Text Generation Evaluation on AlpacaEval
76.1Performance ScoreThoughts-as-Planning
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Thoughts-as-PlanningTransfer Scenario=Fine-tuned (SuperNI → AlpacaEval)2026.04 | 76.1 | 38 | |
| Thoughts-as-PlanningTransfer Scenario=Few-shot (5 examples)2026.04 | 75.2 | 42 | |
| Thoughts-as-PlanningTransfer Scenario=Zero-shot (SuperNI → AlpacaEval)2026.04 | 73.4 | 45 |