</> Code with Papers by Syntology

Browse › Natural Language Processing › Question Answering › SQuAD1.1 dev

Question Answering archive 2025-07-28

SQuAD1.1 dev Benchmark (Question Answering)

55 rows 45 with code listed 2 metrics Dataset page

Question answering can be segmented into domain-specific tasks like community question answering and knowledge-base question answering. Popular benchmark datasets for evaluation question answering systems include SQuAD, HotPotQA, bAbI, TriviaQA, WikiQA, and many others. Models for question answering are typically evaluated on metrics like EM and F1. Some recent top performing models are T5 and XLNet.

The archive carries no text for this table; the description above is the archive's text for the task Question Answering. archive 2025-07-28

Over time archive 2025-07-28

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: F1 (higher is better). Not inferred (points only, no best-so-far line): EM. Points are placed at the row's paper date; 55 of 55 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

Paper Code Ran Syntology Report
1 T5-11B 90.0695.64 ✓ Paper Code 2019 2 of 31 ran · 29 unverified report
2 LUKE 89.8 ✓ Paper Code 2020 3 of 10 ran · 7 unverified report
3 XLNet+DSC 89.7995.77 ✓ Paper Code 2019 0 of 3 ran · 3 unverified report
4 XLNet (single model) 89.795.1 ✓ Paper Code 2019 10 of 24 ran · 14 unverified report
5 T5-3B 88.5394.95 ✓ Paper Code 2019 2 of 31 ran · 29 unverified report
6 T5-Large 770M 86.6693.79 – Paper Code 2019 2 of 31 ran · 29 unverified report
7 BERT-LARGE (Ensemble+TriviaQA) 86.292.2 – Paper Code 2018 204 of 659 ran · 455 unverified report
8 T5-Base 85.4492.08 ✓ Paper Code 2019 2 of 31 ran · 29 unverified report
9 BERT-LARGE (Single+TriviaQA) 84.291.1 – Paper Code 2018 204 of 659 ran · 455 unverified report
10 BERT-Large-uncased-PruneOFA (90% unstruct sparse) 83.3590.2 – Paper Code 2021 linked, not harvested report
11 BERT-Large-uncased-PruneOFA (90% unstruct sparse, QAT Int8) 83.2290.02 – Paper Code 2021 linked, not harvested report
12 BERT-Base-uncased-PruneOFA (85% unstruct sparse) 81.188.42 – Paper Code 2021 linked, not harvested report
13 BERT-Base-uncased-PruneOFA (85% unstruct sparse, QAT Int8) 80.8488.24 – Paper Code 2021 linked, not harvested report
14 BERT-Base-uncased-PruneOFA (90% unstruct sparse) 79.8387.25 – Paper Code 2021 linked, not harvested report
15 TinyBERT-6 67M 79.787.5 – Paper Code 2019 0 of 4 ran · 4 unverified report
16 T5-Small 79.187.24 ✓ Paper Code 2019 2 of 31 ran · 29 unverified report
17 R.M-Reader (single) 78.9 86.3 – Paper Code 2017 linked, not harvested report
18 DensePhrases 78.386.3 – Paper Code 2020 linked, not harvested report
19 DistilBERT-uncased-PruneOFA (85% unstruct sparse) 78.185.82 – Paper Code 2021 linked, not harvested report
20 DistilBERT 77.7 – Paper Code 2019 19 of 27 ran · 8 unverified report
21 DistilBERT-uncased-PruneOFA (85% unstruct sparse, QAT Int8) 77.0385.13 – Paper Code 2021 linked, not harvested report
22 DistilBERT-uncased-PruneOFA (90% unstruct sparse) 76.9184.82 – Paper Code 2021 linked, not harvested report
23 KAR 76.784.9 – Paper – 2018 no code linked report
24 SAN (single) 76.23584.056 – Paper Code 2017 linked, not harvested report
25 DistilBERT-uncased-PruneOFA (90% unstruct sparse, QAT Int8) 75.6283.87 – Paper Code 2021 linked, not harvested report
26 FusionNet 75.383.6 – Paper Code 2017 linked, not harvested report
27 QANet (data aug x3) 75.183.8 – Paper Code 2018 7 of 19 ran · 12 unverified report
28 QANet (data aug x2) 74.583.2 – Paper Code 2018 7 of 19 ran · 12 unverified report
29 DCN+ (single) 74.583.1 – Paper Code 2017 linked, not harvested report
30 QANet 73.682.7 – Paper Code 2018 7 of 19 ran · 12 unverified report
31 PhaseCond (single) 72.181.4 – Paper – 2017 no code linked report
32 SRU 71.480.2 – Paper Code 2017 1 of 1 ran · 0 unverified report
33 Smarnet 71.36280.183 – Paper – 2017 no code linked report
34 DCN (Char + CoVe) 71.379.9 – Paper Code 2017 3 of 3 ran · 0 unverified report
35 R-NET (single) 71.179.5 – Paper – 2017 no code linked report
36 Ruminating Reader 70.679.5 – Paper – 2017 no code linked report
37 FastQAExt (beam-size 5) 70.378.5 – Paper Code 2017 0 of 2 ran · 2 unverified report
38 DrQA (Document Reader only) 69.578.8 – Paper Code 2017 1 of 1 ran · 0 unverified report
39 jNet (TreeLSTM adaptation, QTLa, K=100) 69.1078.38 – Paper – 2017 no code linked report
40 SEDT-LSTM 67.89 77.42 – Paper – 2017 no code linked report
41 BIDAF (single) 67.777.3 – Paper Code 2016 8 of 11 ran · 3 unverified report
42 SECT-LSTM 67.6577.19 – Paper – 2017 no code linked report
43 RASOR 66.474.9 – Paper Code 2016 linked, not harvested report
44 MPCM 66.175.8 – Paper Code 2016 linked, not harvested report
45 DCN 65.475.6 – Paper Code 2016 linked, not harvested report
46 FABIR 65.175.6 – Paper Code 2018 linked, not harvested report
47 Match-LSTM with Bi-Ans-Ptr (Boundary+Search+b) 64.1 64.7 – Paper Code 2016 3 of 3 ran · 0 unverified report
48 OTF dict+spelling (single) 63.06 – Paper – 2017 no code linked report
49 DCR 62.571.2 – Paper – 2016 no code linked report
50 FG fine-grained gate 59.9571.25 – Paper Code 2016 linked, not harvested report
51 LUKE 483M 95 – Paper Code 2020 3 of 10 ran · 7 unverified report
52 BART Base (with text infilling) 90.8 – Paper Code 2019 22 of 53 ran · 31 unverified report
53 BERT large (LAMB optimizer) 90.584 – Paper Code 2019 1 of 11 ran · 10 unverified report
54 DistilBERT 66M 85.8 – Paper Code 2019 19 of 27 ran · 8 unverified report
55 BiDAF + Self Attention + ELMo 85.6 – Paper Code 2018 23 of 58 ran · 35 unverified report

All 55 rows shown. 55 link to a paper page on this site; 7 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 26 rows have a graph line, from 17 distinct papers; 23 rows (14 papers) have at least one sample that ran. Counting each paper once: Syntology ran 307 of 920 samples; 613 unverified. Separately, 212 of those 920 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections