List your company

Performance Estimation on GSM8K

0MAEBQ-RPF Rounded
-0.001440.008280.0180.02772Apr 25, 2026

Evaluation results

MethodLinks
BQ-RPF RoundedBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.040—
BQ-RPF RoundedTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040—
BQ-RPFBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection2026.040—
BQ-RPFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040—
BQ-RPF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.001—
BQ-SF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.001—
BQ-SFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.002—
BQ-RPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.002—
BQ-SF RoundedTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.002—
BQ-SF RoundedSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.002—
BQ-SF RoundedBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection, Integer Rounding=true2026.040.003—
BQ-RPF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.004—
BQ-SF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.004—
BQ-RPFTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.004—
BQ-RPF RoundedSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.004—
BQ-RPFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.040.005—
BQ-TPFTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.005—
BQ-RPF RoundedBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection, Integer Rounding=true2026.040.005—
BQ-SF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.040.006—
BQ-RPF RoundedBudget=1%, Model=Gemini 2.5 Pro2026.040.006—
BQ-SF RoundedBudget=1%, Model=Gemini 2.5 Pro2026.040.006—
BQ-SF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.040.007—
BQ-TPFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.007—
BQ-RPFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.007—
BQ-RPFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.040.009—
BQ-RPF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.040.009—
BQ-TPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.009—
BQ-TPFBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection2026.040.009—
BQ-SF RoundedModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.009—
BQ-TPFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.009—
BQ-RPF RoundedModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.01—
BQ-TPFBudget=1%, Target Model=GPT-3.5 Turbo, Selection Type=Active Selection2026.040.011—
BQ-TPFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.040.013—
BQ-SFSelection Strategy=Active Selection, Feature Type=Score Features (SF), Labeling Budget=1%2026.040.013—
BQ-TPFBudget=1%, Model=Gemini 2.5 Pro2026.040.013—
BQ-RPFModel=Gemma 3 12B, Budget=1%, Selection Strategy=Active Selection2026.040.014—
BQ-TPFModel=Gemma 3 12B, Budget=1%, Selection Strategy=Active Selection2026.040.014—
BQ-TPFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.015—
BQ-RPF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.040.016—
BQ-SFBudget=1%, Target Model=GPT-4o, Selection Strategy=Active Selection + BQ2026.040.019—
BQ-RPF RandTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.019—
BQ-SF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.040.02—
BQ-SFModel=Claude 3.7 Sonnet, Budget=1%, Selection=Active2026.040.022—
BQ-TPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.040.023—
BQ-SFBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=false2026.040.023—
BQ-TPF RandTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Random Selection + BQ2026.040.023—
BQ-SFBudget=1%, Model=Gemini 2.5 Pro2026.040.024—
BQ-SF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.026—
BQ-RPF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.040.026—
BQ-SFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.027—
Random SamplingTarget Model=Claude 4.5 Opus, Budget=1%2026.040.027—
BQ-TPF RoundedTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.027—
BQ-SF RandModel=Claude 3.7 Sonnet, Budget=1%, Selection=Random2026.040.027—
BQ-TPF RandBudget=1%, Model=Gemini 2.5 Pro2026.040.027—
BQ-SF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.028—
BQ-RPF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.028—
BQ-SFBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection2026.040.028—
BQ-RPF RoundedBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.029—
Random SamplingBudget=1%, Target Model=Claude 4.5 Sonnet2026.040.029—
BQ-TPF RoundedBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.029—
BQ-SFSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.029—
BQ-RPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.03—
BQ-RPFTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.03—
Random SamplingBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Sampling2026.040.03—
LR+LUREBudget=1%, Target Model=GPT-52026.040.03—
BQ-TPF RoundedSelection Mode=Active Selection, Budget=1%, Target Model=GPT-52026.040.03—
BQ-SFBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Active Selection2026.040.031—
BQ-TPF RoundedBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Active Selection, Integer Rounding=true2026.040.031—
BQ-RPFBudget=1%, Model=Gemini 2.5 Pro2026.040.031—
BQ-TPF RandBudget=1%, Model=Gemma 3 27B, Selection Strategy=Random Selection2026.040.032—
BQ-RPF RandBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection + BQ2026.040.032—
Random SamplingTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.032—
BQ-TPF RoundedTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Active Selection2026.040.032—
BQ-TPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.032—
BQ-SFTarget Model=Claude 4.5 Opus, Budget=1%, Selection Strategy=Active Selection + BQ2026.040.032—
Random SamplingBudget=1%, Target Model=GPT-52026.040.032—
BQ-SF RandSelection Mode=Random Selection, Budget=1%, Target Model=GPT-52026.040.032—
BQ-SFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.033—
Random SamplingBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.033—
LR+LUREBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.033—
BQ-TPFBudget=1%, Model=Gemma 3 27B, Selection Strategy=Active Selection2026.040.034—
BQ-RPFBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.034—
BQ-SF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.034—
LR+ISBudget=1%, Target Model=Claude 4.5 Sonnet2026.040.034—
BQ-SF RandBudget=1%, Target Model=Claude 4.5 Sonnet, Selection Strategy=Random Selection2026.040.034—
LR+ISTarget Model=Claude 4.5 Opus, Budget=1%2026.040.034—
RF+LURETarget Model=Claude 4.5 Opus, Budget=1%2026.040.034—
RF+LURETarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.035—
BQ-TPF RandBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Random Selection + BQ2026.040.035—
BQ-RPF RoundedBudget=1%, Target Model=Claude 3.5 Haiku, Selection Strategy=Active Selection + BQ2026.040.035—
BQ-TPF RandBudget=1%, Target Model=Gemini 3 Pro, Selection Strategy=Random2026.040.035—
Random SamplingModel=Claude 3.7 Sonnet, Budget=1%2026.040.035—
LR+ISModel=Claude 3.7 Sonnet, Budget=1%2026.040.035—
Random SamplingBudget=1%, Model=Gemini 2.5 Pro2026.040.035—
BQ-TPF RoundedBudget=1%, Model=Gemini 2.5 Pro2026.040.035—
RF+LUREBudget=1%, Target Model=GPT-52026.040.035—
Random SamplingBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.040.036—
RF+LUREBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Random Selection2026.040.036—
BQ-TPF RoundedBudget=1%, Evaluated Model=GPT-5.1, Selection Strategy=Active Selection + BQ, Rounding=true2026.040.036—
LR+ISTarget Model=GPT-5.2, Budget=1%, Selection Strategy=Random Selection2026.040.036—