Browse › Natural Language Processing › Question Answering › PIQA
PIQA Benchmark (Question Answering)
67 rows
62 with code listed
1 metric
Dataset page
Syntology Since the archive (Syntology): 9 placed; 59 newer papers judged to report on this board so far .
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
Direction inferred from the metric name, not from the archive: Accuracy (higher is better). Points are placed at the row's paper date, not an evaluation date; 67 of 67 rows carry one.
Metric
Accuracy
Extra training data
The chart needs JavaScript; the table below carries every value.
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.
only rows whose paper has a sample that ran
only rows whose archive-official repository has a sample that ran
a run counts when it is
a run with no instrument failure any run, instrument failures included
hide rows using extra training data
Ran counts code from the row's paper that executed on a synthesized input, not this result.
Rank
Model
Accuracy Extra Training Data
Paper
Code
Year
Ran Syntology
Report
1
Unicorn 11B (fine-tuned)
90.1 –
Paper
Code
2021
official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
report
2
LLaMA3 8B+MoSLoRA
89.7 –
Paper
Code
2024
official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified
report
3
CompassMTL 567M with Tailor
88.3 –
Paper
Code
2022
linked, not harvested
report
4
LLaMA-3 8B + MixLoRA
87.6 –
Paper
Code
2024
official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified
report
5
DeBERTa-Large 304M
87.4 –
Paper
Code
2022
official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified
report
6
CompassMTL 567M
87.3 –
Paper
Code
2022
linked, not harvested
report
7
LLaMA-2 13B + MixLoRA
86.8 –
Paper
Code
2024
official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified
report
8
Shakti-LLM (2.5B)
86.2 –
Paper
–
2024
no code linked
report
9
DeBERTa-Large 304M (classification-based)
85.9 –
Paper
Code
2022
official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified
report
10
ExDeBERTa 567M
85.5 –
Paper
Code
2022
linked, not harvested
report
11
UnifiedQA 3B
85.3 –
Paper
Code
2020
official (archive's flag): 4 ran · 4 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified
report
12
PaLM 2-L (1-shot)
85.0 –
Paper
Code
2023
linked, not harvested
report
13
Mixtral 8x7B (0-shot)
83.6 –
Paper
Code
2024
5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result
report
14
PaLM 2-M (1-shot)
83.2 –
Paper
Code
2023
linked, not harvested
report
15
LLaMA-2 7B + MixLoRA
83.2 –
Paper
Code
2024
official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified
report
16
Mistral 7B (0-shot)
83.0 –
Paper
Code
2023
official (archive's flag): 9 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
report
17
LLaMA 65B (0-shot)
82.8 –
Paper
Code
2023
official: no sample here; runs from other or unrecorded repositories · 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified
report
18
LLaMA 2 70B (0-shot)
82.8 –
Paper
Code
2023
community repositories only · 33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified
report
19
Camelidae-8×34B
82.7 –
Paper
Code
2024
linked, not harvested
report
20
LLaMA 33B (0-shot)
82.3 –
Paper
Code
2023
official: no sample here; runs from other or unrecorded repositories · 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified
report
21
PaLM 2-S (1-shot)
82.2 –
Paper
Code
2023
linked, not harvested
report
22
Mistral 7B (0-shot)
82.2 –
Paper
Code
2024
5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 5 samples that ran constructed an object rather than computing a result
report
23
MT-NLG 530B (0-shot)
82.0 –
Paper
Code
2019
community repositories only · 12 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 35 unverified
report
24
LLaMA 2 34B (0-shot)
81.9 –
Paper
Code
2023
community repositories only · 33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified
report
25
Gopher 280B (0-shot)
81.8 –
Paper
Code
2021
linked, not harvested
report
26
Chinchilla 70B (0-shot)
81.8 –
Paper
Code
2022
8 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified
report
27
FLAN 137B (few-shot, k=10)
81.7 –
Paper
Code
2021
official: harvested for another paper · 0 ran · 1 unverified
report
28
OPT-175B
81.07 –
Paper
Code
2023
official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
report
29
GPT-3 175B (0-shot)
81.0 –
Paper
Code
2020
community repositories only · 45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified
report
30
SparseGPT 175B (50% Sparsity)
80.63 –
Paper
Code
2023
official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
report
31
FLAN 137B (0-shot)
80.5 –
Paper
Code
2021
official: harvested for another paper · 0 ran · 1 unverified
report
32
LLaMA 2 13B (0-shot)
80.5 –
Paper
Code
2023
community repositories only · 33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified
report
33
LLaMA 13B (0-shot)
80.1 –
Paper
Code
2023
official: no sample here; runs from other or unrecorded repositories · 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified
report
34
LLaMA 7B (0-shot)
79.8 –
Paper
Code
2023
official: no sample here; runs from other or unrecorded repositories · 37 ran (of which 9 constructed an object rather than computing a result; 25 with no instrument failure: 3 honoured, 0 violated, 22 with no contract checked; 12 where Syntology's instrument failed) · 21 unverified
report
35
SparseGPT 175B (4:8 Sparsity)
79.54 –
Paper
Code
2023
official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
report
36
SparseGPT 175B (2:4 Sparsity)
79.54 –
Paper
Code
2023
official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
report
37
RoBERTa-Large 355M
79.4 –
Paper
Code
2019
community repositories only · 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified
report
38
LLaMA 2 7B (0-shot)
78.8 –
Paper
Code
2023
community repositories only · 33 ran (of which 7 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 1 violated, 18 with no contract checked; 13 where Syntology's instrument failed) · 19 unverified
report
39
Bloomberg GPT 50B (1-shot)
77.9 –
Paper
Code
2023
linked, not harvested
report
40
OPT 66B (1-shot)
77.6 –
Paper
Code
2023
linked, not harvested
report
41
RoBERTa-large 355M (fine-tuned)
77.1 –
Paper
Code
2019
linked, not harvested
report
42
phi-1.5-web (1.3B)
77 –
Paper
Code
2023
linked, not harvested
report
43
BLOOM 176B (1-shot)
77 –
Paper
Code
2023
linked, not harvested
report
44
Pythia 12B (5-shot)
76.7 –
Paper
Code
2023
linked, not harvested
report
45
Open-LLaMA-3B-v2
76.2 –
Paper
Code
2023
official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
report
46
Pythia 12B (0-shot)
76 –
Paper
Code
2023
linked, not harvested
report
47
Sheared-LLaMA-2.7B
75.8 –
Paper
Code
2023
official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
report
48
GPT-NeoX 20B (1-shot)
75.8 –
Paper
Code
2023
linked, not harvested
report
49
Pythia 6.9B (0-shot)
75.2 –
Paper
Code
2023
linked, not harvested
report
50
Sheared-LLaMA-1.3B
73.4 –
Paper
Code
2023
official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified
report
51
sMLP - deterministic 9.4B (0-shot)
73 –
Paper
–
2022
no code linked
report
52
GPT-3 Large 760M (0-shot)
72.9 –
Paper
Code
2020
community repositories only · 45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified
report
53
FLAN-T5-Large 783M
72.2 –
Paper
Code
2023
linked, not harvested
report
54
LaMini-GPT 1.5B
71.3 –
Paper
Code
2023
linked, not harvested
report
55
LaMini-F-T5 783M
70.6 –
Paper
Code
2023
linked, not harvested
report
56
GPT-2-XL 1.5B
70.5 –
Paper
Code
2023
linked, not harvested
report
57
Pythia 1B (5-shot)
70.4 –
Paper
Code
2023
linked, not harvested
report
58
GPT-2-small 124M (fine-tuned)
69.2 –
Paper
Code
2019
linked, not harvested
report
59
Gshard 9B
68.1 –
Paper
–
2022
no code linked
report
60
LaMini-T5 738M
67.2 –
Paper
Code
2023
linked, not harvested
report
61
BERT-large 340M (fine-tuned)
66.8 –
Paper
Code
2019
linked, not harvested
report
62
BERT-Large 340M
66.7 –
Paper
Code
2018
official: no sample here; runs from other or unrecorded repositories · 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified
report
63
Base Layers 10B (0-shot)
63.8 –
Paper
–
2022
no code linked
report
64
HASH Layers 10B (0-shot)
63.8 –
Paper
–
2022
no code linked
report
65
T5-Large 738M
55.9 –
Paper
Code
2023
linked, not harvested
report
66
OPT-175B (50% Sparsity)
54.73 –
Paper
Code
2023
official (archive's flag): 2 ran · 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified
report
67
Random chance baseline
50 –
Paper
Code
2019
linked, not harvested
report
