Question Answering on TriviaQA

Metric: F1 (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	F1▼	Extra Data	Paper	Date↕	Code
1	SpanBERT	83.6	No	SpanBERT: Improving Pre-training by Representing...	2019-07-24	Code
2	BigBird-etc	80.9	No	Big Bird: Transformers for Longer Sequences	2020-07-28	Code
3	DPA-RAG	80.1	No	Understand What LLM Needs: Dual Preference Align...	2024-06-26	Code
4	LinkBERT (large)	78.2	No	LinkBERT: Pretraining Language Models with Docum...	2022-03-29	Code
5	DyREX	77.37	No	DyREx: Dynamic Query Representation for Extracti...	2022-10-26	Code
6	Search-o1	74.1	No	Search-o1: Agentic Search-Enhanced Large Reasoni...	2025-01-09	Code
7	MemoReader	73.26	Yes	-	-	-
8	S-Norm	71.32	Yes	Simple and Effective Multi-Paragraph Reading Com...	2017-10-29	Code
9	UnitedQA (Hybrid reader)	70.3	No	UnitedQA: A Hybrid Approach for Open Domain Ques...	2021-01-01	-
10	Reading Twice for NLU	56.73	No	Dynamic Integration of Background Knowledge in N...	2017-06-08	-
11	Mnemonic Reader	52.85	No	Reinforced Mnemonic Reader for Machine Reading C...	2017-05-08	Code
12	MEMEN	46.9	No	MEMEN: Multi-layer Embedding with Memory Network...	2017-07-28	-
13	ReasonBERTR	45.5	No	ReasonBERT: Pre-trained to Reason with Distant S...	2021-09-10	Code
14	ReasonBERTB	37.2	No	ReasonBERT: Pre-trained to Reason with Distant S...	2021-09-10	Code

#1SpanBERTSOTA
83.6
F1· 2019-07-24
SpanBERT: Improving Pre-training by Representing and Predicting Spans Code
#2BigBird-etc
80.9
F1· 2020-07-28
Big Bird: Transformers for Longer Sequences Code
#3DPA-RAG
80.1
F1· 2024-06-26
Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation Code
#4LinkBERT (large)
78.2
F1· 2022-03-29
LinkBERT: Pretraining Language Models with Document Links Code
#5DyREX
77.37
F1· 2022-10-26
DyREx: Dynamic Query Representation for Extractive Question Answering Code
#6Search-o1
74.1
F1· 2025-01-09
Search-o1: Agentic Search-Enhanced Large Reasoning Models Code
#7MemoReader
73.26
F1· Extra Data
No paper
#8S-NormSOTA
71.32
F1· Extra Data· 2017-10-29
Simple and Effective Multi-Paragraph Reading Comprehension Code
#9UnitedQA (Hybrid reader)
70.3
F1· 2021-01-01
UnitedQA: A Hybrid Approach for Open Domain Question Answering
#10Reading Twice for NLUSOTA
56.73
F1· 2017-06-08
Dynamic Integration of Background Knowledge in Neural NLU Systems
#11Mnemonic ReaderSOTA
52.85
F1· 2017-05-08
Reinforced Mnemonic Reader for Machine Reading Comprehension Code
#12MEMEN
46.9
F1· 2017-07-28
MEMEN: Multi-layer Embedding with Memory Networks for Machine Comprehension
#13ReasonBERTR
45.5
F1· 2021-09-10
ReasonBERT: Pre-trained to Reason with Distant Supervision Code
#14ReasonBERTB
37.2
F1· 2021-09-10
ReasonBERT: Pre-trained to Reason with Distant Supervision Code