AI Coding
Mercury 3 vs Haiku 5.5 on four 3D benchmarks — Mercury 3 vs Claude Haiku 5.5
Scoreboard2
- Mercury 3Inception
- Effort high
- Claude Haiku 5.5Anthropic
- Effort high
Prompt
Mercury 3 vs Haiku 5.5 on four 3D benchmarksThe post doesn’t quote the prompt wording.
Haiku produced more detailed scenes; Mercury used about 80% fewer output tokens and ran 24% faster.
@trypalomino’s view (paraphrased)
Inception’s new diffusion model Mercury 3 and Claude Haiku 5.5, both at high, run four 3D benchmarks, including a steam locomotive. Labels show output tokens per run, such as 30.6K for Mercury vs 301K for Haiku.
The post, itemised
- Kind
- Side-by-side
- Task
- Mercury 3 vs Haiku 5.5 on four 3D benchmarks
- Category
- 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 14 s
- Likes
- 3
- Views
- 176
- Bookmarks
- 2
- Sponsored
- No
Cost & time, as stated in the postAs stated: Mercury used about 80% fewer output tokens and was 24% faster (~231 vs 187 tokens/s).
Related
Posted by @trypalomino on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
