Faithful Narrative Generation on credit
100RABasic Design
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Basic DesignDesign=Basic Design, Round=2, Backbone=Claude Sonnet 4.52026.03 | 100 | 100 | 98.8 | 1 | |
| Critic DesignDesign=Critic Design, Round=2, Backbone=Claude Sonnet 4.52026.03 | 100 | 100 | 100 | 0 | |
| Basic DesignDesign=Basic Design, Round=1, Backbone=Claude Sonnet 4.52026.03 | 97.5 | 100 | 97.5 | 1 | |
| Critic DesignDesign=Critic Design, Round=1, Backbone=Claude Sonnet 4.52026.03 | 97.5 | 100 | 98.8 | 2 | |
| Critic-Rule DesignDesign=Critic-Rule Design, Round=1, Backbone=Claude Sonnet 4.52026.03 | 97.5 | 100 | 97.5 | 2 | |
| Critic-Rule DesignDesign=Critic-Rule Design, Round=2, Backbone=Claude Sonnet 4.52026.03 | 97.5 | 100 | 100 | 1 | |
| BaselineDesign=Baseline, Round=0, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 98.8 | 97.5 | 3 | |
| Basic DesignDesign=Basic Design, Round=0, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 98.8 | 97.5 | 3 | |
| Critic DesignDesign=Critic Design, Round=0, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 98.8 | 97.5 | 3 | |
| Critic-Rule DesignDesign=Critic-Rule Design, Round=0, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 98.8 | 97.5 | 3 | |
| Coherent DesignDesign=Coherent Design, Round=0, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 98.8 | 97.5 | 3 | |
| Coherent DesignDesign=Coherent Design, Round=1, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 100 | 98.8 | 4 | |
| Coherent DesignDesign=Coherent Design, Round=2, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 100 | 100 | 2 | |
| Coherent-Rule DesignDesign=Coherent-Rule Design, Round=0, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 98.8 | 97.5 | 3 | |
| Coherent-Rule DesignDesign=Coherent-Rule Design, Round=1, Backbone=Claude Sonnet 4.52026.03 | 93.8 | 100 | 98.8 | 4 | |
| Coherent-Rule DesignDesign=Coherent-Rule Design, Round=2, Backbone=Claude Sonnet 4.52026.03 | 92.5 | 100 | 100 | 3 |