; Claude Code (Claude Opus 5.5) 38 min 31 s, 87,838 tokens.

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