<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-latency-and-throughput</loc><lastmod>2026-02-26T06:06:24.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/atari-game-playing-on-atari-33-seen-games</loc><lastmod>2026-02-26T05:45:51.596Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/floorplan-generation-on-human-expert-user-study</loc><lastmod>2026-02-26T06:07:55.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mit-states-filtered-to-97-classes-test</loc><lastmod>2026-02-26T05:58:30.497Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-ag-news-aapd-imdb-yelp-test</loc><lastmod>2026-02-26T05:58:30.478Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-driving-on-robodrivebench-prompt-corruption-1-0-test</loc><lastmod>2026-02-26T05:36:13.570Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autonomous-driving-on-robodrivebench</loc><lastmod>2026-02-26T05:36:42.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relevance-ranking-on-ms-marco-kendall-s-tau</loc><lastmod>2026-02-26T05:47:52.886Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-opinsummeval</loc><lastmod>2026-02-26T05:47:52.720Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-relevance-on-dialsummeval</loc><lastmod>2026-02-26T05:47:52.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-relevance-on-overall</loc><lastmod>2026-02-26T05:47:52.686Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-groundedness-on-unisumeval</loc><lastmod>2026-02-26T05:47:52.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-groundedness-on-tl-dr</loc><lastmod>2026-02-26T05:47:52.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-groundedness-on-summeval</loc><lastmod>2026-02-26T05:47:52.636Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-groundedness-on-overall</loc><lastmod>2026-02-26T05:47:52.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-completeness-on-unisumeval</loc><lastmod>2026-02-26T05:47:52.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-completeness-on-tl-dr</loc><lastmod>2026-02-26T05:47:52.587Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-completeness-on-overall</loc><lastmod>2026-02-26T05:47:52.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/flowchart-to-mermaid-code-translation-on-flowvqa-test</loc><lastmod>2026-02-26T05:42:05.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/flowchart-to-mermaid-translation-on-flowvqa-subset</loc><lastmod>2026-02-26T06:02:44.116Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stroke-outcome-prediction-on-stroke-outcome-prediction-dataset</loc><lastmod>2026-02-26T05:49:09.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cr-label-prediction-on-medic</loc><lastmod>2026-02-26T05:30:48.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/er-label-prediction-on-medic</loc><lastmod>2026-02-26T05:30:48.749Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ee-label-prediction-on-medic</loc><lastmod>2026-02-26T05:30:48.736Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stock-price-movement-prediction-on-hygon</loc><lastmod>2026-02-26T05:30:48.633Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stock-price-movement-prediction-on-cambricon</loc><lastmod>2026-02-26T05:30:48.620Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stock-price-movement-prediction-on-industrial-fulian</loc><lastmod>2026-02-26T05:30:48.607Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stock-price-movement-prediction-on-iflytek</loc><lastmod>2026-02-26T05:30:48.594Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-paper-to-code-reproduction-on-paper2codebench-2024</loc><lastmod>2026-02-26T06:04:05.682Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-reasoning-on-sugarcrepe</loc><lastmod>2026-02-26T05:30:48.552Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-reasoning-on-countercurate</loc><lastmod>2026-02-26T05:30:48.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/3d-spatial-reasoning-on-cv-bench-3d-full</loc><lastmod>2026-02-26T05:30:48.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/2d-spatial-reasoning-on-cv-bench-full</loc><lastmod>2026-02-26T05:30:48.510Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-reasoning-on-blink-full</loc><lastmod>2026-02-26T05:30:48.481Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-bin-packing-problem-on-offline-bpp-n-700</loc><lastmod>2026-02-26T05:54:11.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multidimensional-knapsack-problem-on-mkp-n-500</loc><lastmod>2026-02-26T05:54:11.687Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/capacitated-vehicle-routing-problem-on-cvrp-n-50</loc><lastmod>2026-02-26T05:54:11.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/orienteering-problem-on-op-n-100</loc><lastmod>2026-02-26T05:54:11.