Population property estimation on DICES
0.001Bias (MAE)BQ-RPF Rounded
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| BQ-RPF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.001 | — | — | |
| BQ-RPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.009 | — | — | |
| BQ-RPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.01 | — | — | |
| BQ-RPF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.04 | 0.013 | — | — | |
| BQ-SFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.014 | — | — | |
| BQ-TPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.014 | — | — | |
| BQ-SF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.04 | 0.018 | — | — | |
| BQ-SF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.018 | — | — | |
| DR (Riesz)2025.09 | 0.02 | 86 | 0.09 | |
| BQ-SFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.022 | — | — | |
| BQ-RPF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.022 | — | — | |
| BQ-TPF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.04 | 0.025 | — | — | |
| BQ-SF RandBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection + BQ2026.04 | 0.027 | — | — | |
| BQ-RPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.04 | 0.027 | — | — | |
| BQ-SFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.04 | 0.027 | — | — | |
| BQ-SFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.03 | — | — | |
| BQ-TPF RandBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection + BQ2026.04 | 0.031 | — | — | |
| BQ-SF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.04 | 0.037 | — | — | |
| BQ-TPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.038 | — | — | |
| RePPI2025.09 | 0.04 | 40 | 0.05 | |
| BQ-RPFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.04 | 0.049 | — | — | |
| PAR2025.09 | 0.05 | 4 | 0.02 | |
| DR (Classical)2025.09 | 0.05 | 32 | 0.06 | |
| BQ-TPF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.04 | 0.05 | — | — | |
| BQ-TPF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.053 | — | — | |
| Random SamplingBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random2026.04 | 0.056 | — | — | |
| RF+ISBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Standard2026.04 | 0.056 | — | — | |
| LR+ISBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Standard2026.04 | 0.056 | — | — | |
| BQ-TPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.04 | 0.057 | — | — | |
| BQ-SF RoundedBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.058 | — | — | |
| BQ-SF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.058 | — | — | |
| BQ-RPF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.058 | — | — | |
| RF+LUREBudget=1%, Model=Gemma 3 27B2026.04 | 0.059 | — | — | |
| LR+LUREBudget=1%, Model=Gemma 3 27B2026.04 | 0.059 | — | — | |
| PPI++2025.09 | 0.06 | 1 | 0.03 | |
| LR+ISBudget=1%, Model=Gemma 3 27B, Selection Strategy=Importance Sampling2026.04 | 0.061 | — | — | |
| BQ-RPF RoundedBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.061 | — | — | |
| BQ-SF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.04 | 0.062 | — | — | |
| RF+ISBudget=1%, Model=Gemma 3 27B, Selection Strategy=Importance Sampling2026.04 | 0.063 | — | — | |
| BQ-RPF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.04 | 0.064 | — | — | |
| BQ-TPF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.04 | 0.068 | — | — | |
| BQ-TPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.069 | — | — | |
| BQ-RPF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.04 | 0.069 | — | — | |
| BQ-RPF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.04 | 0.069 | — | — | |
| BQ-RPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.07 | — | — | |
| RF+LUREBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.04 | 0.072 | — | — | |
| BQ-TPFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.072 | — | — | |
| BQ-TPFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.04 | 0.073 | — | — | |
| LR+LURETarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.074 | — | — | |
| RF+LURETarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.075 | — | — | |
| LR+LUREBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.04 | 0.076 | — | — | |
| BQ-RPF RandBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection + BQ2026.04 | 0.078 | — | — | |
| BQ-RPFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.078 | — | — | |
| LR+ISBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.04 | 0.079 | — | — | |
| RF+LUREBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.04 | 0.079 | — | — | |
| RF+ISBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.04 | 0.08 | — | — | |
| LR+LUREBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.04 | 0.08 | — | — | |
| LR+LUREBudget=1%, Target Model=Claude 4.5 Sonnet2026.04 | 0.08 | — | — | |
| RF+LUREBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Standard2026.04 | 0.085 | — | — | |
| RF+LUREBudget=1%, Target Model=Claude 4.5 Sonnet2026.04 | 0.086 | — | — | |
| BQ-SF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.087 | — | — | |
| BQ-TPF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.094 | — | — | |
| Sample Average2025.09 | 0.1 | 0 | 0.07 | |
| LR+ISBudget=1%, Target Model=Claude 4.5 Sonnet2026.04 | 0.106 | — | — | |
| Random SamplingBudget=1%, Target Model=GPT-4o, Selection Strategy=Uniform Random2026.04 | 0.107 | — | — | |
| BQ-RPF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.108 | — | — | |
| RF+ISBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.04 | 0.108 | — | — | |
| Random SamplingBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Sampling2026.04 | 0.109 | — | — | |
| Random SamplingBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.04 | 0.112 | — | — | |
| BQ-SF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.04 | 0.117 | — | — | |
| BQ-SFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.117 | — | — | |
| BQ-SF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.117 | — | — | |
| BQ-SF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.04 | 0.117 | — | — | |
| BQ-RPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.117 | — | — | |
| BQ-RPF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.117 | — | — | |
| BQ-SFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.117 | — | — | |
| BQ-SF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.117 | — | — | |
| LR+ISBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.04 | 0.118 | — | — | |
| LR+ISTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.129 | — | — | |
| BQ-TPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.133 | — | — | |
| Random SamplingBudget=1%, Target Model=Claude 4.5 Sonnet2026.04 | 0.134 | — | — | |
| Random SamplingTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.139 | — | — | |
| RF+ISTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.149 | — | — | |
| BQ-TPF RoundedBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.151 | — | — | |
| LR+LUREBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Standard2026.04 | 0.152 | — | — | |
| RF+ISBudget=1%, Target Model=Claude 4.5 Sonnet2026.04 | 0.167 | — | — | |
| IPW2025.09 | 0.17 | 7 | 0.1 | |
| BQ-TPF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.04 | 0.211 | — | — | |
| BQ-TPF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.211 | — | — | |
| BQ-TPF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.295 | — | — | |
| BQ-TPF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.335 | — | — | |
| Persona-Based2025.09 | 0.34 | 0 | 0.05 |