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

Comparison research benchmarks · SOTA2 Research

Comparison

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

Loong Set 4: 200K–250K Tokens

55.8LLM Score

12

Feb 26, 2026

Loong Set 3: 100K–200K Tokens

57.84LLM Score

12

Feb 26, 2026

Loong Set 2: 50K–100K Tokens

64.34LLM Score

12

Feb 26, 2026

Loong Set 1: 10K–50K Tokens

75.65LLM Score

12

Feb 26, 2026

StethoBench (test)

70.7BERTScore

8

Mar 4, 2026

54.5ROUGE-1

8

Mar 4, 2026

Held-out games (test)

96.8Accuracy

6

Jun 2, 2026

Popular datasets

Loong StethoBench Held-out games

Follow for updates

Join SOTA2 Contact