https://www.sota2.com/research/sota/computational-complexity-analysis-on-1080p-resolution-video2026-06-04T12:29:52.850Zhttps://www.sota2.com/research/sota/trading-strategy-performance-evaluation-on-binance-usd-m-futures-2025-out-of-sample2026-06-04T12:21:28.317Zhttps://www.sota2.com/research/sota/average-latency-on-math2026-06-04T12:19:50.455Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-average-latency2026-06-04T12:19:50.430Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-s_format-acc2026-06-04T12:19:50.373Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-s_format-accuracy2026-06-04T12:19:50.344Zhttps://www.sota2.com/research/sota/tactile-object-recognition-on-transtac2026-06-04T12:11:21.444Zhttps://www.sota2.com/research/sota/tactile-object-recognition-on-9dtact2026-06-04T12:11:21.423Zhttps://www.sota2.com/research/sota/tactile-object-recognition-on-gelsight-mini2026-06-04T12:11:21.404Zhttps://www.sota2.com/research/sota/reasoning-on-bbh-t2t-1-000-items-test2026-06-04T12:11:21.382Zhttps://www.sota2.com/research/sota/reasoning-on-bbh-s2t-1-000-items-test2026-06-04T12:11:21.360Zhttps://www.sota2.com/research/sota/dimensionality-reduction-on-clinical-dataset-abdominal-pain-train2026-06-04T11:59:48.179Zhttps://www.sota2.com/research/sota/image-reconstruction-and-compression-on-div2k-set22026-06-04T11:49:43.338Zhttps://www.sota2.com/research/sota/instance-segmentation-on-for-instance-tu-wien2026-06-04T11:49:42.376Zhttps://www.sota2.com/research/sota/instance-segmentation-on-for-instance-scion-site2026-06-04T11:49:42.348Zhttps://www.sota2.com/research/sota/instance-segmentation-on-for-instance-rmit2026-06-04T11:49:42.322Zhttps://www.sota2.com/research/sota/instance-segmentation-on-for-instance-nibio-site2026-06-04T11:49:42.300Zhttps://www.sota2.com/research/sota/instance-segmentation-on-for-instance-culs-site2026-06-04T11:49:42.275Zhttps://www.sota2.com/research/sota/spatial-filtering-on-ears-test2026-06-04T11:44:08.565Zhttps://www.sota2.com/research/sota/specification-alignment-on-specbench2026-06-04T11:40:05.804Zhttps://www.sota2.com/research/sota/depth-camera-rendering-on-quadrotor-depth-rendering-2-048-parallel-environments-64x642026-06-04T11:40:05.787Zhttps://www.sota2.com/research/sota/zero-shot-classification-on-evaluation-suite-arcc-arce-boolq-hswag-piqa2026-06-04T11:39:40.106Zhttps://www.sota2.com/research/sota/in-the-wild-segmentation-on-fss2026-06-04T11:36:32.134Zhttps://www.sota2.com/research/sota/in-the-wild-segmentation-on-camo2026-06-04T11:36:32.115Zhttps://www.sota2.com/research/sota/in-the-wild-segmentation-on-ocid2026-06-04T11:36:32.092Zhttps://www.sota2.com/research/sota/cumulative-temporal-regret-on-cap-gsm8k2026-06-04T11:34:00.928Zhttps://www.sota2.com/research/sota/solving-parametric-pdes-on-1d-helmholtz-k-1-00-3-25-5-50-7-75-10-002026-06-04T11:33:30.735Zhttps://www.sota2.com/research/sota/cardiac-segmentation-on-m-and-ms2-lax-4c2026-06-04T11:32:00.054Zhttps://www.sota2.com/research/sota/gradient-inversion-attack-on-cifar-10-test2026-06-04T11:29:37.298Zhttps://www.sota2.com/research/sota/point-polyline-distance-estimation-on-spatial-instruction-dataset2026-06-04T11:25:25.044Zhttps://www.sota2.com/research/sota/hrtf-upsampling-on-hutubs-simulation2026-06-04T11:23:23.281Zhttps://www.sota2.com/research/sota/anomaly-detection-on-shapenetpart-5-shot2026-06-04T11:23:23.261Zhttps://www.sota2.com/research/sota/3d-anomaly-detection-on-shapenetpart-3-shot2026-06-04T11:23:23.239Zhttps://www.sota2.com/research/sota/anomaly-detection-on-shapenetpart-1-shot2026-06-04T11:23:23.214Zhttps://www.sota2.com/research/sota/video-question-answering-on-vidcapbench2026-06-04T11:20:51.998Zhttps://www.sota2.com/research/sota/video-question-answering-on-plm-sgqa2026-06-04T11:20:51.981Zhttps://www.sota2.com/research/sota/video-question-answering-on-activitynet-qa-llm-metrics2026-06-04T11:20:51.961Zhttps://www.sota2.com/research/sota/video-question-answering-on-next-qa-open2026-06-04T11:20:51.943Zhttps://www.sota2.com/research/sota/video-captioning-on-carebench2026-06-04T11:20:51.924Zhttps://www.sota2.com/research/sota/video-captioning-on-vdc-aggregate2026-06-04T11:20:51.902Zhttps://www.sota2.com/research/sota/video-captioning-on-plm-rcap2026-06-04T11:20:51.884Zhttps://www.sota2.com/research/sota/video-captioning-on-plm-rdcap2026-06-04T11:20:51.865Zhttps://www.sota2.com/research/sota/seizure-burden-minimization-on-intrinsic-trace2026-06-04T11:19:35.068Zhttps://www.sota2.com/research/sota/image-classification-on-sun397-test-val2026-06-04T11:17:50.315Zhttps://www.sota2.com/research/sota/image-classification-on-flowers102-test-val2026-06-04T11:17:50.295Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-100-test-val2026-06-04T11:17:50.275Zhttps://www.sota2.com/research/sota/image-classification-on-cifar-100-acc-asr-efficiency2026-06-04T11:14:48.850Zhttps://www.sota2.com/research/sota/image-classification-on-imagenet-1k-acc-asr-size-latency2026-06-04T11:14:48.821Zhttps://www.sota2.com/research/sota/posterior-parameter-estimation-on-3-component-bayesian-univariate-gaussian-mixture-model-k-3-n-5002026-06-04T11:12:17.729Zhttps://www.sota2.com/research/sota/kv-cache-efficiency-on-trace-driven-simulation-no-limit-budget-100k-pool2026-06-04T11:12:17.666Zhttps://www.sota2.com/research/sota/kv-cache-efficiency-on-trace-driven-simulation-50-gb-kv-cache-budget-100k-doc-pool-zipf-doc-popularity2026-06-04T11:12:17.647Zhttps://www.sota2.com/research/sota/kv-cache-efficiency-on-trace-driven-simulation-10-gb-kv-cache-budget-100k-doc-pool-zipf-doc-popularity2026-06-04T11:12:17.627Zhttps://www.sota2.com/research/sota/kv-cache-efficiency-on-trace-driven-simulation-5-gb-kv-cache-budget-100k-doc-pool-zipf-doc-popularity2026-06-04T11:12:17.607Zhttps://www.sota2.com/research/sota/kv-cache-efficiency-on-trace-driven-simulation-1gb-budget-100k-pool2026-06-04T11:12:17.588Zhttps://www.sota2.com/research/sota/few-shot-classification-on-ag-news2026-06-04T11:12:17.532Zhttps://www.sota2.com/research/sota/routing-interpretability-on-preference-700k-test2026-06-04T11:09:46.504Zhttps://www.sota2.com/research/sota/reward-modeling-on-preference-700k-test2026-06-04T11:09:46.487Zhttps://www.sota2.com/research/sota/folding-on-isaac-lab-sim-to-sim-transfer-test2026-06-04T11:09:32.307Zhttps://www.sota2.com/research/sota/folding-on-flex-in-distribution-test2026-06-04T11:09:32.272Zhttps://www.sota2.com/research/sota/garment-folding-on-real-world-unseen-garments2026-06-04T11:09:32.235Zhttps://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-accuracy-ar-percent2026-06-04T11:08:15.574Zhttps://www.sota2.com/research/sota/robotic-manipulation-on-real-world-piper-arm-tasks-task-success-rates2026-06-04T11:04:13.080Zhttps://www.sota2.com/research/sota/trps-affordance-grounding-on-a2a-bench2026-06-04T11:04:13.061Zhttps://www.sota2.com/research/sota/prefill-attack-on-harmbench-harmful-200-standard-behaviors-132026-06-04T11:03:12.639Zhttps://www.sota2.com/research/sota/random-insertion-attack-on-harmbench-200-standard-behaviors2026-06-04T11:03:12.620Zhttps://www