AgentDish directory
open-source applications
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
|
#582
↑ +2
i5h Benchmark
A benchmark for coding agents that tests whether they can formally verify properties of real-world Rust web apps in Lean 4. It includes upstream code, i5h ports, extracted Lean models, proof attempts, and task-by-task results. |
Developer Tools / Code Assistant | 86 | ↑ +2 | 15 days ago | Details |