https://www.sota2.com/research/sota/multi-degradation-image-restoration-on-mio-100-2-concurrent-degradations2026-06-01T08:34:36.086Zhttps://www.sota2.com/research/sota/locomotion-on-d4rl-hopper-medium-expert-v22026-06-16T10:53:42.146Zhttps://www.sota2.com/research/sota/long-form-deep-research-answering-on-healthbench2026-06-01T08:15:11.322Zhttps://www.sota2.com/research/sota/robot-manipulation-on-robot-manipulation-tasks-m-32026-06-01T08:04:25.322Zhttps://www.sota2.com/research/sota/reasoning-on-bbh-matched-n-test2026-06-01T08:04:24.997Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-matched-n-groups-test2026-06-01T08:04:24.965Zhttps://www.sota2.com/research/sota/question-answering-on-mmlu-pro-matched-n-groups-test2026-06-01T08:04:24.939Zhttps://www.sota2.com/research/sota/question-answering-on-truthfulqa-matched-n-test2026-06-01T08:04:24.912Zhttps://www.sota2.com/research/sota/question-answering-on-triviaqa-matched-n-test2026-06-01T08:04:24.858Zhttps://www.sota2.com/research/sota/calibration-on-mean-macro-average-across-benchmarks2026-06-01T08:04:24.822Zhttps://www.sota2.com/research/sota/calibration-on-bbh2026-06-01T08:04:24.783Zhttps://www.sota2.com/research/sota/calibration-on-gsm8k2026-06-01T08:04:24.752Zhttps://www.sota2.com/research/sota/calibration-on-mmlu-pro2026-06-01T08:04:24.719Zhttps://www.sota2.com/research/sota/reasoning-on-bbh-brier-score2026-06-01T07:58:01.749Zhttps://www.sota2.com/research/sota/math-reasoning-on-gsm8k-brier-score2026-06-01T07:58:01.724Zhttps://www.sota2.com/research/sota/language-understanding-on-mmlu-pro-brier-score2026-06-01T07:58:01.704Zhttps://www.sota2.com/research/sota/question-answering-on-truthfulqa-brier-score2026-06-01T07:58:01.677Zhttps://www.sota2.com/research/sota/metric-depth-estimation-on-nyu-v22026-06-01T07:34:17.430Zhttps://www.sota2.com/research/sota/metric-depth-estimation-on-argoverse-22026-06-01T07:34:17.392Zhttps://www.sota2.com/research/sota/gpu-kernel-generation-and-optimization-on-kernelbench-level-22026-06-01T07:24:13.909Zhttps://www.sota2.com/research/sota/gpu-kernel-generation-and-optimization-on-kernelbench-level-12026-06-01T07:24:13.870Zhttps://www.sota2.com/research/sota/license-plate-recognition-on-ccpd-tilt2026-06-05T08:56:08.601Zhttps://www.sota2.com/research/sota/license-plate-recognition-on-ccpd-base2026-06-05T08:56:08.578Zhttps://www.sota2.com/research/sota/ai-text-detection-on-ai-generated-text-held-out-set2026-06-01T06:44:10.028Zhttps://www.sota2.com/research/sota/semantic-correspondence-on-spairu-pck-variants2026-05-29T11:54:06.281Zhttps://www.sota2.com/research/sota/video-generation-on-vbench-5s-horizon-21-frames2026-05-29T11:53:20.474Zhttps://www.sota2.com/research/sota/future-paper-retrieval-on-2k-47k-pool-test2026-05-29T11:47:47.622Zhttps://www.sota2.com/research/sota/document-question-answering-on-charxiv-rq2026-05-29T11:35:35.197Zhttps://www.sota2.com/research/sota/document-question-answering-on-charxiv-dq2026-05-29T11:35:35.169Zhttps://www.sota2.com/research/sota/talking-face-generation-on-hdtf2026-05-29T11:34:04.268Zhttps://www.sota2.com/research/sota/talking-face-generation-on-crema2026-05-29T11:34:04.235Zhttps://www.sota2.com/research/sota/counterfactual-explanation-diversity-on-strikes2026-05-29T11:33:02.158Zhttps://www.sota2.com/research/sota/counterfactual-explanation-diversity-on-prnn-fglass2026-05-29T11:33:02.078Zhttps://www.sota2.com/research/sota/counterfactual-explanation-diversity-on-ecoli2026-05-29T11:33:01.784Zhttps://www.sota2.com/research/sota