Benchmark: Chun-Li Blender test by @luckeyfaradayAI Coding
Chun-Li Blender test, DeepSeek vs Opus — DeepSeek V4.1 Flash 1017 vs Claude Opus 5.5
Scoreboard2
- DeepSeek V4.1 Flash 1017DeepSeek
- Time
- 1 h 13 min
- Cost
- $0.68
- Effort max
- medium confidence
- Left
- Labelled “DeepSeek V4.1 Flash”; posted after DeepSeek’s Oct 17 upgrade, so read as 1017.
- Claude Opus 5.5AnthropicAuthor’s pick
- Time
- 1 h 02 min
- Cost
- $13.25
- Effort xhigh
- Written as “Opus 5.5”
- Right
Prompt
Chun-Li Blender test, DeepSeek vs OpusThe post doesn’t quote the prompt wording.
The price gap is huge, but Opus is still clearly the better result.
@luckeyfaraday’s view (paraphrased)
DeepSeek V4.1 Flash 1017 at max reasoning and Claude Opus 5.5 at xhigh build Chun-Li in Blender from the same prompt on the author's Chun-Li Blender test: DeepSeek took 1h 12m for about $0.68, Opus 1h 02m for about $13.25.
The post, itemised
- Kind
- Side-by-side
- Task
- Chun-Li Blender test, DeepSeek vs Opus
- Category
- 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 24 s
- Likes
- 21
- Views
- 1,338
- Bookmarks
- 3
- Sponsored
- No
NotesThe Opus clip, time and cost match the author’s Oct 15 Chun-Li run against Gemini 4 Argon.
Cost & time, as stated in the postAs shown on screen (estimated API costs): DeepSeek V4.1 Flash 1h 12m 52s, $0.68; Claude Opus 5.5 1h 02m 09s, $13.25.
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
