Browse › Natural Language Processing › Common Sense Reasoning › WinoGrande

Common Sense Reasoning archive 2025-07-28

WinoGrande Benchmark (Common Sense Reasoning)

77 rows 60 with code listed 1 metric Dataset page

Syntology Since the archive (Syntology): 1 placed; 31 newer papers judged to report on this board so far.

Common sense reasoning tasks are intended to require the model to go beyond pattern recognition. Instead, the model should use "common sense" or world knowledge to make inferences.

The archive carries no text for this table; the description above is the archive's text for the task Common Sense Reasoning. 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; 76 of 77 rows carry one.

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.

Paper Code Ran Syntology Report
1 ST-MoE-32B 269B (fine-tuned) 96.1 – Paper Code 2022 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
2 Unicorn 11B (fine-tuned) 91.3 – 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
3 CompassMTL 567M with Tailor 90.5 – Paper Code 2022 linked, not harvested report
4 CompassMTL 567M 89.6 – Paper Code 2022 linked, not harvested report
5 UnifiedQA 11B (fine-tuned) 89.4 – 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
6 Claude 3 Opus (5-shot) 88.5 – Paper – 2024 no code linked report
7 GPT-4 (5-shot) 87.5 – Paper Code 2023 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
8 ExDeBERTa 567M 87 – Paper Code 2022 linked, not harvested report
9 LLaMA-2 13B + MixLoRA 86.3 – 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
10 LLaMA3 8B+MoSLoRA 85.8 – 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
11 PaLM 2-L (1-shot) 83.0 – Paper Code 2023 linked, not harvested report
12 LLaMA-3 8B + MixLoRA 82.1 – 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
13 ST-MoE-L 4.1B (fine-tuned) 81.7 – Paper Code 2022 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified report
14 GPT-3.5 (5-shot) 81.6 – Paper Code 2023 community repositories only · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified report
15 PaLM 540B (0-shot) 81.1 – Paper Code 2022 32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified report
16 Camelidae-8×34B 80.9 – Paper Code 2024 linked, not harvested report
17 PaLM 2-M (1-shot) 79.2 – Paper Code 2023 linked, not harvested report
18 RoBERTa-Winogrande 355M (fine-tuned) 79.1 – Paper Code 2019 linked, not harvested report
19 PaLM 2-S (1-shot) 77.9 – Paper Code 2023 linked, not harvested report
20 Mixtral 8x7B (0-shot) 77.2 – 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
21 PaLM 62B (0-shot) 77.0 – Paper Code 2022 32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified report
22 PaLM-cont 62B (0-shot) 77.0 – Paper Code 2022 32 ran (of which 16 constructed an object rather than computing a result; 24 with no instrument failure: 2 honoured, 1 violated, 21 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified report
23 LLaMA 65B (0-shot) 77.0 – 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
24 LLaMA-2 7B + MixLoRA 76.8 – 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
25 LLaMA 33B (0-shot) 76.0 – 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
26 Mistral 7B (0-shot) 75.3 – 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
27 Claude 3 Sonnet (5-shot) 75.1 – Paper – 2024 no code linked report
28 Chinchilla 70B (0-shot) 74.9 – 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
29 Claude 3 Haiku (5-shot) 74.2 – Paper – 2024 no code linked report
30 Mistral 7B (0-shot) 74.2 – 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
31 phi-1.5-web 1.3B (zero-shot) 74.0 – Paper Code 2023 linked, not harvested report
32 Unified QA 406M (fine-tuned) 73.3 – 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
33 LLaMA 13B (0-shot) 73.0 – 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 FLAN 137B (few-shot, k=16) 72.8 – Paper Code 2021 official: harvested for another paper · 0 ran · 1 unverified report
35 G-DAUG-Combo + RoBERTa-Large 71.4 – Paper Code 2020 official (archive's flag): 2 ran · 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) · 2 unverified report
36 FLAN 137B (0-shot) 71.2 – Paper Code 2021 official: harvested for another paper · 0 ran · 1 unverified report
37 RWKV v5 Eagle 7B 70.8 – – – not matched report
38 Branch-Train-MiX 4x7B (sampling top-1 expert) 70.6 – Paper Code 2024 linked, not harvested report
39 GPT-3 175B (0-shot) 70.2 – 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
40 Gopher 280B (0-shot) 70.1 – Paper Code 2021 linked, not harvested report
41 LLaMA 7B (0-shot) 70.1 – 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
42 BLOOM 176B (1-shot) 67 – Paper Code 2023 linked, not harvested report
43 Pythia 12B (5-shot) 66.6 – Paper Code 2023 linked, not harvested report
44 OPT 66B (1-shot) 66.1 – Paper Code 2023 linked, not harvested report
45 BERT-Winogrande 345M (fine-tuned) 64.9 – Paper Code 2019 linked, not harvested report
46 Bloomberg GPT (one-shot) 64.1 – Paper Code 2023 linked, not harvested report
47 Pythia 12B (0-shot) 63.9 – Paper Code 2023 linked, not harvested report
48 RoE-3B 61.60 – Paper Code 2023 official (archive's flag): 2 ran · 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) · 0 unverified report
49 Pythia 6.9B (0-shot) 60.9 – Paper Code 2023 linked, not harvested report
50 GPT-NeoX (one-shot) 60.6 – Paper Code 2023 linked, not harvested report
51 FLAN-T5-Large 783M 59.9 – Paper Code 2023 linked, not harvested report
52 Pythia 2.8B (0-shot) 59.4 – Paper Code 2023 linked, not harvested report
53 RoBERTa-DPR 355M (0-shot) 58.9 – Paper Code 2019 linked, not harvested report
54 ALBERT-xxlarge 235M 58.7 – Paper – 2021 no code linked report
55 Flipped-3B 58.56 – Paper Code 2022 linked, not harvested report
56 GPT-2-XL 1.5B 58.3 – Paper Code 2023 linked, not harvested report
57 T0-3B (CoT fine-tuned) 57.5 – Paper Code 2023 linked, not harvested report
58 GPT-3 Large 760M (0-shot) 57.4 – 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
59 RoBERTa-base 125M 56.3 – Paper – 2021 no code linked report
60 LaMini-F-T5 783M 56 – Paper Code 2023 linked, not harvested report
61 LaMini-GPT 1.5B 56 – Paper Code 2023 linked, not harvested report
62 BERT-large 345M 55.6 – Paper – 2021 no code linked report
63 KiC-770M 55.30 – Paper – 2022 no code linked report
64 T5-Large 738M 55.2 – Paper Code 2023 linked, not harvested report
65 LaMini-T5 738M 54.9 – Paper Code 2023 linked, not harvested report
66 RoBERTa-large 355M 54.9 – Paper – 2021 no code linked report
67 sMLP – deterministic 9.4B (0-shot) 54.3 – Paper – 2022 no code linked report
68 Switch Transformer 9B (0-shot) 53.4 – Paper – 2022 no code linked report
69 BERT-base 110M 53.1 – Paper – 2021 no code linked report
70 ALBERT-base 11M 52.8 – Paper – 2021 no code linked report
71 BERT-large 345M (0-shot) 51.9 – Paper Code 2019 linked, not harvested report
72 HASH Layers 10B (0-shot) 51.7 – Paper – 2022 no code linked report
73 Gshard 9B (0-shot) 51.1 – Paper – 2022 no code linked report
74 Base Layers 10B (0-shot) 51 – Paper – 2022 no code linked report
75 BERT-DPR 345M (0-shot) 51 – Paper Code 2019 linked, not harvested report
76 Random baseline 50 – Paper – 2021 no code linked report
77 RoBERTa-large 355M (0-shot) 50 – Paper Code 2019 linked, not harvested report