/heads-up-no-limit-texas-hold-em-on-gtowizard-hunl2026-05-29T10:55:50.527Zhttps://www.sota2.com/research/sota/scale-invariant-video-depth-estimation-on-kitti2026-05-29T10:53:48.508Zhttps://www.sota2.com/research/sota/scale-invariant-video-depth-estimation-on-bonn2026-05-29T10:53:48.472Zhttps://www.sota2.com/research/sota/scale-invariant-video-depth-estimation-on-sintel2026-05-29T10:53:48.433Zhttps://www.sota2.com/research/sota/document-retrieval-on-multidocr2026-05-29T10:44:15.116Zhttps://www.sota2.com/research/sota/text-embedding-on-tr-mteb-macro-averaged2026-05-29T10:43:44.423Zhttps://www.sota2.com/research/sota/regression-on-elevators-no-contamination2026-05-29T10:33:41.580Zhttps://www.sota2.com/research/sota/regression-on-kin8nm-no-contamination2026-05-29T10:33:41.551Zhttps://www.sota2.com/research/sota/regression-on-power-no-contamination2026-05-29T10:33:41.520Zhttps://www.sota2.com/research/sota/regression-on-concrete-10-percent-outlier-contamination2026-05-29T10:33:41.487Zhttps://www.sota2.com/research/sota/regression-on-yacht-10-percent-outlier-contamination2026-05-29T10:33:41.461Zhttps://www.sota2.com/research/sota/regression-on-boston-10-percent-outlier-contamination2026-05-29T10:33:41.435Zhttps://www.sota2.com/research/sota/tabular-regression-on-protein-uci-10-percent-outlier-contamination2026-05-29T10:33:41.402Zhttps://www.sota2.com/research/sota/tabular-regression-on-carbon-uci-10-percent-outlier-contamination2026-05-29T10:33:41.369Zhttps://www.sota2.com/research/sota/tabular-regression-on-energy-uci-10-percent-outlier-contamination2026-05-29T10:33:41.340Zhttps://www.sota2.com/research/sota/regression-on-concrete-no-contamination2026-05-29T10:33:41.305Zhttps://www.sota2.com/research/sota/regression-on-yacht-no-contamination2026-05-29T10:33:41.273Zhttps://www.sota2.com/research/sota/regression-on-boston-no-contamination2026-05-29T10:33:41.239Zhttps://www.sota2.com/research/sota/tabular-regression-on-protein-no-contamination-avg-over-10-trials2026-05-29T10:33:41.100Zhttps://www.sota2.com/research/sota/tabular-regression-on-carbon-no-contamination-avg-over-10-trials2026-05-29T10:33:41.055Zhttps://www.sota2.com/research/sota/tabular-regression-on-energy-no-contamination-avg-over-10-trials2026-05-29T10:33:41.008Zhttps://www.sota2.com/research/sota/regression-on-elevators-10-percent-outlier-contamination-test2026-05-29T10:33:40.975Zhttps://www.sota2.com/research/sota/regression-on-kin8nm-10-percent-outlier-contamination-test2026-05-29T10:33:40.940Zhttps://www.sota2.com/research/sota/regression-on-power-10-percent-outlier-contamination-test2026-05-29T10:33:40.905Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-litt3200-ood2026-05-29T10:23:38.859Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-littc2se-ood2026-05-29T10:23:38.827Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-setting-sharp-2-ind2026-05-29T10:23:38.796Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-yunting-ood2026-05-29T10:23:38.767Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-yunting-ind2026-05-29T10:23:38.737Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-meditron-ood2026-05-29T10:23:38.703Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-meditron-ind2026-05-29T10:23:38.668Zhttps://www.sota2.com/research/sota/respiratory-sound-classification-on-akgc417l-ood2026-05-29T10:23:38.639Zhttps://www.sota2.com/research/sota/node-classification-on-oag-cs-h2gb-test2026-05-29T10:13:36.458Zhttps://www.sota2.com/research/sota/node-classification-