v1.0.4
daydreamlive/DEMONv1.0.4Jul 17, 2026by virattt
AI Summary
This release enhances evaluation capabilities by introducing rubric-based partial-credit scoring, contradiction detection, and reproducible sampling. It also improves reporting metrics and fixes inaccuracies found in previous finance evaluation answers.
Key Highlights
- New rubric-based partial-credit scoring and contradiction detection
- New reproducible sampling, quick runs, and configurable models
- Improved eval reporting with metadata, latency, and failure metrics
- Fixes for inaccurate finance evaluation answers and rubric criteria
New Features
- Rubric-based partial-credit scoring
- Contradiction detection
- Reproducible sampling
- Quick runs
- Configurable models
- Concurrency and timeouts
- Enhanced evaluation reporting with latency and failure metrics
Full Release Notes
### Changes - Add rubric-based partial-credit scoring and contradiction detection - Add reproducible sampling, quick runs, configurable models, concurrency, and timeouts - Improve eval reporting with metadata, latency, and failure metrics ### Fixes - Fix inaccurate finance evaluation answers and rubric criteria