All 77 rows shown. 76 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). 28 rows have a graph line, from 15 distinct papers. Rows whose paper has a sample that ran: 26 (24 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument). Papers: 14 with a sample that ran: 12 with a run with no instrument failure, 2 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 28 rows with a graph line, 22 have an archive-official repository: on 10 a sample from it ran (8 with a run with no instrument failure), on 6 the samples that ran came from community repositories only, and on 4 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 234 samples: 169 ran (of which 36 constructed an object rather than computing a result; 125 with no instrument failure: 14 honoured, 7 violated, 104 with no contract checked; 44 where Syntology's instrument failed) · 65 unverified. Separately, 37 of those 234 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 ; 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), 52 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 1,555 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 31 proposed a result; of those 31, 22 gave no cell that passed the extractor's own checks, 8 were rejected by the independent check, 0 await a verdict and 1 was 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
YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference arXiv:2604.13556 YOCO++ 55.48 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

Syntology 1 entry, 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
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
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search arXiv:2609.13356 11 Sep 2026 9 harvested: 9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified refused by a rule: the table's column header does not name the leaderboard's metric
PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path... arXiv:2609.01024 1 Sep 2026 repository linked, no samples harvested rejected by the independent check
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
ARCHead: Activation-Metric Residual Correction for Large Language Model Output Heads arXiv:2608.02703 3 Aug 2026 20 harvested: 19 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 16 where Syntology's instrument failed) · 1 unverified refused by a rule: the value is not on the scale of the leaderboard column's archive values
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
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 rejected by the independent check
ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory arXiv:2606.25156 23 Jun 2026 9 harvested: 6 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; 4 where Syntology's instrument failed) · 3 unverified 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
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 refused by a rule: the table does not name the leaderboard's dataset
NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs arXiv:2605.29716 28 May 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 refused by a rule: the table does not name the leaderboard's dataset
Echoes within the Reasoning: Stealthy and Effective Watermarking via Chain of Thought arXiv:2605.28890 27 May 2026 repository linked, no samples harvested refused by a rule: the number the model quoted is not the number printed in the cell it pointed at
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
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
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
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
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model... arXiv:2604.12374 14 Apr 2026 24 harvested: 20 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; 12 where Syntology's instrument failed) · 4 unverified refused by a rule: the table's column header does not name the leaderboard's metric
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
Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score arXiv:2603.23985 25 Mar 2026 repository linked, no samples harvested refused by a rule: one configuration gave two values for one column
SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection arXiv:2603.22213 23 Mar 2026 11 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) · 5 unverified refused by a rule: the table's column header does not name the leaderboard's metric
GR-SAP: Generative Replay for Safety Alignment Preservation during Fine-Tuning arXiv:2603.10243 10 Mar 2026 10 harvested: 9 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; 5 where Syntology's instrument failed) · 1 unverified refused by a rule: one configuration gave two values for one column
Few-Step Diffusion Language Models via Trajectory Self-Distillation arXiv:2602.12262 12 Feb 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 row label the model quoted is not the row's label
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
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 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
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models arXiv:2601.07372 12 Jan 2026 8 harvested: 6 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified refused by a rule: the row label the model quoted is not the row's label
MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling arXiv:2511.00056 28 Oct 2025 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: the row label the model quoted is not the row's label
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
Prior-based Noisy Text Data Filtering: Fast and Strong Alternative For Perplexity arXiv:2509.18577 23 Sep 2025 13 harvested: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified refused by a rule: the table's column header does not name the leaderboard's metric

Syntology 31 newer papers judged to report on this board: the papers counted above as having proposed a result (1 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 22 counted above as giving no cell that passed the extractor's own checks are the 22 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