https://www.sota2.com/research/sota/longitudinal-classification-on-talklife-80-202026-04-21T07:15:33.231Zhttps://www.sota2.com/research/sota/longitudinal-classification-on-lrs-80-202026-04-21T07:15:33.200Zhttps://www.sota2.com/research/sota/longitudinal-classification-on-annomi-80-202026-04-21T07:15:33.171Zhttps://www.sota2.com/research/sota/multi-task-reasoning-on-average-out-of-domain2026-04-21T07:07:27.966Zhttps://www.sota2.com/research/sota/code-reasoning-on-supergpqa-code-sgpqa-1k-accuracy-pass-at-12026-04-21T07:07:27.933Zhttps://www.sota2.com/research/sota/code-reasoning-on-r-bench-t-code2026-04-21T07:07:27.904Zhttps://www.sota2.com/research/sota/code-reasoning-on-ojbench2026-04-21T07:07:27.869Zhttps://www.sota2.com/research/sota/math-reasoning-on-supergpqa-sgpqa-1k-math2026-04-21T07:07:27.800Zhttps://www.sota2.com/research/sota/math-reasoning-on-r-bench-t-math2026-04-21T07:07:27.761Zhttps://www.sota2.com/research/sota/math-reasoning-on-olympiad-accuracy-pass-at-12026-04-21T07:07:27.729Zhttps://www.sota2.com/research/sota/fuel-property-prediction-on-fuel-ron-10-fold-cross-validation2026-04-20T08:29:57.121Zhttps://www.sota2.com/research/sota/medical-report-generation-on-ultrasound-average2026-04-20T08:21:22.040Zhttps://www.sota2.com/research/sota/medical-report-generation-on-ultrasound-kidney2026-04-20T08:21:21.913Zhttps://www.sota2.com/research/sota/medical-report-generation-on-ultrasound-gynecology2026-04-20T08:21:21.851Zhttps://www.sota2.com/research/sota/medical-report-generation-on-ultrasound-breast2026-04-20T08:21:21.815Zhttps://www.sota2.com/research/sota/hyperspectral-image-classification-on-hsi-benchmark-test2026-04-20T07:54:08.288Zhttps://www.sota2.com/research/sota/pathological-image-classification-on-crc2026-04-20T07:24:53.720Zhttps://www.sota2.com/research/sota/pathological-image-classification-on-mhist2026-04-20T07:24:53.694Zhttps://www.sota2.com/research/sota/pathological-image-classification-on-cam162026-04-20T07:24:53.431Zhttps://www.sota2.com/research/sota/classification-on-smoking-dataset2026-04-20T07:13:58.535Zhttps://www.sota2.com/research/sota/jailbreak-defense-on-jailbreak-attack-suite2026-04-20T06:54:05.127Zhttps://www.sota2.com/research/sota/jailbreak-defense-on-jailbreak-defense-dataset2026-05-26T10:40:41.413Zhttps://www.sota2.com/research/sota/web-api-recommendation-on-programmableweb-test2026-04-20T06:43:48.861Zhttps://www.sota2.com/research/sota/interactive-decision-making-on-webshop-real-wm-w2r-cr-metrics2026-04-16T08:13:26.365Zhttps://www.sota2.com/research/sota/interactive-decision-making-on-textworld2026-04-16T08:13:26.329Zhttps://www.sota2.com/research/sota/session-based-recommendation-on-book-h-at-k-n-at-k2026-04-16T07:03:06.038Zhttps://www.sota2.com/research/sota/session-based-recommendation-on-yelp-k-5-10-202026-04-16T07:03:06.005Zhttps://www.sota2.com/research/sota/session-based-recommendation-on-beauty2026-04-16T07:03:05.968Zhttps://www.sota2.com/research/sota/wrench-forecasting-on-rh20t-test2026-04-15T10:03:49.811Zhttps://www.sota2.com/research/sota/membership-inference-attack-on-challenge-set-third-party-evaluation2026-04-15T09:42:46.983Zhttps://www.sota2.com/research/sota/document-ranking-on-trec-robust-novelty-metrics2026-04-15T09:02:36.545Zhttps://www.sota2.com/research/sota/document-ranking-on-ms-marco-document2026-04-15T09:02:36.511Zhttps://www.sota2.com/research/sota/document-ranking-on-ms-marco-passage2026-04-15T09:02:36.472Zhttps://www.sota2.com/research/sota/continual-unlearning