All 67 rows shown. 67 link to a paper page on this site; 0 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 ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”: of the code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and U are unverified (harvested, no recorded run). Of the N, C constructed an object rather than computing a result (a part of N, never taken away from it), K ran with no instrument failure (honoured or violated the contract Syntology drafted, or ran with no contract checked) and I are failures of Syntology's instrument, not of the code (a wrong contract draft, or a contract check that could not 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). 35 rows have a graph line, from 17 distinct papers. Rows whose paper has a sample that ran: 33 (33 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument). Papers: 16 with a sample that ran: 16 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument. Whose code ran. When the archive marks a repository official for the row's paper, the cell starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code): “official (archive's flag): N ran” counts the samples from it that ran, instrument failures included; “official: harvested, nothing ran”; when it has no sample for this paper and other samples ran, “community repositories only” if every one came from a repository the archive lists for the paper but neither marks official nor records as mentioned in it, or one Syntology harvested outside the archive's links, and “official: no sample here; runs from other or unrecorded repositories” if any came from a repository named in the paper or found in its text by Syntology, or has no repository recorded; “official: harvested for another paper” (no sample from it is linked to this paper) or “official: not harvested”. No state is printed when the archive marks none official. The cell's tooltip names the repositories the samples that ran came from. Of the 35 rows with a graph line, 32 have an archive-official repository: on 17 a sample from it ran (12 with a run with no instrument failure), on 8 the samples that ran came from community repositories only, and on 5 from other or unrecorded repositories. The filters above hide rows and never renumber them; the first two count, by default, only a run with no instrument failure, and offer any run, instrument failures included. Counting each paper once, of 1,008 samples: 518 ran (of which 115 constructed an object rather than computing a result; 400 with no instrument failure: 35 honoured, 10 violated, 355 with no contract checked; 118 where Syntology's instrument failed) · 490 unverified. Separately, 256 of those 1,008 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. Syntology's record for this page last changed 2026-10-05 ; when this build read Syntology's graph is in the build record . Per-sample status is on the paper page; each Ran cell links to that paper's sample list. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect .
Since the archive: results placed by Syntology Syntology
Of the 8,888 newer papers whose tables Syntology has read (8,886 checked in full and 2 with a leaderboard still awaiting a verdict), 83 had this board among the leaderboards the extractor considered for their tables (it keeps at most 10 boards per paper and 4 per dataset; the lists of 1,543 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 59 proposed a result; of those 59, 31 gave no cell that passed the extractor's own checks, 18 were rejected by the independent check, 1 awaits a verdict and 9 were placed. Syntology has checked 8,886 of the 18,637 papers on this site that are newer than the archive (for 3,717 of them no archive leaderboard matched the paper's tables, so there was nothing further to check); 733 were read and have nothing to place (arXiv has no HTML version of the paper, or that version has no tables), 41 could not be read (the extractor's reply could not be parsed), and results from the other 8,977 appear after they are checked.
Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows above.
Measured before publishing, on held-out archive papers: the extractor was given 883 of them and produced output for 881 (the other 2 had no title and were excluded before any model call, so they are not part of this measurement). A model adjudicator (Claude Opus 5.5), blind to which entries were real, judged 108 of 110 accepted entries correct on those held-out archive papers; its own controls: 69 of 70 archive-confirmed entries judged true, 101 of 103 corrupted copies judged false. It was not measured on the newer papers whose results are placed on this site.
