<?xml version="1.0" encoding="UTF-8"?><urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"><url><loc>https://www.sota2.com/research/dataset/expertmath</loc></url><url><loc>https://www.sota2.com/research/dataset/improofbench</loc></url><url><loc>https://www.sota2.com/research/dataset/frontiermath</loc></url><url><loc>https://www.sota2.com/research/dataset/asvp-esd</loc></url><url><loc>https://www.sota2.com/research/dataset/benchmarker</loc></url><url><loc>https://www.sota2.com/research/dataset/social-interaction-simulation</loc></url><url><loc>https://www.sota2.com/research/dataset/role-playing-evaluation</loc></url><url><loc>https://www.sota2.com/research/dataset/role-playing-artifacts</loc></url><url><loc>https://www.sota2.com/research/dataset/average-squad-newsqa-triviaqa-nq-hotpotqa</loc></url><url><loc>https://www.sota2.com/research/dataset/mmlu-prox</loc></url><url><loc>https://www.sota2.com/research/dataset/malaymmlu</loc></url><url><loc>https://www.sota2.com/research/dataset/gmeg-data</loc></url><url><loc>https://www.sota2.com/research/dataset/ax-b</loc></url><url><loc>https://www.sota2.com/research/dataset/ax-g</loc></url><url><loc>https://www.sota2.com/research/dataset/bench-proxy</loc></url><url><loc>https://www.sota2.com/research/dataset/logiccat</loc></url><url><loc>https://www.sota2.com/research/dataset/com-2</loc></url><url><loc>https://www.sota2.com/research/dataset/audiobench</loc></url><url><loc>https://www.sota2.com/research/dataset/dyck</loc></url><url><loc>https://www.sota2.com/research/dataset/video-salmonn</loc></url><url><loc>https://www.sota2.com/research/dataset/forum-dataset</loc></url><url><loc>https://www.sota2.com/research/dataset/precisewikiqa</loc></url><url><loc>https://www.sota2.com/research/dataset/mmcu</loc></url><url><loc>https://www.sota2.com/research/dataset/visualpuzzle</loc></url><url><loc>https://www.sota2.com/research/dataset/vlmareblind</loc></url><url><loc>https://www.sota2.com/research/dataset/prompt-optimization-benchmark</loc></url><url><loc>https://www.sota2.com/research/dataset/polyguard-cyber</loc></url><url><loc>https://www.sota2.com/research/dataset/sequential-cl-tasks</loc></url><url><loc>https://www.sota2.com/research/dataset/upstream-tasks</loc></url><url><loc>https://www.sota2.com/research/dataset/reading-paradigm-data</loc></url><url><loc>https://www.sota2.com/research/dataset/grec</loc></url><url><loc>https://www.sota2.com/research/dataset/russian-bashkir</loc></url><url><loc>https://www.sota2.com/research/dataset/russian-kazakh</loc></url><url><loc>https://www.sota2.com/research/dataset/russian-kyrgyz</loc></url><url><loc>https://www.sota2.com/research/dataset/english-tatar</loc></url><url><loc>https://www.sota2.com/research/dataset/english-chuvash</loc></url><url><loc>https://www.sota2.com/research/dataset/open-ended-generation-tasks</loc></url><url><loc>https://www.sota2.com/research/dataset/boolq-copa-winog-svamp-mawps</loc></url><url><loc>https://www.sota2.com/research/dataset/open-generation</loc></url><url><loc>https://www.sota2.com/research/dataset/ecg-grounding</loc></url><url><loc>https://www.sota2.com/research/dataset/cardiologist-evaluation</loc></url><url><loc>https://www.sota2.com/research/dataset/taiwanese-criminal-case</loc></url><url><loc>https://www.sota2.com/research/dataset/askmind</loc></url><url><loc>https://www.sota2.com/research/dataset/askoverconfidence</loc></url><url><loc>https://www.sota2.com/research/dataset/numinaproof</loc></url><url><loc>https://www.sota2.com/research/dataset/instructor</loc></url><url><loc>https://www.sota2.com/research/dataset/aime-hmmt</loc></url><url><loc>https://www.sota2.com/research/dataset/mcq-quality-assessment-dataset</loc></url><url><loc>https://www.sota2.com/research/dataset/reading-comprehension-mcq-dataset</loc></url><url><loc>https://www.sota2.com/research/dataset/tools