<?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/consolidated-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/multi-domain-evaluation-suite</loc></url><url><loc>https://www.sota2.com/research/dataset/mechanistic-interpretability-benchmark</loc></url><url><loc>https://www.sota2.com/research/dataset/peerqa</loc></url><url><loc>https://www.sota2.com/research/dataset/frontiersci</loc></url><url><loc>https://www.sota2.com/research/dataset/wenetspeech-yue</loc></url><url><loc>https://www.sota2.com/research/dataset/mfa</loc></url><url><loc>https://www.sota2.com/research/dataset/mir</loc></url><url><loc>https://www.sota2.com/research/dataset/sphinx</loc></url><url><loc>https://www.sota2.com/research/dataset/proofpile</loc></url><url><loc>https://www.sota2.com/research/dataset/rarearena</loc></url><url><loc>https://www.sota2.com/research/dataset/room-occupancy</loc></url><url><loc>https://www.sota2.com/research/dataset/nlu-plus-plus</loc></url><url><loc>https://www.sota2.com/research/dataset/verb</loc></url><url><loc>https://www.sota2.com/research/dataset/phi-4</loc></url><url><loc>https://www.sota2.com/research/dataset/wildg</loc></url><url><loc>https://www.sota2.com/research/dataset/pride-and-prejudice</loc></url><url><loc>https://www.sota2.com/research/dataset/infographics</loc></url><url><loc>https://www.sota2.com/research/dataset/search-r1</loc></url><url><loc>https://www.sota2.com/research/dataset/futureomni</loc></url><url><loc>https://www.sota2.com/research/dataset/multi-turn</loc></url><url><loc>https://www.sota2.com/research/dataset/s-and-p</loc></url><url><loc>https://www.sota2.com/research/dataset/triqa</loc></url><url><loc>https://www.sota2.com/research/dataset/talkmoves</loc></url><url><loc>https://www.sota2.com/research/dataset/conditionalqa</loc></url><url><loc>https://www.sota2.com/research/dataset/frtr-bench</loc></url><url><loc>https://www.sota2.com/research/dataset/spreadsheetllm</loc></url><url><loc>https://www.sota2.com/research/dataset/hipe</loc></url><url><loc>https://www.sota2.com/research/dataset/open-platypus</loc></url><url><loc>https://www.sota2.com/research/dataset/tiage</loc></url><url><loc>https://www.sota2.com/research/dataset/head-qa</loc></url><url><loc>https://www.sota2.com/research/dataset/common</loc></url><url><loc>https://www.sota2.com/research/dataset/suzhou</loc></url><url><loc>https://www.sota2.com/research/dataset/crm</loc></url><url><loc>https://www.sota2.com/research/dataset/infographic-vqa</loc></url><url><loc>https://www.sota2.com/research/dataset/knowledge-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/reasoning-datasets</loc></url><url><loc>https://www.sota2.com/research/dataset/knowledge-suite</loc></url><url><loc>https://www.sota2.com/research/dataset/1bw</loc></url><url><loc>https://www.sota2.com/research/dataset/kobest</loc></url><url><loc>https://www.sota2.com/research/dataset/mimic-bhc</loc></url><url><loc>https://www.sota2.com/research/dataset/polish-board-certification-examinations</loc></url><url><loc>https://www.sota2.com/research/dataset/fineval</loc></url><url><loc>https://www.sota2.com/research/dataset/mandarin-minority</loc></url><url><loc>https://www.sota2.com/research/dataset/anes</loc></url><url><loc>https://www.sota2.com/research/dataset/arena-human-preference</loc></url><url><loc>https://www.sota2.com/research/dataset/cot-collection</loc></url><url><loc>https://www.sota2.com/research/dataset/aegissafety</loc></url><url><loc>https://www.sota2.com/research/dataset/ultraeval-audio</loc></url><url><loc>https://www.sota2.com