I’ve been building Saina Helm 2.0, a 0.8B decision model for workflow automation.
I ran it on the public Decision Index 0.3 suite and got 30.17 using model revision 9903c487a3b1eef45c8cc56c76155b9baccb55f9. This is a self-run public result, not an official leaderboard score.
- Reproducible evaluation I’d welcome feedback on the evaluation and suggestions for useful workflow tests or integrations.