Human Pairwise Comparison on Gaming Content Familiar Games N=60 samples
83.3Win RateMeepleLM
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MeepleLMMetric=Authenticity Check2026.01 | 83.3 | 10 | 6.7 | |
| MeepleLMMetric=Opinion Diversity2026.01 | 80 | 6.7 | 13.3 | |
| MeepleLMMetric=Emotional Resonance2026.01 | 76.7 | 13.3 | 10 | |
| MeepleLMMetric=Shareability2026.01 | 73.3 | 16.7 | 10 | |
| GPT-5.1Metric=Opinion Diversity2026.01 | 13.3 | 6.7 | 80 | |
| GPT-5.1Metric=Emotional Resonance2026.01 | 10 | 13.3 | 76.7 | |
| GPT-5.1Metric=Shareability2026.01 | 10 | 16.7 | 73.3 | |
| GPT-5.1Metric=Authenticity Check2026.01 | 6.7 | 10 | 83.3 |