aivs.tv

Harness comparisonAI Coding

Event-driven backend scaffold, two harnesses — Claude Code (Claude Opus 5.5) vs OpenAI Codex (GPT-6.1 Terra)

0:00 / 0:30
Posted byStanislav Sorokin@stas_sorokin_ · on X
View post on X

5 likes584 views

Scoreboard2

  1. Claude Opus 5.5AnthropicClaude Code
  2. GPT-6.1 TerraOpenAIOpenAI Codex

Prompt

Event-driven backend scaffold, two harnessesThe post doesn’t quote the prompt wording.

Claude Code (Claude Opus 5.5) and Codex (GPT-6.1 Terra) get the same event-driven backend prompt in an empty repo: Claude Code kept events in memory in 6 of 6 runs, Codex wrote them to disk in 10 of 10.

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
Event-driven backend scaffold, two harnesses
Category
Web/UI
Mode
Not stated
Posted
Video length
30 s
Likes
5
Views
584
Bookmarks
0
Sponsored
No

NotesThe video is an animated summary of the 16 scaffolds, not the apps themselves.

Related

Claude Opus 5.5GPT-6.1 TerraClaude Opus 5.5 vs GPT-6.1 Terra

Posted by @stas_sorokin_ 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