Browse › Natural Language Processing › Common Sense Reasoning › CommonsenseQA

Common Sense Reasoning archive 2025-07-28

CommonsenseQA Benchmark (Common Sense Reasoning)

38 rows 35 with code listed 1 metric Dataset page

Syntology Since the archive (Syntology): 2 placed; 16 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; 38 of 38 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 GPT-4o (HPT) 92.54 – Paper Code 2024 linked, not harvested report
2 DeBERTaV3-large+KEAR 91.2 ✓ Paper Code 2021 linked, not harvested report
3 PaLM 2 (few‑shot, CoT, SC) 90.4 ✓ Paper Code 2023 linked, not harvested report
4 KEAR 89.4 ✓ Paper Code 2021 linked, not harvested report
5 DEKCOR 83.3 ✓ Paper Code 2020 linked, not harvested report
6 Unicorn 11B (fine-tuned) 79.3 – 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
7 MUPPET Roberta Large 79.2 ✓ Paper Code 2021 linked, not harvested report
8 UnifiedQA 11B (fine-tuned) 79.1 ✓ 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
9 DRAGON 78.2 – Paper Code 2022 official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified report
10 T5-XXL 11B (fine-tuned) 78.1 – 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
11 Albert Lan et al. (2020) (ensemble) 76.5 – Paper Code 2019 official (archive's flag): 6 ran · 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified report
12 UnifiedQA 11B (zero-shot) 76.2 – 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
13 QA-GNN 76.1 – Paper Code 2021 official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 17 unverified report
14 XLNet+GraphReason 75.3 – Paper Code 2019 official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified report
15 GrapeQA: PEGA 73.5 – Paper – 2023 no code linked report
16 RoBERTa+HyKAS Ma et al. (2019) 73.2 – Paper – 2019 no code linked report
17 GPT-3 Direct Finetuned 73.0 – Paper Code 2021 linked, not harvested report
18 STaR (on GPT-J) 72.3 – Paper Code 2022 official: harvested, nothing ran · 0 ran · 2 unverified report
19 RoBERTa-Large 355M 72.1 – 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
20 STaR without Rationalization (on GPT-J) 68.8 – Paper Code 2022 official: harvested, nothing ran · 0 ran · 2 unverified report
21 OPT 66B (1-shot) 66.4 – Paper Code 2023 linked, not harvested report
22 Bloomberg GPT 50B (1-shot) 65.5 – Paper Code 2023 linked, not harvested report
23 CAGE-reasoning 64.7 – Paper Code 2019 5 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; 4 where Syntology's instrument failed) · 0 unverified report
24 BLOOM 176B (1-shot) 64.2 – Paper Code 2023 linked, not harvested report
25 UnifiedQA 440M (fine-tuned) 64 – 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
26 BART-large 440M (fine-tuned) 62.5 – 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
27 BERT_CSlarge 62.2 – Paper – 2019 no code linked report
28 GPT-NeoX 20B (1-shot) 60.4 – Paper Code 2023 linked, not harvested report
29 GPT-J Direct Finetuned 60.0 – Paper Code 2022 official: harvested, nothing ran · 0 ran · 2 unverified report
30 KagNet 58.9 ✓ Paper Code 2019 official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
31 BERT-LARGE 55.9 ✓ Paper Code 2018 community repositories only · 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) · 0 unverified report
32 UL2 20B (chain-of-thought + self-consistency) 55.7 – Paper Code 2022 community repositories only · 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
33 Few-shot CoT LaMDA 137B 55.6 – Paper Code 2022 official: harvested, nothing ran · 0 ran · 2 unverified report
34 UL2 20B (chain-of-thought) 51.4 – Paper Code 2022 community repositories only · 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
35 Few-shot CoT GPT-J 36.6 – Paper Code 2022 official: harvested, nothing ran · 0 ran · 2 unverified report
36 UL2 20B (zero-shot) 34.2 – Paper Code 2022 community repositories only · 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified report
37 Chain of thought ASDiv 28.6 – Paper Code 2022 5 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; 1 where Syntology's instrument failed) · 2 unverified report
38 Few-shot Direct GPT-J 20.9 – Paper Code 2022 official: harvested, nothing ran · 0 ran · 2 unverified report