-and-home-improvement</loc></url><url><loc>https://www.sota2.com/research/dataset/productbench</loc></url><url><loc>https://www.sota2.com/research/dataset/mixed-dataset-nq-popqa-hotpotqa-2wiki</loc></url><url><loc>https://www.sota2.com/research/dataset/service-dialogue-scenarios</loc></url><url><loc>https://www.sota2.com/research/dataset/nl-aave</loc></url><url><loc>https://www.sota2.com/research/dataset/gaia-text-103</loc></url><url><loc>https://www.sota2.com/research/dataset/flores200</loc></url><url><loc>https://www.sota2.com/research/dataset/nap</loc></url><url><loc>https://www.sota2.com/research/dataset/privasis</loc></url><url><loc>https://www.sota2.com/research/dataset/privasis-sanitization</loc></url><url><loc>https://www.sota2.com/research/dataset/physicseval</loc></url><url><loc>https://www.sota2.com/research/dataset/zeroshot</loc></url><url><loc>https://www.sota2.com/research/dataset/wikitext-2-ptb-c4</loc></url><url><loc>https://www.sota2.com/research/dataset/arc-winogrande-hellaswag-piqa</loc></url><url><loc>https://www.sota2.com/research/dataset/fava-annotations</loc></url><url><loc>https://www.sota2.com/research/dataset/muse-bench</loc></url><url><loc>https://www.sota2.com/research/dataset/competition-level-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/wikipedia-activations</loc></url><url><loc>https://www.sota2.com/research/dataset/hrls</loc></url><url><loc>https://www.sota2.com/research/dataset/lrls</loc></url><url><loc>https://www.sota2.com/research/dataset/wideseekbench</loc></url><url><loc>https://www.sota2.com/research/dataset/tobacco-pest-and-disease-control</loc></url><url><loc>https://www.sota2.com/research/dataset/opc</loc></url><url><loc>https://www.sota2.com/research/dataset/proof-rm</loc></url><url><loc>https://www.sota2.com/research/dataset/proofbench</loc></url><url><loc>https://www.sota2.com/research/dataset/psychopathy</loc></url><url><loc>https://www.sota2.com/research/dataset/powerseeking</loc></url><url><loc>https://www.sota2.com/research/dataset/math-chat-if-and-general-qa-tasks</loc></url><url><loc>https://www.sota2.com/research/dataset/arabic-script-darja</loc></url><url><loc>https://www.sota2.com/research/dataset/latin-script-darja</loc></url><url><loc>https://www.sota2.com/research/dataset/qwen2-5-7b</loc></url><url><loc>https://www.sota2.com/research/dataset/custom-hebrew-summarization</loc></url><url><loc>https://www.sota2.com/research/dataset/custom-translation-corpus</loc></url><url><loc>https://www.sota2.com/research/dataset/israeli-trivia</loc></url><url><loc>https://www.sota2.com/research/dataset/custom-hebrew-diacritization-corpus</loc></url><url><loc>https://www.sota2.com/research/dataset/chinese-sdg-reports</loc></url><url><loc>https://www.sota2.com/research/dataset/medical-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/evk-bench</loc></url><url><loc>https://www.sota2.com/research/dataset/mcv-accent</loc></url><url><loc>https://www.sota2.com/research/dataset/guideweb</loc></url><url><loc>https://www.sota2.com/research/dataset/python-code-summarization</loc></url><url><loc>https://www.sota2.com/research/dataset/python-code-completion</loc></url><url><loc>https://www.sota2.com/research/dataset/code-clone-detection</loc></url><url><loc>https://www.sota2.com/research/dataset/python-code-question-answering</loc></url><url><loc>https://www.sota2.com/research/dataset/os-harm</loc></url><url><loc>https://www.sota2.com/research/dataset/steering-conditions</loc></url><url><loc>https://www.sota2.com/research/dataset/20q-breeds</loc></url><url><loc>https://www.sota2.com/research/dataset/md-dx</loc></url><url><loc>https://www.sota2.com/research/dataset/ts-flodial</loc></url><url><loc>https://www.sota2.com/research/dataset/codiq-bench</loc></url><url><loc>https://www.sota2.com/research/dataset/competition-level-datasets</loc></url></urlset>