Harness comparisonAI Coding

Blender sailing scene, Opus in Claude Code vs Sol in Codex — Claude Code (Claude Opus 5.5) vs OpenAI Codex (GPT-6.1 Sol)

0:00 / 0:12
Claude Opus 5.5 in Claude Code (top)
Posted byCole👽@colerepo · on X
View post on X

7 likes191 views

Scoreboard2

  1. Claude Opus 5.5AnthropicClaude Code
    Cost
    $14.78
  2. GPT-6.1 SolOpenAIOpenAI Codex
    Cost
    $7.72

Prompt

Blender sailing scene, Opus in Claude Code vs Sol in CodexThe post doesn’t quote the prompt wording.

Claude Opus 5.5 in Claude Code (top) and GPT-6.1 Sol in Codex (bottom) get the same Blender brief and asset folder, each writing the scene in Python on high reasoning. One scene per model, not a benchmark.

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

The post, itemised

Task
Blender sailing scene, Opus in Claude Code vs Sol in Codex
Mode
Not stated
Posted
Video length
12 s
Likes
7
Views
191
Bookmarks
0
Sponsored
No

NotesThe poster says one scene per model, so not a benchmark; no winner named.

Cost & time, as stated in the postAs stated (estimated API-equivalent cost from token usage, run on subscriptions): Opus $14.78, Sol $7.72; Cycles render 18.5 s/frame vs 15.4 s/frame.

Related

Posted by @colerepo 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