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/traveling-salesman-problem-on-tsp-n-50</loc><lastmod>2026-02-26T05:54:11.639Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-vision-reasoning-on-text-vision-benchmark-all-1-0-test</loc><lastmod>2026-02-26T05:57:32.371Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-vision-reasoning-on-text-vision-benchmark-l5-1-0-test</loc><lastmod>2026-02-26T05:57:33.357Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-vision-reasoning-on-text-vision-benchmark-l4-1-0-test</loc><lastmod>2026-02-26T05:57:33.337Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-vision-reasoning-on-text-vision-benchmark-l3-1-0-test</loc><lastmod>2026-02-26T05:57:33.313Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-vision-reasoning-on-text-vision-benchmark-l2-1-0-test</loc><lastmod>2026-02-26T05:57:33.291Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-vision-reasoning-on-text-vision-benchmark-l1-1-0-test</loc><lastmod>2026-02-26T05:57:33.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-text-only-adaptive-benchmark-all</loc><lastmod>2026-02-26T05:57:32.323Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-text-only-adaptive-benchmark-l5</loc><lastmod>2026-02-26T05:57:33.130Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-text-only-adaptive-benchmark-l4</loc><lastmod>2026-02-26T05:57:33.109Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-text-only-adaptive-benchmark-l3</loc><lastmod>2026-02-26T05:57:33.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-adaptive-benchmark-text-only-l2</loc><lastmod>2026-02-26T05:57:32.304Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-text-only-adaptive-benchmark-l1</loc><lastmod>2026-02-26T05:57:33.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-date-extraction-on-expert-labeled-gold-standard-dataset</loc><lastmod>2026-02-26T05:58:30.391Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-occurrence-extraction-on-expert-labeled-gold-standard-dataset</loc><lastmod>2026-02-26T05:58:30.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-pass-at-16-avg-at-16</loc><lastmod>2026-02-26T05:36:30.565Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cuda-code-validation-on-kernelbench-level-1</loc><lastmod>2026-02-26T06:05:42.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/value-recognition-on-value-assessment-scenarios</loc><lastmod>2026-02-26T05:36:33.491Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lora-retrieval-on-custom-lora-retrieval-benchmark</loc><lastmod>2026-02-26T06:04:21.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fault-assessment-efficiency-on-mmlu-mmlu-pro-workloads</loc><lastmod>2026-02-26T05:40:02.189Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-agriregion-eval-160-questions-test</loc><lastmod>2026-02-26T05:41:37.277Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-fashion-mnist</loc><lastmod>2026-02-26T05:24:49.881Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-mnist</loc><lastmod>2026-02-26T05:24:49.859Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-reasoning-on-out-of-domain-ood-aggregate-hallubench-mathvista-mathverse-mathvision</loc><lastmod>2026-02-26T05:54:05.573Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-reasoning-on-geometry3k-test</loc><lastmod>2026-03-25T13:41:00.381Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-reasoning-on-mm-eureka</loc><lastmod>2026-02-26T05:30:47.901Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-quality-assessment-on-face-dataset</loc><lastmod>2026-02-26T05:37:25.825Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/identity-transformation-on-randomly-sampled-protect-target-face-pairs-test</loc><lastmod>2026-02-26T05:46:56.290Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-100-test-accuracy-macs-and-utilization</loc><lastmod>2026-02-26T05:30:47.640Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-llama-2-70b-sequence-length-2048</loc><lastmod>2026-02-26T05:51:40.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-medical-reasoning-on-curemed-bench-averaged-across-13-languages</loc><lastmod>2026-02-26T05:48:24.298Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/red-teaming-on-harmbench-claude-sonnet-3-5-held-out-test</loc><lastmod>2026-02-26T05:23:51.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/red-teaming-on-harmbench-llama-3-8b-test</loc><lastmod>2026-02-26T05:23:51.583Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/red-teaming-on-harmbench-llama-2-7b-test</loc><lastmod>2026-02-26T05:23:51.424Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-topdown</loc><lastmod>2026-02-26T05:43:30.118Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-tinycars</loc><lastmod>2026-02-26T05:43:30.102Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-solid</loc><lastmod>2026-02-26T05:43:30.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-shootout</loc><lastmod>2026-02-26T05:43:30.064Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-run-n-gun</loc><lastmod>2026-02-26T05:43:30.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-pirates</loc><lastmod>2026-02-26T05:43:30.032Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-heist</loc><lastmod>2026-02-26T05:43:30.020Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-endless</loc><lastmod>2026-02-26T05:43:30.005Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/game-performance-evaluation-on-apex</loc><lastmod>2026-02-26T05:43:29.986Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/formal-theorem-proving-on-putnam-2025</loc><lastmod>2026-06-05T10:17:58.