<?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/image-classification-on-cifar-10-distribution-i-label-scarcity-test</loc><lastmod>2026-02-26T05:31:18.202Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/digital-signature-on-nist-pqc-standards</loc><lastmod>2026-05-06T07:34:21.893Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cyberattack-detection-on-tcdr-test</loc><lastmod>2026-02-26T05:40:47.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cohort-analytics-on-cohort-analytics-1-0-evaluation</loc><lastmod>2026-02-26T05:54:42.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-leakage-defense-on-cifar-10</loc><lastmod>2026-06-02T06:51:08.975Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermark-removal-attack-on-ss-in-processing-watermarking-scheme</loc><lastmod>2026-02-26T05:37:49.895Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-gpt-5-1</loc><lastmod>2026-04-21T11:16:53.554Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermark-detectability-on-400-token-texts-paraphrasing-attack-test</loc><lastmod>2026-02-26T05:24:53.395Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-watermarking-on-ljspeech-in-distribution-codec-compression-accuracy</loc><lastmod>2026-02-26T05:50:08.047Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-watermarking-on-ljspeech-in-distribution</loc><lastmod>2026-02-26T05:45:54.000Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-detection-on-cifar-10-imbalanced-0-9-100-test</loc><lastmod>2026-02-26T05:37:29.596Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-detection-on-cifar-10-imbalanced-0-9-2-test</loc><lastmod>2026-02-26T05:37:29.575Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-sample-detection-on-cifar-10-imbalanced-mu-0-9-rho-200-train-test</loc><lastmod>2026-02-26T05:37:29.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-sample-detection-on-cifar-10-imbalanced-mu-0-9-rho-10-train-test</loc><lastmod>2026-02-26T05:37:29.530Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-sample-detection-on-cifar-10-balanced-rho-1-train-test</loc><lastmod>2026-02-26T05:37:29.509Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-dnn-watermarking-on-tiny-imagenet</loc><lastmod>2026-02-26T05:38:12.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-dnn-watermarking-on-cifar-100</loc><lastmod>2026-02-26T05:38:12.503Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-dnn-watermarking-on-cifar-10</loc><lastmod>2026-02-26T05:38:12.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/citation-generation-on-citeverifier-citation-generation</loc><lastmod>2026-02-26T05:47:37.429Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/citation-validity-judgment-on-citation-validity-ground-truth-archival-analysis-1-0-test</loc><lastmod>2026-02-26T06:08:06.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerability-detection-on-primevul-paired-full</loc><lastmod>2026-02-27T10:57:36.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/record-linkage-risk-assessment-on-10-000-records-dataset-test</loc><lastmod>2026-02-26T05:38:53.701Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-imagenet-val-top-1-peak-final</loc><lastmod>2026-02-26T06:07:07.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-semeval-laptop-test</loc><lastmod>2026-02-26T05:31:14.411Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-semeval-restaurant-test</loc><lastmod>2026-02-26T05:31:14.399Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-arc-e-obqa-siqa-arc-c-winog-piqa-boolq-hellas-llama3-8b</loc><lastmod>2026-02-26T05:23:39.290Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-search-relevance-assessment-on-localqsmed-v1-0</loc><lastmod>2026-02-26T05:46:14.722Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-arxiv-march23</loc><lastmod>2026-02-26T06:00:37.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/end-to-end-terminal-tasks-on-terminal-bench-2</loc><lastmod>2026-02-26T06:03:54.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-coding-on-project-dev-test</loc><lastmod>2026-02-26T06:06:08.543Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-mit-test</loc><lastmod>2026-02-26T05:52:57.856Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-function-chart-generation-on-sfc-industrial-dataset</loc><lastmod>2026-02-26T05:45:57.293Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personal-attack-detection-on-personal-attack-detection</loc><lastmod>2026-02-26T05:31:12.026Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toxicity-detection-on-wikipedia-detox</loc><lastmod>2026-02-26T05:31:12.012Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/aggression-detection-on-wikipedia-detox</loc><lastmod>2026-02-26T05:31:11.995Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personality-detection-on-kaggle-4-dimensional-binary-scores</loc><lastmod>2026-02-26T05:46:46.289Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/role-play-generation-on-role-play-generation-ability-evaluation</loc><lastmod>2026-02-26T05:40:15.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-problem-solving-on-hmmt-february-2025-pass-at-1</loc><lastmod>2026-02-26T06:11:15.174Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-crossner-test</loc><lastmod>2026-06-04T12:41:09.851Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-extraction-on-wikievents-test</loc><lastmod>2026-02-26T05:52:48.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/micro-f1-event-extraction-on-rams-test</loc><lastmod>2026-02-26T05:52:48.332Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sparse-knowledge-graph-reasoning-on-wd-singer</loc><lastmod>2026-02-26T05:50:27.