Night train model benchmark comparison
- Views
- 23.1K
- Likes
- 179
- Replies
- 24
- Saves
- 46
The creator gave four models (GPT-6 Luna, GPT-6.1 Sol, Claude Sonnet 5.5, Claude Haiku 5.5) the same one-line prompt 'Build a night train' and compared the results, noting GPT-6.1 Sol's speed and low cost.
Creator's brief20 chars
Build a night train.
Source: the original post. Kept in its original language, unedited.
Tools the creator mentioned
Original post: https://x.com/EnvolDev/status/2109317150980940047
All works are open data at GitHub · awesome-opus-5.5-video.
Model attribution is as stated by the creator and was not independently reproduced. View counts are a snapshot from 2026-10-12. The work belongs to its creator; DM @GoSailGlobal on X for corrections or removal.
More comparisons
0:42AI self-portrait challenge: Sonnet 5.5 vs GPT-6 Astra
7.3M views
0:28Opus 5.5 vs GPT-6 Astra samurai game demo
1.1M views
0:30GPT-6 Astra vs Claude Opus 5.5 comparison
603.5K views
0:22Grok vs Opus grass-touching simulator cost test
552.1K views
0:44Opus 5.5 vs GPT-6 Sol Unreal game dev
540.1K views
0:13Glitter sticker effect comparison
474.2K views