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-extraction-attack-on-agriculture-lightrag-1-0-test</loc><lastmod>2026-02-26T05:48:34.077Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-extraction-attack-on-agriculture-m-graphrag-1-0-test</loc><lastmod>2026-02-26T05:48:34.059Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/loading-and-reasoning-on-owl2bench-raw</loc><lastmod>2026-02-26T05:48:38.838Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-w-1</loc><lastmod>2026-02-26T05:58:30.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-w</loc><lastmod>2026-02-26T05:58:30.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-n-0-1</loc><lastmod>2026-02-26T05:58:30.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/link-prediction-on-i</loc><lastmod>2026-02-26T05:58:30.094Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/routing-on-ema-150</loc><lastmod>2026-02-26T06:04:28.048Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/routing-on-ema-100</loc><lastmod>2026-02-26T06:04:28.033Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/routing-on-ema-50</loc><lastmod>2026-02-26T06:04:28.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vehicle-routing-on-euclidean-routing-networks-en-100-deterministic</loc><lastmod>2026-02-26T05:40:08.705Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vehicle-routing-on-euclidean-routing-networks-en-50-deterministic</loc><lastmod>2026-02-26T05:40:08.689Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomass-prediction-on-winter-wheat-irrigated-treatment</loc><lastmod>2026-02-26T06:00:18.677Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomass-prediction-on-winter-wheat-rainfed-treatment</loc><lastmod>2026-02-26T06:00:18.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomass-prediction-on-winter-wheat-shelter-treatment</loc><lastmod>2026-02-26T06:00:18.644Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-hard-v5</loc><lastmod>2026-02-26T05:57:23.693Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-memory-on-msc</loc><lastmod>2026-02-26T06:00:45.636Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memory-retention-analysis-on-lti-bench</loc><lastmod>2026-02-26T05:40:06.004Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/energy-consumption-prediction-on-melbourne-water-eastern-treatment-plant-test</loc><lastmod>2026-02-26T05:50:52.942Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-performance-evaluation-on-cybersecurity</loc><lastmod>2026-02-26T05:35:50.377Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-performance-evaluation-on-data-analysis</loc><lastmod>2026-02-26T05:36:23.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-performance-evaluation-on-software-engineering</loc><lastmod>2026-02-26T05:35:50.347Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/db-routing-on-spider-route</loc><lastmod>2026-02-26T05:59:29.648Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/db-routing-on-bird-route</loc><lastmod>2026-02-26T05:59:29.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-human-evaluation-in-distribution</loc><lastmod>2026-02-26T06:08:57.871Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-visual-instruction-out-of-distribution-hard-test</loc><lastmod>2026-02-26T06:08:57.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-visual-instruction-out-of-distribution-simple-test</loc><lastmod>2026-02-26T05:46:43.484Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-visual-instruction-out-of-distribution-test</loc><lastmod>2026-02-26T05:46:43.469Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-visual-instruction-in-distribution-hard-test</loc><lastmod>2026-02-26T05:46:43.452Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-visual-instruction-in-distribution-simple-test</loc><lastmod>2026-02-26T05:46:43.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-visual-instruction-in-distribution-test</loc><lastmod>2026-02-26T05:46:43.417Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-action-prediction-on-ecg-mtd-lead-ii-test</loc><lastmod>2026-02-26T05:53:01.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-action-prediction-on-ecg-mtd-lead-i-test</loc><lastmod>2026-02-26T05:53:01.148Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-action-prediction-on-ecg-mtd-12-leads-test</loc><lastmod>2026-02-26T05:53:01.132Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knapsack-problem-on-kp-n-50-w-12-5-test</loc><lastmod>2026-02-26T05:54:11.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/orienteering-problem-on-op-n-500-standard-test</loc><lastmod>2026-02-26T05:54:11.413Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/orienteering-problem-on-op-n-100-standard-test</loc><lastmod>2026-02-26T05:54:11.398Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multidimensional-knapsack-problem-on-mkp-n-1000-m-5-test</loc><lastmod>2026-02-26T05:54:11.381Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multidimensional-knapsack-problem-on-mkp-n-500-m-5-test</loc><lastmod>2026-02-26T05:54:11.366Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multidimensional-knapsack-problem-on-mkp-n-300-m-5-test</loc><lastmod>2026-02-26T05:54:11.349Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-top-5-percent-most-uncertain-tokens-test</loc><lastmod>2026-02-26T05:53:15.