Quality-Diversity Search on Core War
0.85Peak Generation ScoreDiverse Ensemble
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Diverse EnsembleModel=Claude Sonnet 4.62026.05 | 0.85 | — | — | 0.483 | |
| Homogeneous EnsembleModel=Claude Sonnet 4.62026.05 | 0.825 | — | — | 0.348 | |
| Solo [DRQ]Model=Claude Sonnet 4.62026.05 | 0.775 | — | — | — | |
| Diverse EnsembleModel=GPT-5.4-mini2026.05 | 0.767 | — | — | 0.422 | |
| Diverse EnsembleModel=GPT-5.22026.05 | 0.767 | — | — | 0.454 | |
| Solo [DRQ]Model=GPT-5.4-mini2026.05 | 0.75 | — | — | — | |
| Homogeneous EnsembleModel=GPT-5.4-mini2026.05 | 0.725 | — | — | 0.119 | |
| Homogeneous EnsembleModel=GPT-5.22026.05 | 0.7 | — | — | 0.091 | |
| Diverse EnsembleModel=Claude Haiku 4.52026.05 | 0.7 | — | — | 0.443 | |
| Solo [DRQ]Model=GPT-5.22026.05 | 0.65 | — | — | — | |
| Solo [DRQ]Model=Claude Haiku 4.52026.05 | 0.65 | — | — | — | |
| Homogeneous EnsembleModel=Claude Haiku 4.52026.05 | 0.538 | — | — | 0.139 | |
| Diverse mergedCondition=Diverse merged2026.05 | — | 80.6 | 45.9 | — | |
| Homo mergedCondition=Homo merged2026.05 | — | 59 | 29.85 | — | |
| SoloCondition=Solo2026.05 | — | 63 | 20.46 | — |