AI Coding
Voxel US map, two Claude Fable versions — Claude Fable 5.1 vs Claude Fable 5.2
Scoreboard2
- Claude Fable 5.1Anthropic
- Top
- Claude Fable 5.2Anthropic
- Bottom
Prompt
Voxel US map, two Claude Fable versionsThe post doesn’t quote the prompt wording.
MineBench shows Claude Fable 5.1 (top) and Claude Fable 5.2 (bottom) building the same voxel prompt, an accurate map of the United States, as Fable 5.2 joins its leaderboard. The post has four comparison clips.
The post, itemised
- Kind
- Side-by-side
- Task
- Voxel US map, two Claude Fable versions
- Category
- 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 6 s (+3 more clips)
- Likes
- 3
- Views
- 34
- Bookmarks
- 0
- Sponsored
- No
NotesPosted by the MineBench benchmark account; the cost drop comes from lower API pricing and zero retries in its harness.
Cost & time, as stated in the postMineBench’s figures over 15 builds, Fable 5.1 to Fable 5.2: total cost $147.55 to $38.08, average time 40m 11s to 12m 55s, retries 8 to 0.
Related
Posted by @minebench_ai on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal