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-top-5-percent-most-uncertain-tokens-val</loc><lastmod>2026-02-26T05:53:15.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-all-tokens-test</loc><lastmod>2026-02-26T05:53:15.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-wikitext-2-all-tokens-val</loc><lastmod>2026-02-26T05:53:15.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mountain-car-on-mountain-car</loc><lastmod>2026-02-26T05:54:11.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reinforcement-learning-on-mountain-car-v0</loc><lastmod>2026-02-26T06:04:47.834Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimization-modeling-on-mamo-complex-standard</loc><lastmod>2026-02-26T05:30:44.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimization-modeling-on-industryor-standard</loc><lastmod>2026-02-26T05:30:44.814Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimization-modeling-on-optibench-standard</loc><lastmod>2026-02-26T05:30:44.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-learning-engineering-on-mle-bench-all</loc><lastmod>2026-02-26T05:52:29.160Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-learning-engineering-on-mle-bench-hard</loc><lastmod>2026-02-26T05:52:29.142Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-learning-engineering-on-mle-bench-medium</loc><lastmod>2026-02-26T05:52:29.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-learning-engineering-on-mle-bench-low</loc><lastmod>2026-02-26T05:52:29.111Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/statistical-downscaling-on-mpi-hr-real-gcm</loc><lastmod>2026-02-26T05:49:09.764Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/statistical-downscaling-on-mpi-lr-real-gcm</loc><lastmod>2026-02-26T05:49:09.741Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/statistical-downscaling-on-awi-real-gcm</loc><lastmod>2026-02-26T05:49:09.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/statistical-downscaling-on-miroc6-real-gcm</loc><lastmod>2026-02-26T05:49:09.711Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tabular-data-classification-on-48-openml-tabular-datasets</loc><lastmod>2026-02-26T05:52:29.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-wikitq-bleu-rouge-l</loc><lastmod>2026-02-26T05:37:00.385Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medquad-style-complete-benchmark</loc><lastmod>2026-02-26T05:52:28.982Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-task-expansion-on-alfworld-unseen-domains</loc><lastmod>2026-02-26T06:03:04.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-task-expansion-on-alfworld-unseen-domains-5-shot</loc><lastmod>2026-02-26T06:05:08.454Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-task-expansion-on-alfworld-1-shot-unseen-domains</loc><lastmod>2026-02-26T06:05:39.770Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-task-expansion-on-virtualhome-average-performance-unseen-domains</loc><lastmod>2026-02-26T06:03:04.834Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-task-expansion-on-virtualhome-unseen-domains-5-shot</loc><lastmod>2026-02-26T06:05:08.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-task-expansion-on-virtualhome-unseen-domains-1-shot</loc><lastmod>2026-02-26T06:03:04.815Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-evaluation-on-cybersecurity-benchmarks-cti-mcq-cybermetric-seceval-test</loc><lastmod>2026-02-26T05:38:52.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-reasoning-over-optical-sar-imagery-on-thinkgeo</loc><lastmod>2026-02-26T05:57:46.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-utterance-prediction-on-saynext-pc19k</loc><lastmod>2026-02-27T10:38:50.132Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-utterance-prediction-on-saynext-pc19k-test</loc><lastmod>2026-02-27T10:38:50.190Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-model-debiasing-on-seat</loc><lastmod>2026-02-26T05:45:55.895Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-model-debiasing-on-stereoset-test</loc><lastmod>2026-02-26T05:48:10.586Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/poker-gameplay-performance-on-limit-texas-hold-em</loc><lastmod>2026-02-26T05:53:10.345Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/poker-gameplay-performance-on-leduc-hold-em</loc><lastmod>2026-02-26T05:53:10.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geomagnetic-map-interpolation-on-b-int</loc><lastmod>2026-02-27T10:37:49.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-evaluation-on-overall-knowledge-aggregation-aggregate</loc><lastmod>2026-02-26T05:47:03.