on-ogbn-mag-h2gb-test2026-05-29T10:13:36.425Zhttps://www.sota2.com/research/sota/node-classification-on-oag-chem-h2gb-test2026-05-29T10:13:36.396Zhttps://www.sota2.com/research/sota/node-classification-on-pokec-h2gb-test2026-05-29T10:13:36.364Zhttps://www.sota2.com/research/sota/node-classification-on-mag-year-h2gb-test2026-05-29T10:13:36.322Zhttps://www.sota2.com/research/sota/video-moment-retrieval-on-activitynet-captions-2015-test2026-05-29T10:13:35.682Zhttps://www.sota2.com/research/sota/etiology-prediction-on-retrospective-multimodal-cardiovascular-clinical-decision-making-dataset-test2026-05-29T10:03:33.694Zhttps://www.sota2.com/research/sota/information-retrieval-on-hipaa-derived-qa2026-05-29T10:03:33.584Zhttps://www.sota2.com/research/sota/information-retrieval-on-regops-bench2026-05-29T10:03:33.547Zhttps://www.sota2.com/research/sota/kernel-code-generation-on-kernelbench-v0-2-0-dev0-full-250-task-suite2026-05-29T10:03:33.457Zhttps://www.sota2.com/research/sota/text-to-speech-synthesis-on-ljspeech-mos-wer2026-05-29T09:35:22.657Zhttps://www.sota2.com/research/sota/safety-classification-on-toxicchat-jailbreaking2026-05-29T09:33:23.499Zhttps://www.sota2.com/research/sota/binary-safety-classification-on-wildguard-prompt-safety2026-05-29T09:33:23.467Zhttps://www.sota2.com/research/sota/binary-safety-classification-on-openai-moderation-oai_safety2026-05-29T09:33:23.427Zhttps://www.sota2.com/research/sota/inference-efficiency-on-1024-token-sequences-inference-summary2026-05-29T09:33:22.774Zhttps://www.sota2.com/research/sota/robot-manipulation-on-libero-plus-uncertainty-and-success2026-06-09T08:54:44.443Zhttps://www.sota2.com/research/sota/building-damage-detection-on-xbd-test2026-05-29T09:13:34.390Zhttps://www.sota2.com/research/sota/traversability-estimation-on-goose-c-val2026-05-29T09:13:17.680Zhttps://www.sota2.com/research/sota/traversability-estimation-on-acdc2026-05-29T09:13:17.644Zhttps://www.sota2.com/research/sota/traversability-estimation-on-cityscapes2026-05-29T09:13:17.607Zhttps://www.sota2.com/research/sota/traversability-estimation-on-mountain2026-05-29T09:13:17.578Zhttps://www.sota2.com/research/sota/traversability-estimation-on-campus2026-05-29T09:13:17.538Zhttps://www.sota2.com/research/sota/traversability-estimation-on-goose-val2026-05-29T09:13:17.495Zhttps://www.sota2.com/research/sota/terminal-task-on-terminal-bench-pro2026-05-29T09:13:16.111Zhttps://www.sota2.com/research/sota/terminal-task-on-terminal-bench-1-0-pass-at-1-pass-at-42026-05-29T09:13:16.066Zhttps://www.sota2.com/research/sota/optimization-modeling-on-industryor-sa-micro-average2026-05-29T09:13:15.575Zhttps://www.sota2.com/research/sota/language-modeling-on-openr12026-05-29T09:03:13.076Zhttps://www.sota2.com/research/sota/medical-question-answering-on-vitalbench-tier-b-670-test2026-05-29T09:03:12.752Zhttps://www.sota2.com/research/sota/medical-question-answering-on-vitalbench-tier-a-635-test2026-05-29T09:03:12.721Zhttps://www.sota2.com/research/sota/interactive-agent-task-completion-on-alfworld-unseen-val2026-05-29T08:53:10.417Zhttps://www.sota2.com/research/sota/html-observation-reduction-on-weblinx2026-05-29T08:45:15.570Zhttps://www.sota2.com/research/sota/html-observation-reduction-on-workarena2026-05-29T08:45:15.544Zhttps://www.sota2.com/research/sota/tokenization-efficiency-on-flores-200-dev-plus-devtest2026-05-29T08:43:07.885Zhttps://www.sota2.com/research/sota/tokenization-efficiency-on-in22-gen-test2026-05-29T08:43:07.849Zhttps://www.sota2.com/research