https://www.sota2.com/research/sota/chinese-language-understanding-on-c-eval2026-05-26T09:38:20.920Zhttps://www.sota2.com/research/sota/deepfake-detection-on-celeb-df-v2-test2026-04-24T08:19:47.160Zhttps://www.sota2.com/research/sota/code-generation-on-codecontests2026-05-18T06:40:30.665Zhttps://www.sota2.com/research/sota/few-shot-classification-on-modelnet40-test2026-02-26T05:51:54.113Zhttps://www.sota2.com/research/sota/symbolic-reasoning-on-last-letter-concatenation2026-05-14T08:44:09.266Zhttps://www.sota2.com/research/sota/referring-segmentation-on-refcoco-plus-val2026-07-08T08:04:40.288Zhttps://www.sota2.com/research/sota/image-classification-on-cifar10-long-tailed-test2026-02-26T05:29:36.834Zhttps://www.sota2.com/research/sota/music-genre-classification-on-gtzan2026-06-18T06:45:58.532Zhttps://www.sota2.com/research/sota/web-agent-tasks-on-mind2web-cross-task2026-06-09T07:50:54.498Zhttps://www.sota2.com/research/sota/commonsense-reasoning-on-hellaswag-val2026-06-23T11:18:37.489Zhttps://www.sota2.com/research/sota/camera-tracking-on-replica2026-06-30T07:52:48.654Zhttps://www.sota2.com/research/sota/video-super-resolution-on-spmcs2026-06-09T10:35:25.663Zhttps://www.sota2.com/research/sota/unconditional-image-generation-on-lsun-bedroom-256x2562026-03-23T11:38:34.771Zhttps://www.sota2.com/research/sota/dynamic-link-prediction-on-can-parl-inductive2026-06-04T12:38:35.899Zhttps://www.sota2.com/research/sota/traffic-forecasting-on-pems032026-06-12T06:59:53.346Zhttps://www.sota2.com/research/sota/general-reasoning-on-big-bench-hard2026-05-26T08:11:48.973Zhttps://www.sota2.com/research/sota/question-answering-on-csqa-test2026-05-15T08:05:50.445Zhttps://www.sota2.com/research/sota/irregularly-sampled-time-series-forecasting-on-ushcn-test2026-05-28T06:53:00.074Zhttps://www.sota2.com/research/sota/image-to-text-retrieval-on-mscoco-5k-test2026-04-21T07:53:27.028Zhttps://www.sota2.com/research/sota/hierarchical-text-classification-on-rcv1-v22026-04-20T08:10:47.026Zhttps://www.sota2.com/research/sota/video-captioning-on-msrvtt2026-03-25T14:40:10.481Zhttps://www.sota2.com/research/sota/code-generation-on-codecontests-test2026-05-27T09:50:47.618Zhttps://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-halfcheetah-v2-medium-replay2026-06-02T08:50:32.323Zhttps://www.sota2.com/research/sota/text-reconstruction-from-gradients-on-rotten-tomatoes2026-04-09T23:13:41.566Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-val-accuracy-and-efficiency2026-02-26T06:07:00.546Zhttps://www.sota2.com/research/sota/natural-language-inference-on-mnli-mismatched2026-02-26T05:29:53.021Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-10-lt-gamma-50-test2026-06-04T13:03:21.737Zhttps://www.sota2.com/research/sota/multiple-choice-question-answering-on-arc-easy-test2026-03-04T13:44:22.775Zhttps://www.sota2.com/research/sota/semantic-textual-similarity-on-english-sts-collection-sts12-16-sts-b-sick-r2026-02-26T05:35:53.872Zhttps://www.sota2.com/research/sota/temporal-grounding-on-charades-sta-test2026-05-21T10:42:04.719Zhttps://www.sota2.com/research/sota/vision-and-language-navigation-on-r2r-val-seen2026-03-31T07:50:21.598Zhttps://www.sota2.com/research/sota/objectgoal-navigation-on-mp3d-val2026-02-26T06:05:27.093Zhttps://www.sota2.com/research/sota/video-to-text-retrieval-on-msvd-test2026-04