-on-cifar-100-resnet-20-test2026-04-15T09:02:35.555Zhttps://www.sota2.com/research/sota/knowledge-base-question-answering-on-webquestion2026-04-15T08:54:08.269Zhttps://www.sota2.com/research/sota/image-text-retrieval-on-coco-1-0-test2026-04-15T08:42:31.475Zhttps://www.sota2.com/research/sota/image-classification-on-vtab-plus-1-0-test2026-04-15T08:42:31.443Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-1k-1-0-test-training-efficiency-and-accuracy2026-04-15T08:42:31.404Zhttps://www.sota2.com/research/sota/problem-solving-on-list-function-test2026-04-15T08:42:31.326Zhttps://www.sota2.com/research/sota/multi-turn-dialogue-on-sharegpt-jddc-and-meddg-aggregated2026-04-15T08:42:31.295Zhttps://www.sota2.com/research/sota/multi-turn-dialogue-on-meddg2026-04-15T08:42:31.265Zhttps://www.sota2.com/research/sota/multi-turn-dialogue-on-jddc2026-04-15T08:42:31.235Zhttps://www.sota2.com/research/sota/multi-turn-dialogue-on-sharegpt2026-04-15T08:42:31.196Zhttps://www.sota2.com/research/sota/spreadsheet-understanding-and-manipulation-on-spreadsheetbench-soft-restriction2026-04-15T08:16:15.884Zhttps://www.sota2.com/research/sota/model-accuracy-on-model-utility-evaluation-set2026-04-15T08:12:23.524Zhttps://www.sota2.com/research/sota/text-to-image-generation-on-oneig-bench-en2026-04-15T08:02:21.618Zhttps://www.sota2.com/research/sota/least-squares-optimization-on-least-squares-optimization-test2026-04-15T07:22:11.061Zhttps://www.sota2.com/research/sota/consensus-optimization-test2026-04-15T07:22:11.028Zhttps://www.sota2.com/research/sota/long-horizon-agentic-task-on-browsecomp-plus2026-04-14T12:42:04.720Zhttps://www.sota2.com/research/sota/long-horizon-agentic-task-on-browsecomp2026-04-14T12:42:04.695Zhttps://www.sota2.com/research/sota/long-form-generation-on-1d-difftask-most-ood2026-04-14T12:32:00.393Zhttps://www.sota2.com/research/sota/long-form-generation-on-difftask-ood2026-04-14T12:32:00.362Zhttps://www.sota2.com/research/sota/long-form-generation-on-long-form-generation-datasets-1d-sametask-ood2026-04-14T12:32:00.332Zhttps://www.sota2.com/research/sota/long-form-generation-on-long-form-generation-datasets-loo-near-ood2026-04-14T12:32:00.306Zhttps://www.sota2.com/research/sota/short-form-generation-on-short-form-generation-datasets-1d-difftask-most-ood2026-04-14T12:32:00.280Zhttps://www.sota2.com/research/sota/short-form-generation-on-difftask-ood2026-04-14T12:32:00.252Zhttps://www.sota2.com/research/sota/short-form-generation-on-short-form-generation-1d-sametask-ood2026-04-14T12:32:00.219Zhttps://www.sota2.com/research/sota/short-form-generation-on-short-form-generation-datasets-loo-near-ood2026-04-14T12:32:00.190Zhttps://www.sota2.com/research/sota/text-classification-on-sst-2-accuracy-and-p-value2026-04-14T11:44:25.444Zhttps://www.sota2.com/research/sota/open-set-object-detection-on-cityscapes-to-bdd100k-5-novel-categories2026-04-14T11:28:09.730Zhttps://www.sota2.com/research/sota/open-set-object-detection-on-cityscapes-to-bdd100k-4-novel-categories2026-04-14T11:28:09.701Zhttps://www.sota2.com/research/sota/open-set-object-detection-on-cityscapes-to-bdd100k-3-novel-categories2026-04-14T11:28:09.672Zhttps://www.sota2.com/research/sota/regression-on-biomassters-all-labels2026-04-14T10:31:31.594Zhttps://www.sota2.com/research/sota/regression-on-biomassters-30-percent-labels2026-04-14T10:31:31.561Zhttps://www.sota2.com/research/sota/regression-on-biomassters-1-percent-labels2026-04-14T10:31:31.532Zhttps://www.sota2.com/research/sota/semantic-segmentation-on-pastis-r-all-labels2026-04-14T10:31:31.309Zhttps://www.sota2.com/research/sota/semantic-segmentation-on-pastis-r-30-percent-labels2026-04-14T10:31:31.283Zhttps://www.sota2.com/research/sota/semantic-segmentation-on-pastis-r-1-percent-labels2026-04-14T10:31:31.253Zhttps://www.sota2.com/research/sota/federated-multiple-client-unlearning-on-cifar-100-non-iid-10-clients2026-04-14T10:21:25.647Zhttps://www.sota2.com/research/sota/modeling-attack-on-simulated-crps2026-04-14T10:18:54.333Zhttps://www.sota2.com/research/sota/image-denoising-on-icvl2026-04-14T10:17:23.243Zhttps://www.sota2.com/research/sota/vascular-image-segmentation-on-fbs-dsca2026-04-14T10:11:22.382Zhttps://www.sota2.com/research/sota/vascular-image-segmentation-on-fbs-dias2026-04-14T10:11:22.352Zhttps://www.sota2.com/research/sota/vascular-image-segmentation-on-fts-oct2026-04-14T10:11:22.326Zhttps://www.sota2.com/research/sota/vascular-image-segmentation-on-fvs-orvs2026-04-14T10:11:22.272Zhttps://www.sota2.com/research/sota/vascular-image-segmentation-on-fvs-hrf2026-04-14T10:11:22.249Zhttps://www.sota2.com/research/sota/vascular-image-segmentation-on-fvs-drive2026-04-14T10:11:22.222Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-avg-at-32-pass-at-322026-05-12T07:41:51.773Zhttps://www.sota2.com/research/sota/visual-perception-on-hallusionbench2026-06-04T11:56:14.209Zhttps://www.sota2.com/research/sota/question-answering-on-average-tvqa-sciq-nq-open-test2026-04-14T08:50:59.092Zhttps://www.sota2.com/research/sota/question-answering-on-sciq-in-domain-test2026-04-14T08:50:59.027Zhttps://www.sota2.com/research/sota/visual-place-recognition-on-hk_flood2026-04-14T08:40:56.046Zhttps://www.sota2.com/research/sota/visual-place-recognition-on-sf_flood2026-04-14T08:40:56.021Zhttps://www.sota2.com/research/sota/image-classification-on-office-home-v1-target-set2026-04-14T07:40:41.209Zhttps://www.sota2.com/research/sota/virtual-staining-on-hemit-13-full-dataset2026-04-14T07:00:33.445Zhttps://www.sota2.com/research/sota/dec-pomdp-planning-on-mars-rovers2026-04-13T10:11:41.940Zhttps://www.sota2.com/research/sota/dec-pomdp-planning-on-dec-tiger2026-04-13T10:11:41.833Zhttps://www.sota2.com/research/sota/machine-unlearning-on-cifar-10-30-percent-random-data-forgetting2026-04-14T09:50:41.265Zhttps://www.sota2.com/research/sota/video-question-answering-on-longvideobench-medium2026-04-13T09:40:14.669Zhttps://www.sota2.com/research/sota/uav-image-restoration-on-mdur-zero-shot-settings2026-04-13T09:30:11.670Zhttps://www.sota2.com/research/sota/uav-image-restoration-on-mdur-seen-settings2026-04-13T09:30:11.640Zhttps://www.sota2.com/research/sota/multi-view-classification-on-pie-accuracy2026-05-26T08:34:36.673Zhttps://www.sota2.com/research/sota/image-manipulation-localization-on-imd20-f1-score2026-04-13T09:00:31.529Zhttps://www.sota2.com/research/sota/linguistic-steganography-on-llm-steganography-evaluation-dataset2026-04-13T08:50:03.296Zhttps://www.sota2.com/research/sota/partial-multi-label-learning-on-image-ranking-loss2026-04-13T09:33:21.934Zhttps://www.sota2.com/research/sota/multimodal-reasoning-average-on-combined-m3-bench-plus-video-mme-long2026-04-13T08:31:56.157Zhttps://www.sota2.com/research/sota/long-form-video-multimodal-evaluation-on-video-mme-long2026-04-13T08:31:56.131Zhttps://www.sota2.com/research/sota/multimodal-reasoning-on-m3-bench-web2026-04-13T08:31:56.098Zhttps://www.sota2.com/research/sota/multimodal-reasoning-on-m3-bench-robot2026-04-13T08:31:56.062