Harness comparisonAI Coding
GPU showcase website from given image assets, four models — DeepSeek Harness (DeepSeek V4.1 Flash 1017) vs OpenAI Codex (GPT-6 Luna) vs Claude Code (Claude Haiku 5.5) vs OpenCode (MiniMax M3.1 Flash)
Scoreboard4
- DeepSeek V4.1 Flash 1017DeepSeekDeepSeek Harness
- Time
- 34 min
- Effort Max
- Top left
- GPT-6 LunaOpenAIOpenAI Codex
- Time
- 3.3 min
- Effort Max
- Top right
- Claude Haiku 5.5AnthropicClaude Code
- Time
- 36.3 min
- Effort Max
- Bottom left
- MiniMax M3.1 FlashMiniMaxOpenCode
- Time
- 2 h 28 min
- Effort Max
- Bottom right; the author says it had the site done at about 34 min and kept fixing small things
Prompt
GPU showcase website from given image assets, four modelsThe post doesn’t quote the prompt wording.
DeepSeek V4.1 Flash 1017, GPT-6 Luna, Claude Haiku 5.5 and MiniMax M3.1 Flash, all on Max, each build a showcase website for the author’s graphics card from the same image assets.
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 DeepSeek Harness. More Claude Code vs DeepSeek Harness. More Claude Code vs OpenCode. More DeepSeek Harness vs OpenCode. More OpenAI Codex vs OpenCode. All harness comparisons.
The post, itemised
- Task
- GPU showcase website from given image assets, four models
- Category
- Web/UI
- Mode
- Not stated
- Posted
- Video length
- 50.4 s
- Likes
- 12
- Views
- 397
- Bookmarks
- 1
- Sponsored
- No
NotesNo winner named.
Cost & time, as stated in the postAs stated: DeepSeek V4.1 Flash 1017 33 min 58 s; GPT-6 Luna 3 min 19 s; Claude Haiku 5.5 36 min 19 s; MiniMax M3.1 Flash 2 h 28 min.
Related
Posted by @VulKan42069 on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
