Browse › Natural Language Processing › Common Sense Reasoning › WinoGrande
WinoGrande Benchmark (Common Sense Reasoning)
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
The chart needs JavaScript; the table below carries every value.
Direction inferred from the metric name, not from the archive: Accuracy (higher is better). Points are placed at the row's paper date; 76 of 77 rows carry one.
Results archive 2025-07-28
Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.
| Paper | Code | Ran Syntology | Report | |||||
|---|---|---|---|---|---|---|---|---|
| 1 | ST-MoE-32B 269B (fine-tuned) | 96.1 | – | Paper | Code | 2022 | 5 of 5 ran · 0 unverified | report |
| 2 | Unicorn 11B (fine-tuned) | 91.3 | – | Paper | Code | 2021 | 0 of 5 ran · 5 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 | 4 of 7 ran · 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 | 2 of 5 ran · 3 unverified | report |
| 8 | ExDeBERTa 567M | 87 | – | Paper | Code | 2022 | linked, not harvested | report |
| 9 | LLaMA-2 13B + MixLoRA | 86.3 | – | Paper | Code | 2024 | 6 of 11 ran · 5 unverified | report |
| 10 | LLaMA3 8B+MoSLoRA | 85.8 | – | Paper | Code | 2024 | 4 of 6 ran · 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 | 6 of 11 ran · 5 unverified | report |
| 13 | ST-MoE-L 4.1B (fine-tuned) | 81.7 | – | Paper | Code | 2022 | 5 of 5 ran · 0 unverified | report |
| 14 | GPT-3.5 (5-shot) | 81.6 | – | Paper | Code | 2023 | 2 of 5 ran · 3 unverified | report |
| 15 | PaLM 540B (0-shot) | 81.1 | – | Paper | Code | 2022 | 30 of 37 ran · 7 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 of 5 ran · 0 unverified | report |
| 21 | PaLM 62B (0-shot) | 77.0 | – | Paper | Code | 2022 | 30 of 37 ran · 7 unverified | report |
| 22 | PaLM-cont 62B (0-shot) | 77.0 | – | Paper | Code | 2022 | 30 of 37 ran · 7 unverified | report |
| 23 | LLaMA 65B (0-shot) | 77.0 | – | Paper | Code | 2023 | 26 of 58 ran · 32 unverified | report |
| 24 | LLaMA-2 7B + MixLoRA | 76.8 | – | Paper | Code | 2024 | 6 of 11 ran · 5 unverified | report |
| 25 | LLaMA 33B (0-shot) | 76.0 | – | Paper | Code | 2023 | 26 of 58 ran · 32 unverified | report |
| 26 | Mistral 7B (0-shot) | 75.3 | – | Paper | Code | 2023 | 9 of 11 ran · 2 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 of 11 ran · 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 of 5 ran · 0 unverified | 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 | 4 of 7 ran · 3 unverified | report |
| 33 | LLaMA 13B (0-shot) | 73.0 | – | Paper | Code | 2023 | 26 of 58 ran · 32 unverified | report |
| 34 | FLAN 137B (few-shot, k=16) | 72.8 | – | Paper | Code | 2021 | 0 of 1 ran · 1 unverified | report |
| 35 | G-DAUG-Combo + RoBERTa-Large | 71.4 | – | Paper | Code | 2020 | 2 of 4 ran · 2 unverified | report |
| 36 | FLAN 137B (0-shot) | 71.2 | – | Paper | Code | 2021 | 0 of 1 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 | 15 of 65 ran · 50 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 | 26 of 58 ran · 32 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 | 3 of 3 ran · 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 | 15 of 65 ran · 50 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 of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 28 rows have a graph line, from 15 distinct papers; 25 rows (13 papers) have at least one sample that ran. Counting each paper once: Syntology ran 119 of 234 samples; 115 unverified. Separately, 33 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. Read from the graph 2026-09-24. Per-sample status is on the paper page.
Since the archive: results placed by Syntology Syntology
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 rows above. Measured before publishing: the extractor was run on 883 held-out archive papers and processed 881 of them (the other 2 failed with an error before producing any output and are not part of this measurement); on those 881 papers, a blind reviewer judged 108 of 110 accepted entries correct (95% lower confidence bound 0.9361). Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.
| 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++” | 3 of 5 ran | 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; hover "Where in the paper" for the table's caption and each value's column header. Not part of the archive and not in the chart above. Drawn from 6,264 of 9,581 newer papers checked so far.
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