List your company

Performance Estimation on MMLU

0.002MAEBQ-SF
-0.00060.016950.03450.05205Apr 25, 2026

Evaluation results

MethodLinks
BQ-SFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.002
BQ-SF RoundedSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.002
BQ-TPFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.040.004
BQ-RPF RoundedBudget=1%, Target Model=GPT-3.5 Turbo, Selection Type=Active Selection2026.040.004
BQ-RPF RoundedModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.005
BQ-SFSelection Strategy=Active Selection, Feature Type=Score Features (SF), Labeling Budget=1%2026.040.006
BQ-SFScenario=New Model (NM), Feature Type=Score Features (SF), Labeling Budget=1%2026.040.007
BQ-SF RoundedTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.008
BQ-SF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.01
BQ-SFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.01
BQ-SF RoundedBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection, Integer Rounding=true2026.040.01
BQ-RPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.013
BQ-SFBudget=1%, Model=Gemini 2.5 Pro2026.040.013
BQ-SF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.040.014
BQ-TPFBudget=1%, Model=Gemini 2.5 Pro2026.040.015
BQ-RPFBudget=1%, Target Model=GPT-3.5 Turbo, Selection Type=Active Selection2026.040.018
BQ-TPFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.018
BQ-RPF RoundedSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.022
BQ-SF RoundedBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.040.022
BQ-SFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.040.024
BQ-RPF RandBudget=1%, Model=Gemini 2.5 Pro2026.040.024
BQ-RPF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.025
BQ-SFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.026
BQ-SF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.040.026
BQ-RPF RoundedBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection, Integer Rounding=true2026.040.026
BQ-SF RandBudget=1%, Model=Gemini 2.5 Pro2026.040.028
BQ-SFTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.029
BQ-RPFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.040.03
BQ-RPF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.03
BQ-RPFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.040.034
BQ-RPF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.040.034
BQ-TPF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.035
RF+ISBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.036
BQ-SFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.036
BQ-SFBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.040.036
BQ-RPF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.037
BQ-RPF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.040.037
BQ-SF RoundedModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.037
BQ-SFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.037
BQ-TPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.039
BQ-SF RandModel=Claude 3.7 Sonnet, Budget=1%, Selection=Random2026.040.039
Random SamplingBudget=1%, Model=Gemini 2.5 Pro2026.040.039
LR+LUREBudget=1%, Target Model=GPT-52026.040.039
BQ-SF RandBudget=1%, Target Model=Gemini 3 Flash, Selection=Random Selection + BQ2026.040.039
BQ-SF RandBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection + BQ2026.040.04
RF+LUREBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.040.04
BQ-RPF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.040.04
LR+ISBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.040.041
BQ-SF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.042
LR+ISTarget Model=Claude 4.5 Opus, Budget=1%2026.040.042
BQ-SF RoundedBudget=1%, Model=Gemini 2.5 Pro2026.040.042
BQ-RPF RandModel=Gemma 3 12B, Budget=1%, Selection Strategy=Random Selection2026.040.043
BQ-SF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.040.044
LR+LUREBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.040.046
BQ-SF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.046
BQ-RPFBudget=1%, Model=Gemini 2.5 Pro2026.040.047
LR+LUREBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.048
BQ-TPF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.040.049
BQ-SFBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection2026.040.049
BQ-RPF RoundedTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.05
RF+ISBudget=1%, Target Model=GPT-52026.040.05
BQ-RPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.052
LR+ISBudget=1%, Target Model=GPT-3.5 Turbo2026.040.052
BQ-RPFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.052
RF+LUREBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Standard2026.040.053
LR+LURETarget Model=Claude 4.5 Opus, Budget=1%2026.040.053
BQ-RPF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.053
BQ-TPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.054
LR+LUREBudget=1%, Target Model=GPT-4o, Selection Strategy=Random Selection2026.040.054
BQ-TPF RandBudget=1%, Target Model=Gemini 3 Flash, Selection=Random Selection + BQ2026.040.054
BQ-TPFBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.040.054
BQ-RPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.055
RF+LURETarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.055
BQ-TPF RandModel=Claude 3.7 Sonnet, Budget=1%, Selection=Random2026.040.055
BQ-TPF RandBudget=1%, Model=Gemini 2.5 Pro2026.040.055
BQ-TPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.056
RF+ISTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.057
BQ-TPF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.040.057
BQ-RPF RoundedBudget=1%, Target Model=Gemini 3 Flash, Selection=Active Selection + BQ2026.040.057
LR+ISBudget=1%, Model=Gemma 3 27B2026.040.058
BQ-TPF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.058
BQ-RPF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.058
Random SamplingBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.058
LR+ISBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.058
RF+ISBudget=1%, Target Model=Gemini 3 Flash2026.040.058
BQ-RPF RandBudget=1%, Target Model=Gemini 3 Flash, Selection=Random Selection + BQ2026.040.058
RF+ISTarget Model=Claude 4.5 Opus, Budget=1%2026.040.059
BQ-RPF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.040.059
RF+ISBudget=1%, Target Model=GPT-3.5 Turbo2026.040.06
Random SamplingBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.040.061
Random SamplingTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.061
BQ-RPF RoundedBudget=1%, Model=Gemini 2.5 Pro2026.040.061
RF+ISBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.040.062
BQ-SF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.040.063
Random SamplingTarget Model=Claude 4.5 Opus, Budget=1%2026.040.064
BQ-SF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.040.065
BQ-RPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.040.066
BQ-RPFBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection2026.040.066
RF+ISBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Standard2026.040.067
LR+LUREBudget=1%, Model=Gemini 2.5 Pro2026.040.067