-24T07:00:48.477Zhttps://www.sota2.com/research/sota/image-dehazing-on-dense-haze2026-06-18T08:35:48.699Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-10-4000-labels2026-02-26T05:42:18.614Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-matched-frequency-v2-test2026-07-07T07:27:42.155Zhttps://www.sota2.com/research/sota/action-recognition-on-toyota-smarthome-tsh-cv12026-03-06T07:35:11.339Zhttps://www.sota2.com/research/sota/retrieval-on-hotpotqa2026-05-28T08:45:05.301Zhttps://www.sota2.com/research/sota/cardiac-segmentation-on-acdc2026-03-24T16:53:08.608Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-and-weights-remaining2026-02-26T05:29:57.987Zhttps://www.sota2.com/research/sota/commonsense-question-answering-on-cosmosqa2026-05-11T10:44:01.685Zhttps://www.sota2.com/research/sota/anomaly-detection-on-shanghaitech2026-02-26T05:26:19.619Zhttps://www.sota2.com/research/sota/node-classification-on-acm-test2026-07-07T08:16:05.536Zhttps://www.sota2.com/research/sota/polyp-segmentation-on-cvc-colondb-test2026-05-26T10:54:20.505Zhttps://www.sota2.com/research/sota/few-shot-classification-on-cub-200-2011-test2026-04-02T08:58:03.800Zhttps://www.sota2.com/research/sota/clustering-on-cifar-100-20-test2026-02-26T05:30:22.475Zhttps://www.sota2.com/research/sota/salient-object-detection-on-ecssd-1-000-images-test2026-05-26T09:26:42.499Zhttps://www.sota2.com/research/sota/action-recognition-on-kinetics-600-val2026-02-26T06:06:44.908Zhttps://www.sota2.com/research/sota/model-calibration-on-cifar-102026-04-10T00:04:45.731Zhttps://www.sota2.com/research/sota/image-classification-on-places205-val2026-02-26T06:07:12.261Zhttps://www.sota2.com/research/sota/named-entity-recognition-on-ner-test2026-02-26T05:43:15.680Zhttps://www.sota2.com/research/sota/generative-modeling-on-cifar-102026-06-30T09:48:38.281Zhttps://www.sota2.com/research/sota/object-localization-on-cub-200-2011-test2026-02-26T06:07:20.148Zhttps://www.sota2.com/research/sota/cuboid-layout-estimation-on-panocontext-test2026-02-26T05:21:15.087Zhttps://www.sota2.com/research/sota/video-generation-on-ucf1012026-03-11T09:21:41.527Zhttps://www.sota2.com/research/sota/person-re-identification-on-market-1501-single-query-test2026-02-26T06:00:59.119Zhttps://www.sota2.com/research/sota/saliency-detection-on-njud-test2026-02-26T05:48:56.999Zhttps://www.sota2.com/research/sota/human-part-parsing-on-pascal-person-part-test2026-02-26T06:10:28.364Zhttps://www.sota2.com/research/sota/molecular-generation-on-zinc250k2026-02-26T06:07:53.555Zhttps://www.sota2.com/research/sota/speech-separation-on-libri2mix-test2026-07-03T06:48:30.308Zhttps://www.sota2.com/research/sota/keyword-spotting-on-google-speech-commands-v1-test2026-02-26T05:29:01.621Zhttps://www.sota2.com/research/sota/offline-reinforcement-learning-on-hopper-medium2026-05-29T08:11:55.444Zhttps://www.sota2.com/research/sota/question-answering-on-boolq-test2026-07-08T07:38:22.786Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-ood2026-03-31T10:27:54.038Zhttps://www.sota2.com/research/sota/anomaly-localization-on-visa-test2026-06-15T07:52:53.628Zhttps://www.sota2.com/research/sota/anomaly-classification-on-resc2026-02-26T05:25:19.485Zhttps://www.sota2.com/research/sota/imputation-on-powerplant-mar2026-07-07T09:04:29.764Zhttps://www.sota2.com/research/sota/accuracy-on-winogrande-common-sense-reasoning2026-07-07T11:00:54.618Zhttps://www.sota2.com/research/sota/face-verification-on-lfw-auroc-tpr-and-pe-gap-metrics2026-06-04T12:09:20.030Zhttps://www.sota2.com/research/sota/accuracy-on-arc-c-question-answering2026-07-03T06:16:42.580Zhttps://www.sota2.com/research/sota/counterfactual-generation-on-taxi15002026-05-13T09:14:06.995Zhttps://www.sota2.com/research/sota/video-reasoning-on-videomathqa2026-06-11T09:09:19.282Zhttps://www.sota2.com/research/sota/multiple-choice-question-answering-on-piqa2026-06-29T06:54:59.683Zhttps://www.sota2.com/research/sota/interactive-decision-making-on-alfworld-unseen2026-07-07T10:10:31.090Zhttps://www.sota2.com/research/sota/question-answering-on-newsqa-f1-em2026-06-12T07:24:43.260Zhttps://www.sota2.com/research/sota/general-knowledge-on-mmlu-pro-accuracy2026-07-07T10:25:37.801Zhttps://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-diamond-pass-at-1-token-count2026-06-02T07:45:43.828Zhttps://www.sota2.com/research/sota/multimodal-evaluation-on-mme-total2026-05-19T07:41:10.575Zhttps://www.sota2.com/research/sota/few-shot-3d-semantic-segmentation-on-s3dis-s12026-07-01T07:49:19.190Zhttps://www.sota2.com/research/sota/road-extraction-on-massachusetts2026-04-20T07:10:15.159Zhttps://www.sota2.com/research/sota/machine-unlearning-on-tofu-1-0-forget102026-06-29T06:48:54.466Zhttps://www.sota2.com/research/sota/depth-estimation-on-bonn2026-06-23T08:29:20.639Zhttps://www.sota2.com/research/sota/driver-dnf-prediction-on-rel-f12026-05-25T08:08:59.461Zhttps://www.sota2.com/research/sota/dialogue-on-mt-bench2026-07-01T08:24:37.174Zhttps://www.sota2.com/research/sota/reward-modeling-on-rewardbench-v2-test2026-04-28T07:17:16.335Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-minerva-accuracy-percent2026-04-10T09:48:24.009Zhttps://www.sota2.com/research/sota/spatial-reasoning-granular-metrics-on-mmsi-bench2026-06-19T08:50:37.481Zhttps://www.sota2.com/research/sota/multi-hop-qa-on-2wikimultihopqa2026-05-13T09:00:49.739Zhttps://www.sota2.com/research/sota/language-modeling-on-lm1b-val2026-05-26T13:44:01.207Zhttps://www.sota2.com/research/sota/multi-task-knowledge-and-reasoning-on-mmlu-pro2026-06-11T09:20:57.252Zhttps://www.sota2.com/research/sota/general-image-understanding-on-mmstar2026-07-08T07:00:51.824Zhttps://www.sota2.com/research/sota/image-classification-on-vision-datasets-14-tasks-1-0-test2026-03-04T08:08:05.875Zhttps://www.sota2.com/research/sota/load-forecasting-on-gefcom2026-03-04T15:56:01.493Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-pass-at-12026-03-24T14:31:14.320Zhttps://www.sota2.com/research/sota/visual-question-answering-on-infoseek-unseen-q-unseen-e-metrics2026-07-09T07:30:15.681Zhttps://www.sota2.com/research/sota/graph-anomaly-detection-on-citeseer2026-06-30T09:38:03.897Zhttps://www.sota2.com/research/sota/video-understanding-on-videomme-subtitle-accuracy2026-06-30T10:06:47.208Zhttps://www.sota2.com/research/sota/surface-normal-estimation-on-ibims-12026-07-08T08:10:12.515Zhttps://www.sota2.com/research/sota/counting-on-tallyqa2026-06-02T12:10:02.171Zhttps://www.sota2.com/research/sota/fact-based-visual-question-answering-on-fvqa2026-05-12T16:52:01.852Zhttps://www.sota2.com/research/sota/video-understanding-on-videommmu2026-07-07T07:50:53.517Zhttps://www.sota2.com/research/sota