Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Spy

Benchmarks

Task NameDataset NameSOTA ResultTrend
Personally Identifiable Information (PII) Entity RecognitionSPY Legal Questions
Name93.2
6
PII DetectionSPY (Synthetic PII Yesterday)
Legal Precision52.2
5
Option PricingSPY 2025Q2 τ=14d (Whole sample)
IVRMSE9.49
5
Option PricingSPY 2020Q1 τ=14d (Whole sample)
IVRMSE5.53
5
Option PricingSPY 2020Q2 τ=56d
IVRMSE4.36
5
Option PricingSPY 2020Q1 τ=56d (Whole sample)
IVRMSE1.23
5
Option HedgingSPY ATM 2020Q1
Shortfall Probability91
5
Option Pricing AccuracySPY Moneyness > 1.03 28d maturity 2025Q2
IVRMSE4.04
5
Option Pricing AccuracySPY 2020Q1, Moneyness > 1.03, 28d maturity
IVRMSE2.02
5
Option Pricing AccuracySPY 2025Q2, Moneyness > 1, 28d maturity
IVRMSE3.97
5
Option Pricing AccuracySPY Moneyness < 1, 28d maturity 2025Q2
IVRMSE7.55
5
Option Pricing AccuracySPY 2020Q1, Moneyness < 1, 28d maturity
IVRMSE1.61
5
Option Pricing AccuracySPY Whole sample 28d maturity 2025Q2
IVRMSE7.34
5
Option Pricing AccuracySPY 2020Q1 Whole sample 28d maturity
IVRMSE1.76
5
Social DeductionSpy
Accuracy70
3
Option HedgingSPY K/F=1.03 2025Q2
ES 5%14.535
2
Option HedgingSPY ATM 2025Q2
ES 5%17.711
2
Option HedgingSPY K/F=1.03 2020Q1
Expected Shortfall (5%)6.187
2
Option HedgingSPY 2025Q2 K/F=1.03 (τ = 56d)
ES5%15.437
1
Option HedgingSPY ATM (τ = 56d) 2025Q2
ES 5%22.015
1
Option HedgingSPY K/F=1.03 (τ = 56d) 2020Q1
ES (5%)8.002
1
Option HedgingSPY ATM (τ = 56d) 2020Q1
Exposure Shortfall (5%)9.963
1
Showing 22 of 22 rows