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

Model

Benchmarks

Task NameDataset NameSOTA ResultTrend
ClassificationModel 1
Accuracy0.9295
27
Confidence region coverage estimationModel synthetic 5.2
Coverage Probability95.45
27
Confidence region coverage estimationModel synthetic 5.1
Coverage Probability95.45
27
Metastability EvaluationModel II
Q Value2.9882
8
Portfolio OptimizationModel Scenario S4 M3
Annualized Sharpe Ratio0.821
7
Portfolio OptimizationModel Scenario S3 M3
Annualized Sharpe Ratio1.047
7
Portfolio OptimizationModel Scenario S2 M3
Annualized Sharpe Ratio1.673
7
Portfolio OptimizationModel Scenario S1 M3
Annualized Sharpe Ratio3.48
7
Portfolio OptimizationModel Scenario S4 M2
Annualized Sharpe Ratio0.86
7
Portfolio OptimizationModel M2 Scenario S3
Annualized Sharpe Ratio1.222
7
Portfolio OptimizationModel S4 M1
Annualized Sharpe Ratio0.754
7
Portfolio OptimizationModel Scenario S3 M1
Annualized Sharpe Ratio1.035
7
Portfolio OptimizationModel M1 Scenario S2
Annualized Sharpe Ratio2.001
7
Portfolio OptimizationModel Scenario S1 M1
Annualized Sharpe Ratio3.091
7
LLM Inference11B parameter model INT8
Throughput (TPS)110
6
Single-stream decode622.9 MB 4-layer model
Latency (ms/token)1.08
4
Data TradingModel 4 n = 5
Social Welfare0.337
3
Data TradingModel 2 n = 5
Social Welfare0.621
3
Data TradingModel 1 n = 5
Social Welfare10.804
3
Showing 19 of 19 rows