/sota/per-word-fertility-on-flores-200-dev-plus-devtest2026-05-29T08:43:07.183Zhttps://www.sota2.com/research/sota/task-success-on-memgui-bench-1-0-test2026-05-29T08:33:07.837Zhttps://www.sota2.com/research/sota/safety-evaluation-on-abstainqa-test2026-05-29T08:33:03.894Zhttps://www.sota2.com/research/sota/safety-evaluation-on-abstainqa-val2026-05-29T08:33:03.853Zhttps://www.sota2.com/research/sota/safety-and-truthfulness-evaluation-on-truthfulqa-val2026-05-29T08:33:03.809Zhttps://www.sota2.com/research/sota/knowledge-based-language-understanding-on-mmlu-pro-val2026-05-29T08:33:03.761Zhttps://www.sota2.com/research/sota/multi-task-generalization-on-multi-task-overall-average2026-05-29T08:33:03.711Zhttps://www.sota2.com/research/sota/selective-question-answering-on-abstainqa-test2026-05-29T08:33:03.663Zhttps://www.sota2.com/research/sota/selective-question-answering-on-abstainqa-val2026-05-29T08:33:03.609Zhttps://www.sota2.com/research/sota/hardened-language-understanding-on-mmlu-pro-test2026-05-29T08:33:03.391Zhttps://www.sota2.com/research/sota/hardened-language-understanding-on-mmlu-pro-val2026-05-29T08:33:03.343Zhttps://www.sota2.com/research/sota/time-series-anomaly-detection-on-ucr-test2026-05-29T08:25:03.414Zhttps://www.sota2.com/research/sota/general-language-capability-on-aggregate-ifeval-ifbench-arena-hard-v2-0-creative-writing-v3-writingbench2026-05-29T08:23:01.985Zhttps://www.sota2.com/research/sota/forgery-detection-on-celeb-df-v12026-05-29T08:12:58.651Zhttps://www.sota2.com/research/sota/forgery-detection-on-deepfakedetection-dfd2026-05-29T08:12:58.618Zhttps://www.sota2.com/research/sota/forgery-detection-on-faceshifter2026-05-29T08:12:58.584Zhttps://www.sota2.com/research/sota/forgery-detection-on-dfd2026-05-29T08:12:58.502Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-2-ant-medium2026-06-23T08:03:33.756Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-2-ant-medium-replay2026-06-23T08:03:33.730Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-2-ant-medium-expert2026-06-23T08:03:33.701Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-3-hopper-medium2026-06-23T08:03:33.676Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-6-halfcheetah-medium2026-06-23T08:03:33.654Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-6-halfcheetah-medium-replay2026-06-23T08:03:33.820Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-6-halfcheetah-medium-expert2026-06-23T08:03:33.626Zhttps://www.sota2.com/research/sota/multi-agent-reinforcement-learning-on-mamujoco-omiga-6-halfcheetah-expert2026-06-23T08:03:33.599Zhttps://www.sota2.com/research/sota/regression-on-uci-yacht-til2026-05-29T08:07:51.599Zhttps://www.sota2.com/research/sota/regression-on-uci-wine-red-til2026-05-29T08:07:51.576Zhttps://www.sota2.com/research/sota/regression-on-uci-superconduct2026-05-29T08:07:51.544Zhttps://www.sota2.com/research/sota/regression-on-uci-power-til2026-05-29T08:07:51.514Zhttps://www.sota2.com/research/sota/regression-on-uci-boston-til2026-05-29T08:07:51.490Zhttps://www.sota2.com/research/sota/regression-on-uci-energy-til2026-05-29T08:07:51.460Zhttps://www.sota2.com/research/sota/regression-on-uci-concrete-til2026-05-29T08:07:51.426Zhttps://www.sota2.com/research/sota/regression-on-uci-carbon2026-05-29T08:07:51.399Zhttps://www.sota2.com/research/sota/regression-on-wine-red-uci2026-05-29T08:07:51.333Zhttps://www.sota2.com/research/sota/regression-on-superconduct-uci2026-05-29T08:07:51.293Zhttps://www.sota2.com/research/sota/regression-on