Harness comparisonAI Coding
Dynasty Warriors stage, Claude Code Opus vs Codex Sol — Claude Code (Claude Opus 5.5) vs OpenAI Codex (GPT-6.1 Sol)
Claude Code with Claude Opus 5.5 and Codex with GPT-6.1 Sol each build a full Dynasty Warriors-style stage from two prompts: a framework prompt, then a bug-fix and visuals pass.
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
- Dynasty Warriors stage, Claude Code Opus vs Codex Sol
- Category
- Games
- Mode
- Multi-turn
- Posted
- Video length
- 3.6 min (+1 more clip)
- Likes
- 3
- Views
- 85
- Bookmarks
- 0
- Sponsored
- No
Cost & time, as stated in the postAs stated: Opus 5.5 110 min + 280 min (6 h 40 min total, 2 h 33 min API time); GPT-6.1 Sol 32 min + about 7 h 30 min, 5 h 32 min actual work.
Related
Posted by @backerd_ceo5 on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