.sota2.com/research/sota/transit-network-design-on-amsterdam2026-06-04T11:03:12.576Zhttps://www.sota2.com/research/sota/transit-network-design-on-xi-an2026-06-04T11:03:12.556Zhttps://www.sota2.com/research/sota/reading-order-on-fcr2026-06-04T11:02:42.381Zhttps://www.sota2.com/research/sota/reading-order-on-ohg2026-06-04T11:02:42.346Zhttps://www.sota2.com/research/sota/dropout-prediction-on-edx-dropout-prediction-14d-test2026-06-04T11:01:41.930Zhttps://www.sota2.com/research/sota/multi-agent-path-planning-on-gibson-ribera2026-06-04T11:01:41.841Zhttps://www.sota2.com/research/sota/multi-agent-path-planning-on-gibson-cantwell2026-06-04T11:01:41.824Zhttps://www.sota2.com/research/sota/multi-agent-path-planning-on-gibson-denmark2026-06-04T11:01:41.803Zhttps://www.sota2.com/research/sota/multi-agent-mapping-and-path-planning-on-gibson-ribera2026-06-04T11:01:41.752Zhttps://www.sota2.com/research/sota/multi-agent-mapping-and-path-planning-on-gibson-cantwell2026-06-04T11:01:41.733Zhttps://www.sota2.com/research/sota/multi-agent-mapping-and-path-planning-on-gibson-denmark2026-06-04T11:01:41.707Zhttps://www.sota2.com/research/sota/autonomous-parking-on-dsc3d-test2026-06-04T11:00:41.448Zhttps://www.sota2.com/research/sota/autonomous-parking-on-dlp-test2026-06-04T11:00:41.426Zhttps://www.sota2.com/research/sota/multi-turn-covert-exfiltration-detection-on-synthetic-multi-turn-covert-exfiltration-suite2026-06-04T10:59:39.993Zhttps://www.sota2.com/research/sota/visual-planning-on-robosuite2026-06-04T10:59:09.687Zhttps://www.sota2.com/research/sota/latent-action-policy-learning-on-ogbench2026-06-04T10:59:09.670Zhttps://www.sota2.com/research/sota/latent-action-policy-learning-on-crafter2026-06-04T10:59:09.649Zhttps://www.sota2.com/research/sota/push-cover-on-real-world-tabletop-manipulation2026-06-04T10:59:09.615Zhttps://www.sota2.com/research/sota/cover-on-real-world-tabletop-manipulation2026-06-04T10:59:09.597Zhttps://www.sota2.com/research/sota/push-on-real-world-tabletop-manipulation2026-06-04T10:59:09.577Zhttps://www.sota2.com/research/sota/mitosis-classification-on-normal-vs-abnormal-mitosis-1st-frame2026-06-04T10:57:07.034Zhttps://www.sota2.com/research/sota/modulation-recognition2026-06-04T10:57:06.713Zhttps://www.sota2.com/research/sota/image-generation-on-imagenet-256-x-256-partial-train2026-06-04T10:54:35.850Zhttps://www.sota2.com/research/sota/navigation-on-embodiedbench-vanilla2026-06-04T10:52:01.967Zhttps://www.sota2.com/research/sota/manipulation-task-on-embodiedbench-vanilla2026-06-04T10:52:01.737Zhttps://www.sota2.com/research/sota/traveling-salesman-problem-on-tsp10k2026-06-04T10:51:01.019Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-pass-at-1-metrics2026-06-04T10:49:30.715Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-pass-at-1-last-pass-at-1-best2026-06-04T10:49:30.694Zhttps://www.sota2.com/research/sota/3d-texture-generation-on-lvis2026-06-04T10:43:57.234Zhttps://www.sota2.com/research/sota/3d-texture-generation-on-sa-3dao2026-06-04T10:43:57.213Zhttps://www.sota2.com/research/sota/3d-texture-generation-on-preference-set2026-06-04T10:43:57.195Zhttps://www.sota2.com/research/sota/3d-texture-generation-on-iso3d2026-06-04T10:43:57.178Zhttps://www.sota2.com/research/sota/retrieval-augmented-generation-on-average-all-6-datasets2026-06-04T10:40:24.694Zhttps://www.sota2.com/research/sota/math-reasoning-on-amc23-speed-length-modification2026-06-04T10:38:53.767Zhttps://www.sota2.com/research/sota/math-reasoning-on-math-500-generation-efficiency-and-accuracy2026-06-04T10:38:53.748Zhttps://www.sota2.com/research/sota/reasoning-on-gpqa-avg-length-modify-ratio-estimated-speed-acc-acc-improv2026-06-04T10:38:53.729Zhttps://www.sota2.com/research/sota/object-classification-on-thue-act-502026-06-04T10:36:53.117Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-82026-06-04T10:32:21.055Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-72026-06-04T10:32:21.035Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-62026-06-04T10:32:21.015Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-52026-06-04T10:32:20.995Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-42026-06-04T10:32:20.973Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-32026-06-04T10:32:20.951Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-22026-06-04T10:32:20.929Zhttps://www.sota2.com/research/sota/clustering-on-synthetic-data-set-12026-06-04T10:32:20.910Zhttps://www.sota2.com/research/sota/system-identification-on-non-interacting-process2026-06-04T10:30:50.462Zhttps://www.sota2.com/research/sota/system-identification-on-interacting-process2026-06-04T10:30:50.444Zhttps://www.sota2.com/research/sota/inference-in-gaussian-process-dynamical-systems-on-cmu-motion-capture-subject-64-trial-102026-06-04T10:30:20.111Zhttps://www.sota2.com/research/sota/inference-in-gaussian-process-dynamical-systems-on-cmu-motion-capture-subject-64-trial-92026-06-04T10:30:20.093Zhttps://www.sota2.com/research/sota/inference-in-gaussian-process-dynamical-systems-on-cmu-motion-capture-subject-64-trial-82026-06-04T10:30:20.073Zhttps://www.sota2.com/research/sota/pendulum-tracking-on-pendulum-swing-data-test2026-06-04T10:30:20.052Zhttps://www.sota2.com/research/sota/pctl-formula-satisfaction-probability-on-stochastic-dubins-vehicle-case-studies-case-c2026-06-04T10:29:49.882Zhttps://www.sota2.com/research/sota/pctl-formula-satisfaction-probability-on-stochastic-dubins-vehicle-case-studies-case-b2026-06-04T10:29:49.860Zhttps://www.sota2.com/research/sota/pctl-formula-satisfaction-probability-on-stochastic-dubins-vehicle-case-studies-case-a2026-06-04T10:29:49.842Zhttps://www.sota2.com/research/sota/unsupervised-likelihood-estimation-on-iris2026-06-04T10:20:15.446Zhttps://www.sota2.com/research/sota/unsupervised-likelihood-estimation-on-elliptical2026-06-04T10:20:15.423Zhttps://www.sota2.com/research/sota/visual-odometry-on-replica-sequences2026-06-04T10:19:13.754Zhttps://www.sota2.com/research/sota/visual-odometry-on-tum-fr2_xyz2026-06-04T10:18:44.918Zhttps://www.sota2.com/research/sota/abstract-reasoning-on-arc-8-held-out-tasks2026-06-04T10:17:44.363Zhttps://www.sota2.com/research/sota/gui-agent-task-success-on-osworld-vlc-test2026-06-04T10:16:13.327Zhttps://www.sota2.com/research/sota/gui-agent-task-success-on-osworld-chrome-test2026-06-04T10:16:13.309Zhttps://www.sota2.com/research/sota/simultaneous-speech-translation-on-iwslt-cs-en-2026-dev2026-06-04T10:15:12.919Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-math-pass-at-1-accuracy-standard-error2026-06-04T10:14:12.084Zhttps://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-d-pass-at-1-accuracy-standard-error2026-06-04T10:14:12.066Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-pass-at-1-accuracy-standard-error2026-06-04T10:14:12.046Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-aime-26-pass-at-1-accuracy-standard-error2026-06-04T10:14:12.025Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-aime25-pass-at-1-accuracy-standard-error2026-06-04T10:14:12.005Zhttps://www.sota2.com/research