Zhttps://www.sota2.com/research/sota/table-question-answering-on-sstqa-test2026-04-13T08:31:25.701Zhttps://www.sota2.com/research/sota/class-agnostic-3d-instance-segmentation-on-scannet2002026-06-15T07:38:15.295Zhttps://www.sota2.com/research/sota/uncertainty-estimation-on-obqa2026-04-13T07:49:40.951Zhttps://www.sota2.com/research/sota/uncertainty-estimation-on-race-llama-3-1-8b-and-gemma-2-9b-backbones-test2026-04-13T07:49:40.891Zhttps://www.sota2.com/research/sota/state-variable-inference-on-chua-s-circuit-system2026-04-13T07:40:29.982Zhttps://www.sota2.com/research/sota/image-manipulation-localization-on-autosplice2026-05-28T08:18:52.475Zhttps://www.sota2.com/research/sota/image-manipulation-localization-on-cocoglide2026-05-28T08:18:52.439Zhttps://www.sota2.com/research/sota/video-temporal-grounding-on-charades-sta-r-at-1-metrics2026-05-06T07:54:34.127Zhttps://www.sota2.com/research/sota/prompt-injection-defense-on-sep2026-05-28T10:05:02.500Zhttps://www.sota2.com/research/sota/prompt-injection-defense-on-opi-open-prompt-injection2026-05-28T10:05:02.464Zhttps://www.sota2.com/research/sota/hyperspectral-image-denoising-on-washington-dc-mall-hsi-gaussian-plus-stripe-noise2026-04-10T09:25:06.945Zhttps://www.sota2.com/research/sota/hsi-denoising-on-salinas-hsi2026-04-10T09:25:06.886Zhttps://www.sota2.com/research/sota/ood-detection-on-gastrovision2026-04-10T09:21:35.263Zhttps://www.sota2.com/research/sota/deepfake-detection-on-protocol-2-hybrid-fr-fs-efs-v1-test2026-04-10T09:08:29.125Zhttps://www.sota2.com/research/sota/deepfake-detection-on-protocol-1-ff-plus-plus-dfdcp-dfd-cdf2-v1-test2026-04-10T09:08:29.084Zhttps://www.sota2.com/research/sota/transfer-entropy-estimation-on-70-dimensional-linear-stacking-linear-gaussian-system-y-x-t-100002026-04-10T08:44:42.261Zhttps://www.sota2.com/research/sota/transfer-entropy-estimation-on-70-dimensional-linear-stacking-linear-gaussian-system-x-y-t-100002026-04-10T08:44:42.234Zhttps://www.sota2.com/research/sota/classification-on-heart-full-performance-metrics2026-05-26T10:46:15.009Zhttps://www.sota2.com/research/sota/time-series-generation-on-metropt32026-04-10T08:39:04.059Zhttps://www.sota2.com/research/sota/time-series-generation-on-sine2026-04-10T08:39:04.005Zhttps://www.sota2.com/research/sota/time-series-generation-on-ett2026-04-10T08:39:03.959Zhttps://www.sota2.com/research/sota/time-series-generation-on-electric-motor-em2026-04-10T08:39:03.930Zhttps://www.sota2.com/research/sota/synthetic-time-series-generation-on-metropt32026-04-10T08:38:38.221Zhttps://www.sota2.com/research/sota/synthetic-time-series-generation-on-sine2026-04-10T08:38:38.194Zhttps://www.sota2.com/research/sota/synthetic-time-series-generation-on-ett2026-04-10T08:38:38.164Zhttps://www.sota2.com/research/sota/synthetic-time-series-generation-on-ecg2026-04-10T08:38:38.125Zhttps://www.sota2.com/research/sota/synthetic-time-series-generation-on-electric-motor2026-04-10T08:38:38.094Zhttps://www.sota2.com/research/sota/membership-inference-attack-on-image-autoregressive-iar-models2026-05-27T09:51:48.141Zhttps://www.sota2.com/research/sota/gui-element-injection-attack-success-on-screenspot-pro-885-sample-split2026-04-10T08:13:47.221Zhttps://www.sota2.com/research/sota/self-supervised-monocular-depth-estimation-on-kitti-eigen2026-04-10T07:38:48.100Zhttps://www.sota2.com/research/sota/recommendation-on-modcloth-test2026-04-10T07:28:45.591Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-and-aime242026-04-10T07:10:19.076Zhttps://www.sota2.com/research/sota/long-context-understanding-on-ruler-8k-to-256k-contexts2026-04-10T07:10:19.039Zhttps://www.sota2.com/research/sota/long-context-multi-task-evaluation-on-longbench-e2026-04-10T07:10:19.005Zhttps://www.sota2.com/research/sota/free-form-description-evaluation-on-eventhallusion2026-04-10T06:58:33.942Zhttps://www.sota2.com/research/sota/classification-on-asia2026-04-10T06:48:30.746Zhttps://www.sota2.com/research/sota/multimodal-to-text-retrieval-on-mm-bright2026-04-10T00:59:53.655Zhttps://www.sota2.com/research/sota/vision-centric-reasoning-on-v-bench-overall2026-04-10T00:38:20.254Zhttps://www.sota2.com/research/sota/question-answering-on-sports-understanding2026-04-10T00:28:16.439Zhttps://www.sota2.com/research/sota/question-answering-on-multiarith2026-04-10T00:28:16.399Zhttps://www.sota2.com/research/sota/free-question-answering-on-auto-categorization-context-free2026-04-10T00:28:16.370Zhttps://www.sota2.com/research/sota/free-question-answering-on-barqa-contextual2026-04-10T00:28:16.341Zhttps://www.sota2.com/research/sota/free-question-answering-on-squad-contextual-v1-12026-04-10T00:28:16.304Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-100n-resnet-18-test2026-04-09T21:07:53.866Zhttps://www.sota2.com/research/sota/video-based-dialogue-evaluation-on-video-chatgpt2026-04-21T08:31:20.902Zhttps://www.sota2.com/research/sota/temporal-reasoning-date-on-synthetic-temporal-dataset-10-fold-cv2026-04-08T09:10:46.151Zhttps://www.sota2.com/research/sota/story-generation-on-story-generation-gender-us-real-distribution2026-04-08T08:57:30.391Zhttps://www.sota2.com/research/sota/story-generation-on-story-generation-gender-uk-real-distribution2026-04-08T08:57:30.330Zhttps://www.sota2.com/research/sota/distribution-alignment-on-aggregate-of-six-datasets2026-04-08T08:57:30.295Zhttps://www.sota2.com/research/sota/distribution-alignment-on-gender-us-real2026-04-08T08:57:30.166Zhttps://www.sota2.com/research/sota/distribution-alignment-on-gender-uk-real2026-04-08T08:57:30.102Zhttps://www.sota2.com/research/sota/video-question-answering-on-moviechat2026-05-12T10:54:52.246Zhttps://www.sota2.com/research/sota/video-captioning-on-video-detail-description-vdd2026-04-08T08:47:28.907Zhttps://www.sota2.com/research/sota/video-captioning-on-video-detail-caption-vdc2026-04-08T08:47:28.872Zhttps://www.sota2.com/research/sota/jailbreaking-on-ehragent-all2026-04-08T08:37:24.911Zhttps://www.sota2.com/research/sota/video-question-answering-on-videoagent-aggregate-egoschema-and-next-qa2026-04-08T08:37:24.778Zhttps://www.sota2.com/research/sota/text-summarization-on-text-summarization-ba-ppl2026-04-08T08:00:54.335Zhttps://www.sota2.com/research/sota/code-retrieval-on-mteb-code-val2026-04-08T07:49:48.121Zhttps://www.sota2.com/research/sota/code-retrieval-on-freshstack-val2026-04-08T07:49:48.080Zhttps://www.sota2.com/research/sota/code-retrieval-on-ds10k-val2026-04-08T07:49:48.043Zhttps://www.sota2.com/research/sota/code-retrieval-on-mbpp-val2026-04-08T07:49:48.002Zhttps://www.sota2.com/research/sota/code-retrieval-on-humaneval-val2026-04-08T07:49:47.935Zhttps://www.sota2.com/research/sota/global-relocalization-on-industrial-like-environment2026-04-08T07:30:06.504Zhttps://www.sota2.com/research/sota/multi-step-reasoning-on-browsecomp-plus-ood2026-04-08T06:56:54.304Zhttps://www.sota2.com/research/sota/multi-hop-information-seeking-on-infoseek-eval-id2026-04-08T06:56:54.268Zhttps://www.sota2.com/research/sota/language-modeling-on-pubmedqa-mdq2026-04-07T10:38:41.315Zhttps://www.sota2.com/research/sota/long-term-forecasting-on-exchange-10-percent-few-shot2026-04-07T10:28:34.709Zhttps://www.sota2.com/research/sota/average-treatment-effect-estimation-on-ihdp2026-06-04T08:50:21.105Zhttps://www.sota2.com/research/sota/single-transfer-cross-chain-tracing-on-thor25hf-mini2026-04-07T10:03:21.984Zhttps://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-lm-f1-acc2026-04-08T07:04:23.682Zhttps://www.sota2.com/research/sota/camera-tracking-on-dl3dv2026-04-07T09:03:24.821Zhttps://www.sota2.com/research/sota/geolocation-on-geobrowse-level-2-browsecomp-style2026-04-07T08:52:50.921Zhttps://www.sota2.com/research/sota/geolocation-on-geobrowse-level-1-visual-cues2026-04-07T08:52:50.887Zhttps://www.sota2.com/research/sota/monocular-dynamic-scene-reconstruction-on-hosnerf-test2026-06-30T07:04:58.533Zhttps://www.sota2.com/research/sota/multi-hop-retrieval-on-multihop-rag-test2026-04-07T07:35:51.826Zhttps://www.sota2.com/research/sota/bivariate-causal-discovery-on-sim-ln-accuracy-audrc2026-04-08T09:18:50.429Zhttps://www.sota2.com/research/sota/cross-institutional-code-mapping-on-upmc-lab-loinc2026-04-07T07:06:44.717Zhttps://www.sota2.com/research/sota/cross-institutional-code-mapping-on-bdx-ccam-ccs2026-04-07T07:06:44.686Zhttps://www.sota2.com/research/sota/cross-institutional-code-mapping-on-upmc-px-ccs2026-04-07T07:06:44.650Zhttps://www.sota2.com/research/sota/mapping-quality-on-scannet-v12026-04-06T08:52:20.745Zhttps://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-val-asr-asr-g2026-04-06T08:38:10.745Zhttps://www.sota2.com/research/sota/temporal-sentence-grounding-on-charades-sta2026-05-26T12:24:41.173Zhttps://www.sota2.com/research/sota/hallucination-detection-on-mmmu-pro2026-04-06T08:17:58.034Zhttps://www.sota2.com/research/sota/hallucination-detection-on-crag-mm2026-04-06T08:17:57.997Zhttps://www.sota2.com/research/sota/open-vocabulary-object-detection-on-ov-lvis-v1-0-val2026-06-05T09:16:49.736Zhttps://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-n3dv-throughput2026-04-06T07:50:43.755Zhttps://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-st-nerf2026-04-06T07:50:43.717Zhttps://www.sota2.com/research/sota/dynamic-scene-reconstruction-on-dy-3dgs2026-04-06T07:50:43.677Zhttps://www.sota2.com/research/sota/state-estimation-on-view-of-delft-test2026-04-06T07:38:05.011Zhttps://www.sota2.com/research/sota/adversarial-attack-on-imagenet-augmix2026-04-06T07:25:05.864Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-pass-at-1-avg-tokens2026-06-23T11:16:36.173Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-math-p2026-04-06T07:16:20.375Zhttps://www.sota2.com/research/sota/reasoning-on-lqa2026-04-06T07:07:43.448Zhttps://www.sota2.com/research/sota/stem-question-answering-on-mqa2026-04-06T07:07:43.372Zhttps://www.sota2.com/research/sota/stem-question-answering-on-sciq-first-token-accuracy2026-04-06T07:07:43.324Zhttps://www.sota2.com/research/sota/narrative-understanding-on-mc-t2026-04-06T07:07:43.274Zhttps://www.sota2.com/research/sota/narrative-understanding-on-hs2026-04-06T07:07:43.219Zhttps://www.sota2.com/research/sota/narrative-understanding-on-sc2026-04-06T07:07:43.173Zhttps://www.sota2.com/research/sota/commonsense-reasoning-on-cqa2026-04-06T07:07:43.131Zhttps://www.sota2.com/research/sota/commonsense-reasoning-on-ms2026-04-06T07:07:43.078Zhttps://www.sota2.com/research/sota/commonsense-reasoning-on-obqa-first-token-accuracy2026-04-06T07:07:43.038Z