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-overall-hallucination-aggregation</loc><lastmod>2026-02-26T05:47:03.007Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-argilla-7k-test</loc><lastmod>2026-02-26T05:48:05.640Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/health-prediction-on-health-prediction-tasks-test</loc><lastmod>2026-02-26T06:05:49.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-t14</loc><lastmod>2026-02-26T05:30:43.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-t13</loc><lastmod>2026-02-26T05:30:43.838Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-t12</loc><lastmod>2026-02-26T05:49:09.623Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-t4</loc><lastmod>2026-02-26T06:00:19.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-execution-on-autohealth-medical-benchmark-suite-tasks-t1-t17</loc><lastmod>2026-02-26T06:05:49.526Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-execution-on-health-benchmark</loc><lastmod>2026-02-26T06:05:49.410Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-model-selection-on-21-datasets-few-shot</loc><lastmod>2026-02-26T05:53:07.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-30-events-prediction-on-kasteren-c</loc><lastmod>2026-02-26T05:42:56.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-30-events-prediction-on-casas-milan</loc><lastmod>2026-02-26T05:42:56.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/desktop-operating-system-task-execution-on-osworld</loc><lastmod>2026-02-26T05:26:27.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-interaction-on-osworld-w-o-loop</loc><lastmod>2026-02-26T05:26:27.843Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-interaction-on-osworld-w-loop</loc><lastmod>2026-02-26T05:26:27.822Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-babilong-128k-context-length</loc><lastmod>2026-02-26T05:59:05.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-babilong-64k-context-length</loc><lastmod>2026-02-26T05:59:05.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-reasoning-on-babi-task-1-qa1-50-samples</loc><lastmod>2026-02-26T05:30:43.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-commonsense-reasoning-on-strategyqa-sampled-50-val</loc><lastmod>2026-02-26T05:30:43.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grade-school-mathematics-reasoning-on-gsm8k-sampled-50-test</loc><lastmod>2026-02-26T05:30:43.357Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-agent-on-aggregated-rebencht-codeci-bird</loc><lastmod>2026-02-26T05:54:28.667Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-agent-on-bird</loc><lastmod>2026-02-26T05:57:23.144Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-agent-on-codeci</loc><lastmod>2026-02-26T05:36:31.185Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-agent-on-rebencht</loc><lastmod>2026-02-26T05:54:04.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-illustration-generation-on-figurebench-textbook</loc><lastmod>2026-02-26T05:34:43.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-illustration-generation-on-figurebench-survey</loc><lastmod>2026-02-26T05:34:44.341Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-illustration-generation-on-figurebench-blog</loc><lastmod>2026-02-26T05:34:44.325Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biology-on-single-cell-analysis-denoising</loc><lastmod>2026-04-23T08:39:53.313Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ai-capability-progress-modeling-on-metr-experiment-data-h_model</loc><lastmod>2026-02-26T05:50:52.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-on-atari-pacman</loc><lastmod>2026-02-26T06:02:12.990Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-prism-1-0-test</loc><lastmod>2026-02-26T05:37:54.032Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-prism-normalized-step-test</loc><lastmod>2026-02-26T05:37:54.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-15-000-listwise-rankings-test</loc><lastmod>2026-02-26T05:37:26.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-prism-1-0-full</loc><lastmod>2026-02-26T05:37:54.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sensitivity-to-logical-boundaries-on-questbench</loc><lastmod>2026-02-26T05:48:44.873Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-selection-ranking-on-100-problem-mini-activation-set-held-out</loc><lastmod>2026-02-26T05:57:44.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-spots-mouse-spleen</loc><lastmod>2026-02-26T05:53:24.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-human-lymph-node-dataset-10x-genomics-visium</loc><lastmod>2026-02-26T05:53:24.072Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-mouse-thymus-stereo-cite-seq-downstream</loc><lastmod>2026-02-26T05:53:24.059Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-protein-expression-prediction-on-human-lymph-node-dataset</loc><lastmod>2026-02-26T06:00:00.639Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-protein-expression-prediction-on-mouse-thymus-dataset</loc><lastmod>2026-02-26T06:00:00.623Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spatial-protein-expression-prediction-on-mouse-spleen-dataset</loc><lastmod>2026-02-26T06:00:00.608Z</lastmod></url></urlset>