Loading live stats
Today we're releasing ViBench 2.0, a benchmark for long-horizon software building. Agents start from an empty project and build a whole product, one feature at a time, without seeing what comes next.
Even the best models (GPT-6.1 Sol, GPT-6 Astra, Opus 5.5) pass every check in
| Subjects | Developer Tools, AI |
|---|---|
| Colors | Colors sampled from the image |
| Posted | |
| Views | 10.3k+ |
| Spotted | |
| Curator | @baseddesigner |
Try Replit
Get $20 in Replit credits when you subscribe.
