AI Coding
Blind Mario level test, Kimi K3.1 Pro vs Opus — Kimi K3.1 Pro vs Claude Opus 5.5
Scoreboard2
- Kimi K3.1 ProMoonshot AI
- Time
- 12.6 min
- Cost
- $0.69
- Effort Max
- Model B (bottom)
- Claude Opus 5.5AnthropicAuthor’s pick
- Time
- 31.2 min
- Cost
- $6.30
- Effort xhigh
- Model A (top)
Prompt
Blind Mario level test, Kimi K3.1 Pro vs OpusThe post doesn’t quote the prompt wording.
In a follow-up reply that reveals the names, the poster says Opus 5.5 wins and it wasn't close.
@luckeyfaraday’s view (paraphrased)
Kimi K3.1 Pro and Claude Opus 5.5 get the same one-line prompt for a Mario level, one shot each, shown as Model A (top) and Model B (bottom) with names hidden.
The post, itemised
- Kind
- Side-by-side
- Task
- Blind Mario level test, Kimi K3.1 Pro vs Opus
- Category
- Games, 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 21 s
- Likes
- 1
- Views
- 128
- Bookmarks
- 0
- Sponsored
- No
Cost & time, as stated in the postAs shown in the poster's reveal: Kimi K3.1 Pro (max reasoning) 12 min 34 s, $0.69; Claude Opus 5.5 (xhigh) 31 min 10 s, $6.30.
Related
Posted by @luckeyfaraday on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
