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

Long-form Question Answering research benchmarks – Page 2 · SOTA2 Research

Long-form Question Answering

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

ELI5 KILT (test)

25.4F1

8

Feb 27, 2026

32.61BLEU

7

Apr 16, 2026

ATTR. FIRST_CoT

38.6ROUGE-L

7

Feb 26, 2026

MM-Telco Telecom Blog

27ROUGE-1

6

Apr 20, 2026

Long-form QA Datasets Average No-RAG

75.88VeriScore F1@k

5

Jul 7, 2026

ELI5 standard original

Fourier-BART-FP

26.9RL Score

5

Feb 26, 2026

GroundBench (test)

87.5Faithfulness (Full)

4

Feb 26, 2026

90.9AIS (Decomposition)

4

Feb 26, 2026

KILT ELI5 (test)

36.3Retrieval Score

4

Feb 26, 2026

Error-Informed Refinement (EIR)

100Comprehensiveness

3

Feb 26, 2026

38.2R-L

3

Feb 26, 2026

KILT ELI5 (dev test)

26.3RL Score

3

Feb 26, 2026

MS MARCO (evaluation)

2.7Fluency

2

Feb 26, 2026

Page 2 of 2

Popular datasets

ELI5 Long-form QA Datasets Biography LongFact Fava

Follow for updates

Join SOTA2 Contact