Strategic Question Answering on StrategyQA (Reusability Score)
51.57Reusability ScorePhi
Evaluation Results
| Method | Links | |
|---|---|---|
| PhiExecutor=Strong Comm.2026.02 | 51.57 | |
| R1Executor=Strong Comm.2026.02 | 48.88 | |
| LlamaExecutor=Strong Comm.2026.02 | 45.87 | |
| PhiExecutor=Full Comm.2026.02 | 45.25 | |
| R1Executor=Full Comm.2026.02 | 44.58 | |
| GemmaExecutor=Strong Comm.2026.02 | 44.53 | |
| LlamaExecutor=Full Comm.2026.02 | 43.35 | |
| GemmaExecutor=Full Comm.2026.02 | 42.13 | |
| LlamaExecutor=Weak Comm.2026.02 | 40.82 | |
| R1Executor=Weak Comm.2026.02 | 40.28 | |
| GemmaExecutor=Weak Comm.2026.02 | 39.72 | |
| PhiExecutor=Weak Comm.2026.02 | 38.92 |