/faithfulness-evaluation-on-wikibio2026-04-16T07:13:06.266Zhttps://www.sota2.com/research/sota/faithfulness-evaluation-on-tellmewhy2026-04-16T07:13:06.147Zhttps://www.sota2.com/research/sota/language-understanding-on-ceval2026-06-05T08:27:49.261Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-college2026-04-20T06:31:22.567Zhttps://www.sota2.com/research/sota/gui-grounding-on-screenspot-pro-test2026-06-15T07:56:57.204Zhttps://www.sota2.com/research/sota/composed-image-retrieval-on-fashioniq-dress2026-07-03T08:04:39.163Zhttps://www.sota2.com/research/sota/gaze-target-estimation-on-gazefollow2026-07-07T11:15:02.218Zhttps://www.sota2.com/research/sota/video-reconstruction-on-ucf-1012026-06-17T07:12:46.211Zhttps://www.sota2.com/research/sota/semantic-occupancy-prediction-on-semantickitti-test2026-07-01T08:22:35.953Zhttps://www.sota2.com/research/sota/semantic-segmentation-on-a-1502026-04-28T10:31:57.058Zhttps://www.sota2.com/research/sota/speech-reconstruction-on-libritts-clean-test2026-07-07T11:43:46.376Zhttps://www.sota2.com/research/sota/visual-reasoning-on-mmvp2026-07-07T07:48:52.017Zhttps://www.sota2.com/research/sota/open-vocabulary-semantic-segmentation-on-cityscapes-without-background2026-03-25T14:43:16.209Zhttps://www.sota2.com/research/sota/open-vocabulary-semantic-segmentation-on-pascal-context-59-without-background2026-03-25T14:43:16.030Zhttps://www.sota2.com/research/sota/question-answering-on-arc-hellaswag-and-mmlu-zero-shot-test2026-02-26T05:23:38.199Zhttps://www.sota2.com/research/sota/classification-on-rsna-pneumonia2026-06-30T06:39:46.424Zhttps://www.sota2.com/research/sota/image-super-resolution-on-b100-x2-test2026-05-19T10:45:11.843Zhttps://www.sota2.com/research/sota/question-answering-on-medqa-test2026-04-29T07:48:48.860Zhttps://www.sota2.com/research/sota/multimodal-evaluation-on-mm-bench2026-06-23T10:45:12.589Zhttps://www.sota2.com/research/sota/symbolic-reasoning-on-letter2026-03-24T15:30:20.945Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-icbhi-dataset-official-60-40-percent-split2026-06-11T10:47:09.385Zhttps://www.sota2.com/research/sota/camouflaged-object-detection-on-chameleon-test2026-04-21T08:20:12.419Zhttps://www.sota2.com/research/sota/image-retrieval-on-gld-v2-test2026-03-10T07:15:09.359Zhttps://www.sota2.com/research/sota/image-retrieval-on-roxford2026-04-02T08:42:49.571Zhttps://www.sota2.com/research/sota/semantic-segmentation-on-coco-stuff-272026-05-28T10:38:55.163Zhttps://www.sota2.com/research/sota/visual-question-answering-on-vqa-rad2026-06-25T08:15:04.582Zhttps://www.sota2.com/research/sota/univariate-time-series-forecasting-on-ettm12026-06-08T07:19:22.251Zhttps://www.sota2.com/research/sota/image-classification-on-cifar100-idn-test2026-02-26T05:28:29.075Zhttps://www.sota2.com/research/sota/image-classification-on-cifar10-idn-test2026-02-26T05:28:28.895Zhttps://www.sota2.com/research/sota/summarization-on-cnn-daily-mail2026-02-27T06:22:16.557Zhttps://www.sota2.com/research/sota/anomaly-detection-on-mvtec-ad-1-0-test2026-03-25T13:47:04.690Zhttps://www.sota2.com/research/sota/anomaly-segmentation-on-fishyscapes-static-val2026-07-07T10:17:04.223Zhttps://www.sota2.com/research/sota/object-detection-on-dronevehicle2026-07-07T11:34:41.564Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-real-test2026-02-26T06:07:00.526Zhttps://www.sota2.com/research/sota/image-dehazing-on-nh-haze2026-07-03T07:11:13.223Zhttps://www.sota2.com/research/sota/wsi-classification-on-tcga-lung-cancer-dataset-test2026-02-26T05:30:23.465Zhttps://www.sota2.com/research/sota/class-incremental-learning-on-cifar100-b50-test2026-02-26T05:35:14.861Zhttps://www.sota2.com/research/sota/person-re-identification-on-dukemtmc-reid-to-market15012026-02-26T06:09:40.852Zhttps://www.sota2.com/research/sota/hateful-meme-detection-on-hateful-memes-test2026-05-08T08:03:17.716Zhttps://www.sota2.com/research/sota/image-classification-on-digits-five2026-05-06T07:31:50.111Zhttps://www.sota2.com/research/sota/object-detection-on-foggy-cityscapes-val2026-02-26T06:09:32.416Zhttps://www.sota2.com/research/sota/passage-retrieval-on-triviaqa-test2026-02-26T06:07:21.693Zhttps://www.sota2.com/research/sota/depth-completion-on-kitti-test2026-02-26T06:00:09.832Zhttps://www.sota2.com/research/sota/sentence-retrieval-on-mscoco-5k-test2026-02-26T05:59:25.218Zhttps://www.sota2.com/research/sota/out-of-distribution-detection-on-cifar-100-id-vs-lsun-ood-test2026-02-26T05:25:54.990Zhttps://www.sota2.com/research/sota/aspect-level-sentiment-classification-on-semeval-restaurant-2014-test2026-02-27T09:17:13.827Zhttps://www.sota2.com/research/sota/question-answering-on-webquestions-webqs2026-02-26T05:32:49.289Zhttps://www.sota2.com/research/sota/scene-text-recognition-on-ic03-accuracy2026-02-27T07:11:56.313Zhttps://www.sota2.com/research/sota/5-way-image-classification-on-miniimagenet2026-02-26T05:54:15.972Zhttps://www.sota2.com/research/sota/person-re-identification-on-mars2026-02-26T06:00:59.140Zhttps://www.sota2.com/research/sota/multi-turn-response-selection-on-douban-conversation-corpus2026-02-26T05:49:35.389Zhttps://www.sota2.com/research/sota/dependency-parsing-on-wsj-test2026-02-26T06:07:48.369Zhttps://www.sota2.com/research/sota/image-classification-on-voc-2007-test2026-02-26T06:09:33.990Zhttps://www.sota2.com/research/sota/binary-segmentation-on-kvasir-seg-test2026-02-26T05:40:28.522Zhttps://www.sota2.com/research/sota/survival-prediction-on-tcga-brca-test2026-05-21T11:59:26.421Zhttps://www.sota2.com/research/sota/anomaly-detection-on-resc2026-06-30T10:13:20.144Zhttps://www.sota2.com/research/sota/table-question-answering-on-wikitq-dev2026-06-08T06:53:08.140Zhttps://www.sota2.com/research/sota/semantic-segmentation-on-fmb2026-06-16T09:18:29.416Zhttps://www.sota2.com/research/sota/oriented-object-detection-on-dior-r2026-05-06T07:19:13.250Zhttps://www.sota2.com/research/sota/zero-shot-accuracy-on-arc-easy2026-05-26T08:31:34.709Zhttps://www.sota2.com/research/sota/text-to-image-generation-on-wise2026-05-08T08:35:48.041Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-theoremqa2026-06-30T08:23:01.696Zhttps://www.sota2.com/research/sota/planning-on-rotating-ddi2026-07-07T11:54:21.545Zhttps://www.sota2.com/research/sota/imputation-on-facial-expression-dataset-mnar2026-07-07T09:04:30.059Zhttps://www.sota2.com/research/sota/data-imputation-on-powerplant-mar-test2026-07-07T09:04:29.855Zhttps://www.sota2.com/research/sota/traveling-salesman-problem-on-tsplib-all-instances-n-2502026-06-30T08:55:44.654Zhttps://www.sota2.com/research/sota/capacitated-vehicle-routing-problem-on-cvrplib2026-06-30T08:55:44.630Zhttps://www.sota2.com/research/sota/binary-