/sota/model-editing-on-kamel-multi-token-targets-n-42026-06-04T10:11:10.876Zhttps://www.sota2.com/research/sota/model-editing-on-kamel-multi-token-targets-n-32026-06-04T10:11:10.861Zhttps://www.sota2.com/research/sota/model-editing-on-kamel-multi-token-targets-n-22026-06-04T10:11:10.842Zhttps://www.sota2.com/research/sota/editing-efficacy-on-kamel-4-tokens2026-06-04T10:11:10.821Zhttps://www.sota2.com/research/sota/editing-efficacy-on-kamel-3-tokens2026-06-04T10:11:10.801Zhttps://www.sota2.com/research/sota/editing-efficacy-on-kamel-2-tokens2026-06-04T10:11:10.782Zhttps://www.sota2.com/research/sota/editing-efficacy-on-kamel-1-token2026-06-04T10:11:10.762Zhttps://www.sota2.com/research/sota/graph-coloring-on-mycielski-c5-3-test2026-06-04T10:11:10.745Zhttps://www.sota2.com/research/sota/graph-coloring-on-kg-9-3-test2026-06-04T10:11:10.727Zhttps://www.sota2.com/research/sota/graph-coloring-on-icosahedral-test2026-06-04T10:11:10.708Zhttps://www.sota2.com/research/sota/graph-coloring-on-petersen-test2026-06-04T10:11:10.691Zhttps://www.sota2.com/research/sota/graph-coloring-on-w_14-test2026-06-04T10:11:10.672Zhttps://www.sota2.com/research/sota/graph-coloring-on-c_31-test2026-06-04T10:11:10.623Zhttps://www.sota2.com/research/sota/graph-coloring-on-c_30-test2026-06-04T10:11:10.603Zhttps://www.sota2.com/research/sota/graph-coloring-on-k_-4-8-test2026-06-04T10:11:10.585Zhttps://www.sota2.com/research/sota/graph-coloring-on-k_10-test2026-06-04T10:11:10.566Zhttps://www.sota2.com/research/sota/style-transfer-on-imgedit-6-styles2026-06-04T10:09:09.798Zhttps://www.sota2.com/research/sota/style-transfer-on-qwen-generated-long-tail-stylized-images-gta-v-minecraft-american-comic-low-poly-3d-voxel-lego2026-06-04T10:09:09.758Zhttps://www.sota2.com/research/sota/multi-task-learning-on-sarcos2026-06-04T10:08:09.485Zhttps://www.sota2.com/research/sota/puzzle-solving-on-puzzle-avg-across-difficulty-levels2026-06-04T10:05:38.802Zhttps://www.sota2.com/research/sota/puzzle-solving-on-puzzle-human-hard2026-06-04T10:05:38.784Zhttps://www.sota2.com/research/sota/puzzle-solving-on-puzzle-human-normal2026-06-04T10:05:38.764Zhttps://www.sota2.com/research/sota/puzzle-solving-on-puzzle-human-easy2026-06-04T10:05:38.743Zhttps://www.sota2.com/research/sota/puzzle-solving-on-puzzle-trivial2026-06-04T10:05:38.722Zhttps://www.sota2.com/research/sota/video-generation-on-egodex2026-06-04T10:03:07.000Zhttps://www.sota2.com/research/sota/multi-document-summarization-on-vims2026-06-04T10:02:36.707Zhttps://www.sota2.com/research/sota/imitation-learning-on-gsrd-out-of-distribution2026-06-04T10:00:04.163Zhttps://www.sota2.com/research/sota/imitation-learning-on-gsrd-initial-conditions2026-06-04T10:00:04.134Zhttps://www.sota2.com/research/sota/non-stationary-online-learning-on-interval-dynamic-regret2026-06-04T09:59:07.195Zhttps://www.sota2.com/research/sota/4d-cardiac-mesh-synthesis-on-uk-biobank2026-06-04T09:59:07.144Zhttps://www.sota2.com/research/sota/live-music-accompaniment-on-live-music-accompaniment-val2026-06-04T09:57:02.328Zhttps://www.sota2.com/research/sota/complete-video-soundtrack-generation-on-v2st-bench2026-06-04T09:46:54.611Zhttps://www.sota2.com/research/sota/text-to-speech-generation-on-tts2026-06-04T09:46:54.568Zhttps://www.sota2.com/research/sota/long-form-generation-on-longfact2026-06-04T09:43:52.691Zhttps://www.sota2.com/research/sota/hallucination-detection-on-factualbio-paragraph-length-biographies2026-06-04T09:43:52.673Zhttps://www.sota2.com/research/sota/choroid-plexus-segmentation-on-extended-dataset-test2026-06-04T09:38:17.719Zhttps://www.sota2.com/research/sota/choroid-plexus-segmentation-on-dataset-test2026-06-04T09:38:17.698Zhttps://www.sota2.com/research/sota/image-attention-modeling-on-mit1003-natural2026-06-04T09:37:16.765Zhttps://www.sota2.com/research/sota/saliency-prediction-on-avad-zero-shot2026-06-04T09:37:16.731Zhttps://www.sota2.com/research/sota/video-attention-modeling-on-video-attention-modeling-general2026-06-04T09:37:16.710Zhttps://www.sota2.com/research/sota/motion-style-transfer-on-16-converted-actions-test2026-06-04T09:33:46.075Zhttps://www.sota2.com/research/sota/ciphertext-sobel-operator-computation-on-image-size-648-x-20402026-06-04T09:32:15.440Zhttps://www.sota2.com/research/sota/step-level-failure-attribution-on-who-and-when-hc2026-06-04T09:28:58.494Zhttps://www.sota2.com/research/sota/step-level-failure-attribution-on-who-and-when-alg2026-06-04T09:28:58.467Zhttps://www.sota2.com/research/sota/long-term-memory-question-answering-on-locomo-overall2026-06-04T09:28:58.319Zhttps://www.sota2.com/research/sota/lesion-localization-on-chestx-ray142026-06-04T09:24:08.871Zhttps://www.sota2.com/research/sota/lesion-localization-on-ms-cxr2026-06-04T09:24:08.848Zhttps://www.sota2.com/research/sota/flip-cube-on-expert-manipulation-trials2026-06-04T09:12:00.261Zhttps://www.sota2.com/research/sota/code-generation-on-humaneval-performance-metrics2026-06-04T09:12:00.242Zhttps://www.sota2.com/research/sota/reasoning-on-bbh-score-tps-flops2026-06-04T09:12:00.223Zhttps://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-throughput-and-score2026-06-04T09:12:00.201Zhttps://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-pro-throughput-and-efficiency2026-06-04T09:12:00.181Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-math-tps-flops-score2026-06-04T09:12:00.161Zhttps://www.sota2.com/research/sota/science-question-answering-on-gpqa-tps-flops-score2026-06-04T09:12:00.136Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-throughput-and-flops2026-06-04T09:12:00.114Zhttps://www.sota2.com/research/sota/code-generation-on-humaneval-tps-speed-score2026-06-04T09:12:00.096Zhttps://www.sota2.com/research/sota/general-language-understanding-on-mmlu-tps-speed-score2026-06-04T09:12:00.077Zhttps://www.sota2.com/research/sota/mathematics-and-science-question-answering-on-gpqa2026-06-04T09:12:00.057Zhttps://www.sota2.com/research/sota/long-context-language-understanding-on-longbench-specific-metric-selection2026-06-04T09:12:00.039Zhttps://www.sota2.com/research/sota/graduate-level-question-answering-on-gpqa-score2026-06-04T09:11:59.996Zhttps://www.sota2.com/research/sota/code-generation-on-humaneval-tps-flops-score2026-06-04T09:11:59.978Zhttps://www.sota2.com/research/sota/code-generation-on-mbpp-tps-flops-score2026-06-04T09:11:59.957Zhttps://www.sota2.com/research/sota/efficiency-metrics-on-big-bench-hard-reasoning-bbh2026-06-04T09:11:59.935Zhttps://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-throughput-and-efficiency2026-06-04T09:11:59.913Zhttps://www.sota2.com/research/sota/multi-task-language-understanding-on-mmlu-pro-performance-tps-flops2026-06-04T09:11:59.890Zhttps://www.sota2.com/research/sota/mathematical-problem-solving-on-math-throughput-and-computational-load2026-06-04T09:11:59.868Zhttps://www.sota2.com/research/sota/graduate-level-science-q-and-a-on-gpqa-tps-score2026-06-04T09:11:59.847Zhttps://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-throughput-and-flops-efficiency2026-06-04T09:11:59.830Z