Paper
Method (configuration)
Accuracy Date
Where in the paper
Code Syntology
Report
Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax... arXiv:2609.18131
2.54 Colla-Q
80.5 16 Sep 2026
Table 1, row “2.54 Colla-Q”Caption: “Table 1: Zero-shot task performance (%) of the quantized Mixtral 8 × 7B on…”
repository linked, no samples harvested
report
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference arXiv:2606.26587
Llama-3.1-8B SharQ
80.20 25 Jun 2026
Table 1, row “Llama-3.1-8B SharQ”Caption: “Table 1: Zero-shot and few-shot evaluation of SharQ across three LLMs. Accuracy…”
3 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
report
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM... arXiv:2605.29843
4 HARP · Llama 2 7B
78.3 28 May 2026
Table 2, row “4 HARP”Caption: “Table 2: Zero-shot accuracy ( acc , ↑ ) under QuIP# (RHT) vs. HARP on Llama 2…”
9 harvested: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
report
YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference arXiv:2604.13556
YOCO++
71.16 15 Apr 2026
Table 1, row “YOCO++”Caption: “Table 1 : Zero-shot accuracy on commonsense reasoning tasks.”
5 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified
report
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with... arXiv:2604.11841
Llama-3-8B PERA ( r=32 )
89.83 12 Apr 2026
Table 1, row “Llama-3-8B PERA ( r=32 )”Caption: “Table 1: Accuracy(%) comparison of LLaMA model with various fine-tuned methods…”
18 harvested: 15 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified
report
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large... arXiv:2604.06291
Qwen2.5-7B TalkLoRA ( r=16 )
90.9 7 Apr 2026
Table 1, row “Qwen2.5-7B TalkLoRA ( r=16 )”Caption: “Table 1: Accuracy(%) comparison of various methods fine-tuning Qwen2.5-7B,…”
2 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result
report
High-Fidelity Pruning for Large Language Models arXiv:2603.08083
20% HFPrune (Ours)
77.3 9 Mar 2026
Table 1, row “20% HFPrune (Ours)”Caption: “Table 1: Zero-shot performance on LLaMA-2-7B, which are finetuned on the LaMini…”
held, no recorded run
report
NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models arXiv:2602.06694
Q3-8
63.32 6 Feb 2026
Table 3, row “Q3-8”Caption: “Table 3 : Zero-shot accuracy comparison on commonsense reasoning tasks using…”
5 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified
report
RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs arXiv:2602.05367
Gemma3-12B RaBiT (Ours)
78.95 5 Feb 2026
Table 10, row “Gemma3-12B RaBiT (Ours)”Caption: “Table 10 : Detailed Zero-Shot Reasoning Accuracy on Gemma Models (%).…”
6 harvested: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified
report
Syntology 9 entries, one per paper, newest first by month (the arXiv date, else the month in the arXiv id), then by arXiv id. Each value is the cell text as the paper prints it; under "Where in the paper" is the start of the table's caption as the paper prints it (ranking words shown as […]; a caption carrying TeX this page does not render, or quoting a percentage figure, is left to the hover and says so), and hovering there gives the caption start and each value's column header. Not part of the archive and not in the chart above. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
Newer papers whose tables Claude Sonnet 4.5 judged to report on this benchmark (a model's judgement, not a result; newest first by arXiv id)
Paper
arXiv date
Ran Syntology
Outcome
Distilling Sequential Computation in Transformer Language Models arXiv:2609.27233
23 Sep 2026
repository linked, no samples harvested
rejected by the independent check
ChainDoRA: Tensor-Train Factorized Weight-Decomposed Low-Rank Adaptation for... arXiv:2609.25058
8 Sep 2026
repository linked, no samples harvested
rejected by the independent check
Colla-Q: Toward Collaborative Experts in MoE Quantization via Minimax Precision Balancing arXiv:2609.18131
16 Sep 2026
repository linked, no samples harvested
placed
T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With... arXiv:2609.15160
14 Sep 2026
3 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
refused by a rule: the row label the model quoted is not the row's label
Instella-MoE Technical Report arXiv:2609.00791
1 Sep 2026
5 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
refused by a rule: the quoted value appears more than once in the row
Rethinking Expressivity and Efficiency in Test-Time Training arXiv:2608.21308
21 Aug 2026
8 harvested: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified
refused by a rule: one configuration gave two values for one column
Gated Recurrent Transformers: Expressive Depth through Recurrent Modulation arXiv:2608.15062
15 Aug 2026
6 harvested: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 6 samples that ran constructed an object rather than computing a result
refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
Commit Locally, Exit Globally: Coordinating Adaptive Sampling and Early Exit in... arXiv:2607.28166
30 Jul 2026
15 harvested: 15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 3 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified
refused by a rule: the row label the model quoted is not the row's label
The State-Prediction Separation Hypothesis arXiv:2607.01218
1 Jul 2026
6 harvested: 3 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified
rejected by the independent check
CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs arXiv:2606.26650
25 Jun 2026
repository linked, no samples harvested
refused by a rule: the row is an ablation variant, not the method itself
SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference arXiv:2606.26587
25 Jun 2026
3 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
placed
Scaling Linear Mode Connectivity and Merging to Billion Parameter Pretrained Transformers arXiv:2606.23607
22 Jun 2026
repository linked, no samples harvested
rejected by the independent check
Variable-Width Transformers arXiv:2606.18246
16 Jun 2026
2 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
rejected by the independent check
Muonᵖ: Muon with Fractional Spectral Powers arXiv:2606.13867
11 Jun 2026
held, no recorded run
rejected by the independent check
PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training arXiv:2606.06470
4 Jun 2026
9 harvested: 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified
refused by a rule: the value is not on the scale of the leaderboard column's archive values
q0: Primitives for Hyper-Epoch Pretraining arXiv:2606.03938
2 Jun 2026
7 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified
refused by a rule: the model pointed at a header row
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression arXiv:2606.02559
1 Jun 2026
30 harvested: 14 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 9 where Syntology's instrument failed) · 16 unverified
rejected by the independent check
CART: Context-Anchored Recurrent Transformer -- A Parameter-Efficient Architecture... arXiv:2606.01495
31 May 2026
16 harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified
rejected by the independent check
DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts arXiv:2606.01062
31 May 2026
4 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified
rejected by the independent check
ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression arXiv:2606.00494
30 May 2026
6 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified
refused by a rule: one configuration gave two values for one column
D³: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training arXiv:2605.31164
29 May 2026
repository linked, no samples harvested
refused by a rule: the row label the model quoted is not the row's label
HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization arXiv:2605.29843
28 May 2026
9 harvested: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
placed
EVA: Accelerating LLM Decoding via an Efficient Vector Quantization Architecture arXiv:2605.24144
22 May 2026
13 harvested: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified
refused by a rule: one configuration gave two values for one column
Delta Attention Residuals arXiv:2605.18855
13 May 2026
3 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
rejected by the independent check
Generating Pretraining Tokens from Organic Data for Data-Bound Scaling arXiv:2605.17849
18 May 2026
3 harvested: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified
refused by a rule: the table's column header does not name the leaderboard's metric
WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points arXiv:2605.17471
17 May 2026
4 harvested: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result
refused by a rule: one configuration gave two values for one column
MuonQ: Enhancing Low-Bit Muon Quantization via Directional Fidelity Optimization arXiv:2605.11396
12 May 2026
15 harvested: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified
rejected by the independent check
BCJR-QAT: A Differentiable Relaxation of Trellis-Coded Weight Quantization arXiv:2605.10655
11 May 2026
9 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified
rejected by the independent check
Synthetic Pre-Pre-Training Improves Language Model Robustness to Noisy Pre-Training Data arXiv:2605.10129
11 May 2026
2 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
refused by rules: the model pointed at a header row; the number the model quoted is not the number printed in the cell it pointed at
EdgeFlowerTune: Evaluating Federated LLM Fine-Tuning Under Realistic Edge System Constraints arXiv:2605.08636
9 May 2026
19 harvested: 19 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 18 where Syntology's instrument failed) · 0 unverified
rejected by the independent check
MDN: Parallelizing Stepwise Momentum for Delta Linear Attention arXiv:2605.05838
7 May 2026
7 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified
refused by a rule: one configuration gave two values for one column
Statistically-Lossless Quantization of Large Language Models arXiv:2605.02404
4 May 2026
repository linked, no samples harvested
refused by a rule: the row label the model quoted is not the row's label
YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference arXiv:2604.13556
15 Apr 2026
5 harvested: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified
placed
Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order... arXiv:2604.11841
12 Apr 2026
18 harvested: 15 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 12 where Syntology's instrument failed) · 3 unverified
placed
Optimal Decay Spectra for Linear Recurrences arXiv:2604.07658
8 Apr 2026
5 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified
refused by a rule: the row is an ablation variant, not the method itself
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models arXiv:2604.06291
7 Apr 2026
2 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result
placed
Swift-SVD: Theoretical Optimality Meets Practical Efficiency in Low-Rank LLM Compression arXiv:2604.01609
2 Apr 2026
1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
