List your company

ResearchFormerly WizWand

Model Selection

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

14 Time-Series Datasets (test)

33.9Top-1 Probability

8

Mar 10, 2026

LOVM VLM Zoo original

0.498R_S Score

8

Feb 26, 2026

LOVM average over 23 datasets

0.504R5 Score

8

Feb 26, 2026

36 Benchmarks Average (test)

78.28Selected-Model Accuracy

6

Jun 9, 2026

Multisensory Causal Inference

3.1LML RMSE

6

Apr 23, 2026

CFD Closure Models Sparsity 0.90 (test)

Hybrid Cold-Start Recommender System

0.11Mean Regret

5

Apr 13, 2026

CFD Closure Models Sparsity 0.75 (test)

Hybrid Cold-Start Recommender System

0.094Mean Regret

5

Apr 13, 2026

CFD Closure Models Sparsity 0.50 (test)

Hybrid Cold-Start Recommender System

0.097Mean Regret

5

Apr 13, 2026

CFD Closure Models Sparsity 0.25 (test)

Hybrid Cold-Start Recommender System

0.085Mean Regret

5

Apr 13, 2026

20 series benchmark pairs (test)

0.778Pearson r

4

Feb 26, 2026

HuggingGPT Human Evaluation Set 130 diverse requests (test)

93.89Passing Rate

1

Feb 26, 2026

Proposed Model Selection (PID-based)

100Performance

1

Feb 26, 2026

MUSTARD (unseen)

Proposed Model Selection (PID-based)

95.15Performance

1

Feb 26, 2026

Proposed Model Selection (PID-based)

99.35Performance

1

Feb 26, 2026

UR-FUNNY (unseen)

Proposed Model Selection (PID-based)

98.58Performance

1

Feb 26, 2026

ENRICO (unseen)

Proposed Model Selection (PID-based)

1Performance

1

Feb 26, 2026

Proposed Model Selection (PID-based)

99.78Performance

1

Feb 26, 2026

5 Synthetic Datasets (unseen)

Proposed Model Selection (PID-based)

0.999Performance

1

Feb 26, 2026

—

—Primary metric

0

Mar 10, 2026