/research/dataset/colbench</loc></url><url><loc>https://www.sota2.com/research/dataset/caco2</loc></url><url><loc>https://www.sota2.com/research/dataset/short-sequence</loc></url><url><loc>https://www.sota2.com/research/dataset/predex</loc></url><url><loc>https://www.sota2.com/research/dataset/fate</loc></url><url><loc>https://www.sota2.com/research/dataset/alice-in-wonderland</loc></url><url><loc>https://www.sota2.com/research/dataset/bcs</loc></url><url><loc>https://www.sota2.com/research/dataset/litqa</loc></url><url><loc>https://www.sota2.com/research/dataset/lcb-pro</loc></url><url><loc>https://www.sota2.com/research/dataset/text-generation</loc></url><url><loc>https://www.sota2.com/research/dataset/bg</loc></url><url><loc>https://www.sota2.com/research/dataset/ko</loc></url><url><loc>https://www.sota2.com/research/dataset/mas</loc></url><url><loc>https://www.sota2.com/research/dataset/bank77</loc></url><url><loc>https://www.sota2.com/research/dataset/english-corpus</loc></url><url><loc>https://www.sota2.com/research/dataset/math-domain-reasoning-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/general-domain-reasoning-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/tool-decathlon</loc></url><url><loc>https://www.sota2.com/research/dataset/game24</loc></url><url><loc>https://www.sota2.com/research/dataset/structqa</loc></url><url><loc>https://www.sota2.com/research/dataset/pokemon-blip-captions</loc></url><url><loc>https://www.sota2.com/research/dataset/commonsense-reasoning-tasks</loc></url><url><loc>https://www.sota2.com/research/dataset/acp</loc></url><url><loc>https://www.sota2.com/research/dataset/apt-reports</loc></url><url><loc>https://www.sota2.com/research/dataset/dilithium</loc></url><url><loc>https://www.sota2.com/research/dataset/lvlm-evaluation-set</loc></url><url><loc>https://www.sota2.com/research/dataset/kimi-vl</loc></url><url><loc>https://www.sota2.com/research/dataset/grpc</loc></url><url><loc>https://www.sota2.com/research/dataset/postgresql</loc></url><url><loc>https://www.sota2.com/research/dataset/github-issue-reports</loc></url><url><loc>https://www.sota2.com/research/dataset/nlp-benchmarks</loc></url><url><loc>https://www.sota2.com/research/dataset/cti-bench</loc></url><url><loc>https://www.sota2.com/research/dataset/fp_add</loc></url><url><loc>https://www.sota2.com/research/dataset/secenclave</loc></url><url><loc>https://www.sota2.com/research/dataset/sodor</loc></url><url><loc>https://www.sota2.com/research/dataset/sql-create-context</loc></url><url><loc>https://www.sota2.com/research/dataset/lanl</loc></url><url><loc>https://www.sota2.com/research/dataset/tele-eval</loc></url><url><loc>https://www.sota2.com/research/dataset/llmail-inject</loc></url><url><loc>https://www.sota2.com/research/dataset/mira</loc></url><url><loc>https://www.sota2.com/research/dataset/jailbench</loc></url><url><loc>https://www.sota2.com/research/dataset/attacks</loc></url><url><loc>https://www.sota2.com/research/dataset/piibench</loc></url><url><loc>https://www.sota2.com/research/dataset/production-traffic</loc></url><url><loc>https://www.sota2.com/research/dataset/phi-3</loc></url><url><loc>https://www.sota2.com/research/dataset/cwe</loc></url><url><loc>https://www.sota2.com/research/dataset/dnrti</loc></url><url><loc>https://www.sota2.com/research/dataset/fsm</loc></url><url><loc>https://www.sota2.com/research/dataset/b14</loc></url><url><loc>https://www.sota2.com/research/dataset/alto</loc></url><url><loc>https://www.sota2.com/research/dataset/deepseek-llm</loc></url></urlset>