Performance Estimation on DIVE
0.002MAEBQ-TPF
Evaluation Results
| Method | Links | |
|---|---|---|
| BQ-TPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.002 | |
| BQ-SFSelection Strategy=Active Selection, Feature Type=Score Features (SF), Labeling Budget=1%2026.04 | 0.002 | |
| BQ-SF RoundedBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.002 | |
| BQ-SFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.003 | |
| BQ-SF RoundedBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection, Integer Rounding=true2026.04 | 0.005 | |
| BQ-TPFBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.04 | 0.005 | |
| BQ-SF RoundedSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.04 | 0.006 | |
| BQ-SF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.012 | |
| BQ-SFTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.04 | 0.017 | |
| BQ-RPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.019 | |
| BQ-SF RandModel=Gemma 3 12B, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.019 | |
| BQ-SF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.04 | 0.02 | |
| BQ-RPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.02 | |
| BQ-SF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.04 | 0.02 | |
| BQ-SFSelection Strategy=Random Selection, Feature Type=Score Features (SF), Labeling Budget=1%2026.04 | 0.02 | |
| BQ-SFModel=Gemma 3 12B, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.02 | |
| BQ-SF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.04 | 0.021 | |
| BQ-SF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.04 | 0.022 | |
| BQ-SFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.023 | |
| BQ-TPFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.04 | 0.025 | |
| BQ-SFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.026 | |
| BQ-RPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.029 | |
| BQ-RPF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.04 | 0.03 | |
| BQ-SF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.04 | 0.03 | |
| BQ-TPFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.032 | |
| BQ-TPF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.04 | 0.032 | |
| RF+ISLabeling Budget=1%2026.04 | 0.033 | |
| BQ-TPF RandBudget=1%, Target Model=Gemini 3 Flash, Selection=Random Selection + BQ2026.04 | 0.034 | |
| BQ-SF RoundedBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.04 | 0.034 | |
| BQ-SF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.035 | |
| LR+LURETarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.036 | |
| BQ-RPF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.037 | |
| BQ-TPFTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.04 | 0.038 | |
| BQ-SFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.04 | 0.038 | |
| BQ-TPFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.04 | 0.039 | |
| BQ-SF RoundedModel=Gemma 3 12B, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.039 | |
| BQ-RPFBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.04 | 0.04 | |
| BQ-TPF RandBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection + BQ2026.04 | 0.041 | |
| BQ-SF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.041 | |
| BQ-SF RandBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.041 | |
| Random SamplingBudget=1%, Target Model=GPT-52026.04 | 0.041 | |
| BQ-SF RoundedTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.04 | 0.043 | |
| BQ-RPF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.04 | 0.044 | |
| BQ-RPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.04 | 0.045 | |
| Random SamplingBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.04 | 0.046 | |
| BQ-TPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.04 | 0.048 | |
| BQ-SF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.04 | 0.048 | |
| BQ-TPF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.04 | 0.049 | |
| BQ-TPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.049 | |
| Random SamplingBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.049 | |
| BQ-SFBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.049 | |
| BQ-SFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.04 | 0.051 | |
| BQ-SFBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.04 | 0.052 | |
| Random SamplingTarget Model=Claude 4.5 Opus, Budget=1%2026.04 | 0.055 | |
| BQ-RPF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.04 | 0.056 | |
| BQ-RPF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.057 | |
| BQ-RPF RandModel=Gemma 3 12B, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.057 | |
| BQ-SF RandBudget=1%, Target Model=Gemini 3 Flash, Selection=Random Selection + BQ2026.04 | 0.058 | |
| BQ-SF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.04 | 0.059 | |
| BQ-RPF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.04 | 0.059 | |
| BQ-TPF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.04 | 0.059 | |
| Random SamplingModel=Gemma 3 12B, Budget=1%2026.04 | 0.059 | |
| LR+LUREBudget=1%, Target Model=Gemini 3 Flash2026.04 | 0.06 | |
| BQ-TPF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.04 | 0.061 | |
| RF+LURETarget Model=Claude 4.5 Opus, Budget=1%2026.04 | 0.062 | |
| BQ-SF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.04 | 0.063 | |
| BQ-TPFBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.063 | |
| BQ-SF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.04 | 0.066 | |
| BQ-TPF RandModel=Claude 3.7 Sonnet, Budget=1%, Selection=Random2026.04 | 0.066 | |
| BQ-SF RoundedModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.04 | 0.067 | |
| BQ-SFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.04 | 0.068 | |
| LR+LUREModel=Claude 3.7 Sonnet, Budget=1%2026.04 | 0.068 | |
| BQ-RPF RoundedBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.04 | 0.069 | |
| BQ-SF RandBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection + BQ2026.04 | 0.07 | |
| BQ-RPF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.04 | 0.07 | |
| BQ-TPF RandBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.07 | |
| RF+LUREBudget=1%, Target Model=GPT-52026.04 | 0.071 | |
| RF+LUREBudget=1%, Target Model=Claude 4.5 Sonnet2026.04 | 0.072 | |
| RF+ISBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.04 | 0.074 | |
| LR+LUREBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.04 | 0.074 | |
| BQ-SF RandModel=Claude 3.7 Sonnet, Budget=1%, Selection=Random2026.04 | 0.074 | |
| BQ-RPF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.04 | 0.075 | |
| LR+ISTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.075 | |
| BQ-RPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.04 | 0.076 | |
| BQ-TPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.04 | 0.076 | |
| LR+ISBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.076 | |
| BQ-SF RoundedBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.04 | 0.079 | |
| RF+LURETarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.079 | |
| RF+ISModel=Claude 3.7 Sonnet, Budget=1%2026.04 | 0.079 | |
| BQ-TPF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.04 | 0.08 | |
| Random SamplingBudget=1%, Target Model=GPT-4o, Selection Strategy=Uniform Random2026.04 | 0.081 | |
| BQ-TPF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.04 | 0.081 | |
| LR+ISTarget Model=Claude 4.5 Opus, Budget=1%2026.04 | 0.081 | |
| LR+ISModel=Claude 3.7 Sonnet, Budget=1%2026.04 | 0.081 | |
| LR+ISLabeling Budget=1%2026.04 | 0.082 | |
| LR+LURELabeling Budget=1%2026.04 | 0.083 | |
| BQ-RPFBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.083 | |
| RF+ISBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.04 | 0.085 | |
| RF+ISBudget=1%, Model=Gemini 2.5 Pro2026.04 | 0.086 | |
| LR+LUREModel=Gemma 3 12B, Budget=1%2026.04 | 0.086 |