Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Performance Prediction research benchmarks – Page 2 · SOTA2 Research

Performance Prediction

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Average within Task

4.29MAE

9

Feb 26, 2026

1.96MAE

9

Feb 26, 2026

0.8MAE

9

Feb 26, 2026

2.21MAE

9

Feb 26, 2026

0.89Train R^2

7

Jul 2, 2026

0.969Train R^2

7

Jul 2, 2026

0.89R^2 (Train)

7

Jul 2, 2026

0.685Train R^2

6

Jul 2, 2026

0.897Train R-squared

6

Jul 2, 2026

Performance Prediction Evaluation Suite 70B Model on GSM8k, MATH, BBH, TriviaQA, MBPP, AGIEval, DROP, MMLU-pro (evaluation sets)

1.55Mean Absolute Prediction Error (%)

6

Mar 10, 2026

ARC-LoRA (test)

0.32MAE

5

Mar 18, 2026

0.34MAE

5

Mar 18, 2026

AmericasNLP Spanish to Bribri 2023 (test)

0.32MAE

4

Feb 26, 2026

AmericasNLP Chatino to Spanish 2023 (test)

1.21MAE

4

Feb 26, 2026

AmericasNLP Bribri to Spanish 2023 (test)

0.16MAE

4

Feb 26, 2026

Chatino to Spanish

Neuron-wise MoS

0.01MAE

4

Feb 26, 2026

Bribri to Spanish

0.01MAE

4

Feb 26, 2026

1.96MAE

3

Jul 7, 2026

Spectral Signature

1.95MAE

3

Jul 7, 2026

Spectral Signature

3.25MAE

3

Jul 7, 2026

1.61MAE

3

Jul 7, 2026

BIG-bench (test)

1.144Boolean Expressions

3

Feb 26, 2026

BIG-bench (train)

2.487Boolean Expressions Score

3

Feb 26, 2026

Page 2 of 2

Popular datasets

ARC WMT Sentiment MMLU AmericasNLP

Follow for updates

Join SOTA2 Contact