refused by a rule: the value is not on the scale of the leaderboard column's archive values
AMALIA Technical Report: A Fully Open Source Large Language Model for European Portuguese arXiv:2603.26511
27 Mar 2026
repository linked, no samples harvested
refused by a rule: the table's column header does not name the leaderboard's metric
Scaling Attention via Feature Sparsity arXiv:2603.22300
17 Mar 2026
repository linked, no samples harvested
rejected by the independent check
SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization arXiv:2603.08185
9 Mar 2026
6 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified
refused by a rule: the table's column header does not name the leaderboard's metric
High-Fidelity Pruning for Large Language Models arXiv:2603.08083
9 Mar 2026
held, no recorded run
placed
ROSE: Reordered SparseGPT for More Accurate One-Shot Large Language Models Pruning arXiv:2603.05878
6 Mar 2026
held, no recorded run
rejected by the independent check
3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs arXiv:2603.01376
2 Mar 2026
6 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified
refused by a rule: the table's column header does not name the leaderboard's metric
PRISM: Parallel Residual Iterative Sequence Model arXiv:2602.10796
11 Feb 2026
held, no recorded run
rejected by the independent check
SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm arXiv:2602.08064
8 Feb 2026
1 harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
refused by a rule: one configuration gave two values for one column
NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models arXiv:2602.06694
6 Feb 2026
5 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified
placed
RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs arXiv:2602.05367
5 Feb 2026
6 harvested: 5 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified
placed
SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference arXiv:2602.00942
1 Feb 2026
3 harvested: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 2 samples that ran constructed an object rather than computing a result
awaiting a verdict
KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices arXiv:2601.21579
29 Jan 2026
10 harvested: 10 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 5 honoured, 3 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified
rejected by the independent check
HESTIA: A Hessian-Guided Differentiable Quantization-Aware Training Framework for... arXiv:2601.20745
28 Jan 2026
6 harvested: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified
refused by a rule: the table's column header does not name the leaderboard's metric
Sherry: Hardware-Efficient 1.25-Bit Ternary Quantization via Fine-grained Sparsification arXiv:2601.07892
12 Jan 2026
repository linked, no samples harvested
refused by a rule: the table's column header does not name the leaderboard's metric
PuzzleMoE: Efficient Compression of Large Mixture-of-Experts Models via Sparse Expert... arXiv:2511.04805
6 Nov 2025
8 harvested: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified
refused by a rule: one configuration gave two values for one column
DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization arXiv:2511.04063
6 Nov 2025
16 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 10 unverified
refused by a rule: one configuration gave two values for one column
Learning Grouped Lattice Vector Quantizers for Low-Bit LLM Compression arXiv:2510.20984
23 Oct 2025
repository linked, no samples harvested
refused by a rule: one configuration gave two values for one column
AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs arXiv:2510.10467
12 Oct 2025
27 harvested: 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 15 unverified
refused by a rule: one configuration gave two values for one column
Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a... arXiv:2510.03206
3 Oct 2025
2 harvested: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified
rejected by the independent check
Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability arXiv:2510.00565
1 Oct 2025
1 harvested: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result
refused by a rule: one configuration gave two values for one column
HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space arXiv:2509.22299
26 Sep 2025
8 harvested: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified
refused by rules: the value is not on the scale of the leaderboard column's archive values; the quoted value appears more than once in the row
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models arXiv:2509.12019
15 Sep 2025
6 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified
refused by a rule: one configuration gave two values for one column
Syntology 59 newer papers judged to report on this board: the papers counted above as having proposed a result (9 placed); every one is listed here and in the JSON twin . The order is the arXiv identifier's, newest first, not a rank. The judgement is the model's, read from the paper's own tables; the outcome is what Syntology's checks did with it, and no value from a paper that was not placed is printed. “refused by a rule” names the extractor's rule; “no cell passed the extractor's checks” means the extractor's record holds no cell for this board, passed or refused. The 31 counted above as giving no cell that passed the extractor's own checks are the 31 marked “refused by a rule”. Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
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