classification-on-65-binary-imbalanced-datasets2026-06-29T06:11:59.888Zhttps://www.sota2.com/research/sota/vision-language-alignment-on-imagenet-100-accuracy2026-06-23T10:19:27.144Zhttps://www.sota2.com/research/sota/vision-language-alignment-on-cifar-1002026-06-23T10:19:27.085Zhttps://www.sota2.com/research/sota/classification-on-controlled-distribution-shift2026-06-23T10:02:47.317Zhttps://www.sota2.com/research/sota/classification-tasks2026-06-23T10:02:47.258Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-10-standard-test-clean-accuracy2026-06-25T08:21:38.952Zhttps://www.sota2.com/research/sota/secure-code-generation-on-python-test2026-06-16T09:42:18.643Zhttps://www.sota2.com/research/sota/secure-code-generation-on-java-evaluation2026-06-16T09:42:18.530Zhttps://www.sota2.com/research/sota/secure-code-generation-on-c-plus-plus-test2026-06-16T09:42:18.455Zhttps://www.sota2.com/research/sota/question-answering-on-naturalqa-accuracy-rejection-rate-speedup2026-06-11T11:16:53.587Zhttps://www.sota2.com/research/sota/question-answering-on-webquestions-accuracy-rejection-rate-speedup2026-06-11T11:16:53.544Zhttps://www.sota2.com/research/sota/image-classification-on-tinyimagenet-second-session-transition2026-06-09T09:23:52.492Zhttps://www.sota2.com/research/sota/diagnosis-prediction-on-held-out-test2026-06-09T08:57:16.732Zhttps://www.sota2.com/research/sota/face-verification-on-rfw-calibration-and-group-fairness2026-06-04T12:09:20.178Zhttps://www.sota2.com/research/sota/face-verification-on-lfw-auroc-and-calibration2026-06-04T12:09:19.868Zhttps://www.sota2.com/research/sota/calibration-on-lfw2026-06-04T12:09:19.737Zhttps://www.sota2.com/research/sota/calibration-on-bfw2026-06-04T12:09:19.703Zhttps://www.sota2.com/research/sota/calibration-on-rfw2026-06-04T12:09:19.660Zhttps://www.sota2.com/research/sota/language-modeling-on-language-modeling-scaling-study-dataset2026-06-04T06:48:07.343Zhttps://www.sota2.com/research/sota/multiple-choice-question-answering-on-average-obqa-arc-c-arc-e-sciq-siqa2026-06-02T09:49:05.335Zhttps://www.sota2.com/research/sota/object-detection-on-deeppcb-1-0-test2026-06-02T09:28:55.220Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-1k-standard-accuracy2026-07-07T09:18:07.530Zhttps://www.sota2.com/research/sota/image-classification-on-tiny-imagenet-standard-and-robust-accuracy-via-autoattack2026-06-29T07:01:35.496Zhttps://www.sota2.com/research/sota/reasoning-on-bbh-mmlu-arc-c-and-thmqa-test2026-05-27T07:51:21.270Zhttps://www.sota2.com/research/sota/multi-label-recognition-on-nus-wide-map2026-06-12T07:27:46.572Zhttps://www.sota2.com/research/sota/speculative-decoding-on-livecodebench2026-06-02T08:14:34.731Zhttps://www.sota2.com/research/sota/class-erasure-on-imagenette2026-05-18T08:10:05.744Zhttps://www.sota2.com/research/sota/drc-script-synthesis-on-rule2drc-1-000-problems2026-05-18T07:58:01.671Zhttps://www.sota2.com/research/sota/drc-script-synthesis-on-rule2drc-test2026-05-18T07:58:01.635Zhttps://www.sota2.com/research/sota/commonsense-reasoning-on-hellaswag-hs-accuracy2026-06-02T13:51:44.101Zhttps://www.sota2.com/research/sota/general-capability-on-aggregate-gpqa-d-gsm8k-humaneval-math-500-mbpp-mmlu-pro2026-05-12T12:34:32.238Zhttps://www.sota2.com/research/sota/commonsense-reasoning-on-hellaswag-accuracy-acc_norm2026-06-29T07:20:19.321Z