-power-uci2026-05-29T08:07:51.261Zhttps://www.sota2.com/research/sota/regression-on-carbon-uci2026-05-29T08:07:51.228Zhttps://www.sota2.com/research/sota/regression-on-uci-yacht-308-6-1-test2026-05-29T08:07:50.762Zhttps://www.sota2.com/research/sota/regression-on-uci-wine-red-test2026-05-29T08:07:50.727Zhttps://www.sota2.com/research/sota/regression-on-uci-superconduct-test2026-05-29T08:07:50.696Zhttps://www.sota2.com/research/sota/regression-on-uci-carbon-10721-7-1-test2026-05-29T08:07:50.668Zhttps://www.sota2.com/research/sota/web-task-success-on-mind2web-live2026-05-29T07:52:49.211Zhttps://www.sota2.com/research/sota/soil-characterization-mapping-on-soil-mapping-simulation-t-100-percent-completion-1-02026-05-29T07:44:05.776Zhttps://www.sota2.com/research/sota/soil-characterization-mapping-on-soil-mapping-simulation-t-50-percent-completion-1-02026-05-29T07:44:05.750Zhttps://www.sota2.com/research/sota/soil-characterization-mapping-on-soil-mapping-simulation-t-25-percent-completion-1-02026-05-29T07:44:05.724Zhttps://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-relocate-human-cloned-expert2026-05-29T07:42:47.440Zhttps://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-hammer-3-tasks-human-cloned-expert2026-05-29T07:42:47.406Zhttps://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-door-human-cloned-expert2026-05-29T07:42:47.372Zhttps://www.sota2.com/research/sota/offline-reinforcement-learning-on-d4rl-adroit-pen-human-cloned-expert2026-05-29T07:42:47.334Zhttps://www.sota2.com/research/sota/age-regression-on-biopoint2026-05-29T07:42:45.872Zhttps://www.sota2.com/research/sota/asd-classification-on-biopoint2026-05-29T07:42:45.800Zhttps://www.sota2.com/research/sota/cog-score-composite-regression-on-hcp2026-05-29T07:42:45.754Zhttps://www.sota2.com/research/sota/mvp-ranking-on-nba-regular-season-mvp-voting-results-2021-20222026-05-29T07:32:41.045Zhttps://www.sota2.com/research/sota/mvp-ranking-on-nba-regular-season-mvp-voting-results-2022-20232026-05-29T07:32:41.009Zhttps://www.sota2.com/research/sota/mvp-ranking-on-nba-regular-season-mvp-voting-results-2023-20242026-05-29T07:32:40.978Zhttps://www.sota2.com/research/sota/web-navigation-on-mind2web-avg2026-05-28T10:33:21.378Zhttps://www.sota2.com/research/sota/high-resolution-visual-search-on-hr-bench-4k2026-05-28T10:32:29.455Zhttps://www.sota2.com/research/sota/compressed-sensing-on-ms-coco2026-05-28T10:32:28.462Zhttps://www.sota2.com/research/sota/anisotropic-deblurring-on-ms-coco-runtime2026-05-28T10:32:28.422Zhttps://www.sota2.com/research/sota/runtime-efficiency-for-super-resolution-on-ms-coco2026-05-28T10:32:28.389Zhttps://www.sota2.com/research/sota/runtime-performance-for-inpainting-on-ms-coco2026-05-28T10:32:28.357Zhttps://www.sota2.com/research/sota/2x-compressed-sensing-on-ms-coco2026-05-28T10:32:28.257Zhttps://www.sota2.com/research/sota/anisotropic-deblurring-on-ms-coco2026-05-28T10:32:28.226Zhttps://www.sota2.com/research/sota/4x-super-resolution-on-ms-coco2026-05-28T10:32:28.189Zhttps://www.sota2.com/research/sota/image-inpainting-on-ms-coco2026-05-28T10:32:28.150Zhttps://www.sota2.com/research/sota/2x-compressed-sensing-on-ms-coco-test2026-05-28T10:32:28.076Zhttps://www.sota2.com/research/sota/4x-super-resolution-on-ms-coco-test2026-05-28T10:32:28.037Zhttps://www.sota2.com/research/sota/random-inpainting-on-ms-coco-test2026-05-28T10:32:27.996Zhttps://www.sota2.com/research/sota/robotic-manipulation-on-libero-small-scale2026-05-28T10:22:25.617Zhttps://www.sota2.com/