All 38 rows shown. 38 link to a paper page on this site; 8 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). 24 rows have a graph line, from 13 distinct papers. Rows whose paper has a sample that ran: 18 (18 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument). Papers: 12 with a sample that ran: 12 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 24 rows with a graph line, 22 have an archive-official repository: on 11 a sample from it ran (11 with a run with no instrument failure), on 5 the samples that ran came from community repositories only, and on 0 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 291 samples: 193 ran (of which 31 constructed an object rather than computing a result; 156 with no instrument failure: 12 honoured, 1 violated, 143 with no contract checked; 37 where Syntology's instrument failed) · 98 unverified. Separately, 63 of those 291 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), 32 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 1,576 of the 8,888 were already full without this board, so if it was crowded out of them it is not counted), and 16 proposed a result; of those 16, 13 gave no cell that passed the extractor's own checks, 1 was rejected by the independent check, 0 await a verdict and 2 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
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on... arXiv:2607.17266 DoG (Ours) · GPT 86.0 19 Jul 2026 Table 2, row “DoG (Ours)”Caption: “Table 2 : Accuracy (%) comparison of DoG and DoG-E with different baselines on…” 3 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) · 0 unverified report
Persona Switch: Mixing Distinct Perspectives in Decoding Time arXiv:2601.15708 LLaMA-3.1 (8B) Persona Switch 73.30 22 Jan 2026 Table 1, row “LLaMA-3.1 (8B) Persona Switch”Caption: “Table 1: Experimental results on five reasoning datasets. We report accuracy…” 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 report

Syntology 2 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
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
SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic... arXiv:2608.26550 27 Aug 2026 6 harvested: 5 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; 5 where Syntology's instrument failed) · 1 unverified refused by a rule: one configuration gave two values for one column
Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain... arXiv:2607.17266 19 Jul 2026 3 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) · 0 unverified placed
Matching Tasks to Objectives: Fine-Tuning and Prompt-Tuning Strategies for... arXiv:2606.24841 23 Jun 2026 9 harvested: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified refused by a rule: the table's column header does not name the leaderboard's metric
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
ExpWeaver: LLM Agents Learn from Experience via Latent RAG arXiv:2606.01041 31 May 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM Agents arXiv:2605.30712 29 May 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs arXiv:2605.22297 21 May 2026 10 harvested: 9 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; 5 where Syntology's instrument failed) · 1 unverified refused by a rule: the table's column header does not name the leaderboard's metric
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
Beyond Static Personas: Situational Personality Steering for Large Language Models arXiv:2604.13846 15 Apr 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: the row label the model quoted is not the row's label
Hear Both Sides: Efficient Multi-Agent Debate via Diversity-Aware Message Retention arXiv:2603.20640 21 Mar 2026 11 harvested: 8 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; 5 where Syntology's instrument failed) · 3 unverified refused by a rule: the model gave no value to check against the cell
How Far Ahead Do LLMs Plan? Uncovering the Latent Horizon in Chain-of-Thought Reasoning arXiv:2602.02103 2 Feb 2026 repository linked, no samples harvested refused by a rule: the table's column header does not name the leaderboard's metric
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
Persona Switch: Mixing Distinct Perspectives in Decoding Time arXiv:2601.15708 22 Jan 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 placed
Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs arXiv:2510.22139 25 Oct 2025 6 harvested: 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 refused by a rule: the table's column header does not name the leaderboard's metric
SwiReasoning: Switch-Thinking in Latent and Explicit for Pareto-Superior Reasoning LLMs arXiv:2510.05069 6 Oct 2025 6 harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified refused by a rule: the table does not name the leaderboard's dataset

Syntology 16 newer papers judged to report on this board: the papers counted above as having proposed a result (2 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 13 counted above as giving no cell that passed the extractor's own checks are the 13 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