research/sota/mobile-agent-ui-interaction-on-aitz2026-05-28T10:22:25.428Zhttps://www.sota2.com/research/sota/customer-support-interaction-on-c-bench-telecom-ours-test2026-05-28T10:13:38.399Zhttps://www.sota2.com/research/sota/customer-support-interaction-on-bench-telecom-verified-test2026-05-28T10:13:38.375Zhttps://www.sota2.com/research/sota/customer-support-interaction-on-c-bench-retail-ours-test2026-05-28T10:13:38.348Zhttps://www.sota2.com/research/sota/customer-support-interaction-on-bench-retail-verified-test2026-05-28T10:13:38.306Zhttps://www.sota2.com/research/sota/customer-support-interaction-on-c-bench-airline-ours-test2026-05-28T10:13:38.281Zhttps://www.sota2.com/research/sota/customer-support-interaction-on-bench-airline-verified-test2026-05-28T10:13:38.255Zhttps://www.sota2.com/research/sota/3d-box-localization-on-scanrefer2026-05-28T10:12:21.034Zhttps://www.sota2.com/research/sota/competency-tagging-on-utc2026-05-28T10:12:20.781Zhttps://www.sota2.com/research/sota/monocular-depth-estimation-on-cityscapes-416-x-128-test2026-05-28T10:05:32.726Zhttps://www.sota2.com/research/sota/generalized-zero-shot-learning-on-nus-wide2026-05-28T09:44:21.232Zhttps://www.sota2.com/research/sota/generalized-zero-shot-learning-on-coco-20142026-05-28T09:44:21.191Zhttps://www.sota2.com/research/sota/open-ended-medical-consultation-on-healthbench-hard2026-05-28T09:32:09.792Zhttps://www.sota2.com/research/sota/watermark-evasion-on-llm-watermarking-algorithms-kgw-unigram-upv-ewd-dip-sir-exp2026-05-28T09:32:08.296Zhttps://www.sota2.com/research/sota/general-language-modeling-evaluation-on-aggregate-wino-hella-arc-e-arc-c-mmlu2026-05-28T09:12:01.042Zhttps://www.sota2.com/research/sota/general-language-understanding-on-winogrande-hellaswag-arc-mmlu-consolidated2026-05-28T09:12:00.951Zhttps://www.sota2.com/research/sota/ambiguity-detection-on-ambient2026-05-28T09:02:46.564Zhttps://www.sota2.com/research/sota/portrait-animation-on-emh-benchmark2026-05-28T08:43:34.195Zhttps://www.sota2.com/research/sota/subset-level-sensitivity-prediction-on-sampled-test2026-05-28T08:42:03.144Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-test-accuracy-tokens-training-time-speedup2026-05-28T08:41:51.327Zhttps://www.sota2.com/research/sota/multimodal-geometry-reasoning-on-geo3k2026-05-28T08:41:51.295Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-math-test-accuracy-efficiency-speedup2026-05-28T08:41:51.106Zhttps://www.sota2.com/research/sota/reconstruction-on-function-composition-hard-tier-12026-05-28T08:32:27.633Zhttps://www.sota2.com/research/sota/reconstruction-on-function-composition-easy-tier-12026-05-28T08:32:27.601Zhttps://www.sota2.com/research/sota/reconstruction-on-function-composition-tier-1-id2026-05-28T08:32:27.573Zhttps://www.sota2.com/research/sota/mask-prediction-mask_block_128-on-function-composition-tier-1-hard2026-05-28T08:32:27.495Zhttps://www.sota2.com/research/sota/mask-prediction-mask_block_128-on-function-composition-tier-1-easy2026-05-28T08:32:27.470Zhttps://www.sota2.com/research/sota/mask-prediction-mask_block_128-on-function-composition-tier-1-id2026-05-28T08:32:27.437Zhttps://www.sota2.com/research/sota/mask-prediction-mask_random_30-on-function-composition-tier-1-hard2026-05-28T08:32:27.406Zhttps://www.sota2.com/research/sota/mask-prediction-mask_random_30-on-function-composition-tier-1-easy2026-05-28T08:32:27.376Zhttps://www.sota2.com/research/sota/mask-prediction-mask_random_30-on-function-composition-tier-1-id2026-05-28T08:32:27.346Z