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sparse-knowledge-graph-reasoning-on-nell23k</loc><lastmod>2026-02-26T05:50:27.603Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sparse-knowledge-graph-reasoning-on-fb15k-237-50-percent-sparse</loc><lastmod>2026-02-26T05:50:27.590Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-sequence-modeling-on-amazon-review</loc><lastmod>2026-02-26T05:33:57.293Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-sequence-modeling-on-us-earthquake</loc><lastmod>2026-02-26T05:31:10.668Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-sequence-modeling-on-nyc-taxi</loc><lastmod>2026-02-26T05:31:10.656Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-sequence-modeling-on-chicago-crime</loc><lastmod>2026-02-26T05:31:10.641Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-modeling-evaluation-on-helmet-held-out-eval</loc><lastmod>2026-02-26T05:34:03.779Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-ruler-dev</loc><lastmod>2026-02-26T05:34:02.065Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-as-a-judge-robustness-on-sage-hard</loc><lastmod>2026-02-26T05:45:08.520Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-as-a-judge-robustness-on-sage-easy</loc><lastmod>2026-02-26T05:45:08.583Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/refusal-evaluation-on-ccp-sensitive</loc><lastmod>2026-02-26T06:01:50.141Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-reasoning-on-time-dialog-test</loc><lastmod>2026-02-26T05:48:40.377Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stored-household-item-location-prediction-on-stored-household-item-challenge-1-0-dev</loc><lastmod>2026-02-26T05:31:07.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-knowledge-capability-on-fineval</loc><lastmod>2026-02-26T06:03:53.181Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-knowledge-capability-on-financeiq</loc><lastmod>2026-02-26T06:03:53.148Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-knowledge-capability-on-flamecer</loc><lastmod>2026-02-26T06:03:53.133Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-reasoning-and-semantic-understanding-on-voicebench-test</loc><lastmod>2026-02-26T05:34:52.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-essay-scoring-on-asap-kaggle-2-0-test</loc><lastmod>2026-02-26T05:59:08.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-retrieval-on-niah-multi</loc><lastmod>2026-02-26T05:31:05.590Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dementia-prognosis-on-adni</loc><lastmod>2026-02-26T05:31:05.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-question-answering-on-gpqa-accuracy-and-response-length</loc><lastmod>2026-05-12T14:11:55.561Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/error-detection-on-paperaudit-dataset-icml-branch-1-0</loc><lastmod>2026-02-26T05:41:20.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/evidence-retrieval-on-claim-evidence-sets-test</loc><lastmod>2026-02-26T05:49:36.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overstatement-detection-on-claim-evidence-sets</loc><lastmod>2026-02-26T05:38:05.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-generated-text-detection-on-hc3-coling2025-val</loc><lastmod>2026-02-26T05:24:52.678Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-generated-text-detection-on-mage-coling2025-val</loc><lastmod>2026-02-26T05:24:52.650Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-generated-text-detection-on-coling2025-m4gt-val</loc><lastmod>2026-02-26T05:24:52.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-generated-text-detection-on-semeval2024-m4-test</loc><lastmod>2026-02-26T05:24:52.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-document-retrieval-on-visrag</loc><lastmod>2026-03-04T15:57:01.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/entity-linking-on-esco-test</loc><lastmod>2026-02-26T05:31:03.659Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-generation-on-ancient-chinese-cultural-system-1-0-test</loc><lastmod>2026-02-26T05:57:37.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-voicebench</loc><lastmod>2026-02-26T05:50:03.380Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-capability-evaluation-on-acebench-agent</loc><lastmod>2026-02-26T05:52:58.724Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tool-use-on-tau-bench</loc><lastmod>2026-02-26T06:02:09.839Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-uner</loc><lastmod>2026-03-13T09:16:02.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-multiconer-v2</loc><lastmod>2026-02-26T05:51:27.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-multiconer-v1</loc><lastmod>2026-02-26T05:51:27.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-masakhaner</loc><lastmod>2026-02-26T05:51:27.711Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-dynamic-ner</loc><lastmod>2026-05-18T06:25:49.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-msvamp-bangla</loc><lastmod>2026-02-26T05:34:22.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-mgsm-bangla</loc><lastmod>2026-02-26T05:34:22.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/competitive-programming-on-livecodebench-v6-test</loc><lastmod>2026-02-26T06:03:52.380Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ko-ifeval</loc><lastmod>2026-03-20T10:04:57.228Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-countdown-context-lengths-128-256-512</loc><lastmod>2026-05-15T06:39:29.210Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-p-at-1</loc><lastmod>2026-02-26T05:54:45.990Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-p-at-1-and-p-at-32</loc><lastmod>2026-02-26T05:54:45.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-p-at-1-p-at-32</loc><lastmod>2026-02-26T05:54:45.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-nusax-minangkabau-test</loc><lastmod>2026-02-26T05:52:25.280Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-nusax-javanese-jav-test</loc><lastmod>2026-02-26T05:52:25.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-nusax-buginese-bug-test</loc><lastmod>2026-02-26T05:31:01.965Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-nusax-acehnese-ace-test</loc><lastmod>2026-02-26T05:31:01.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-task-on-tau2-telecom</loc><lastmod>2026-02-26T05:31:42.081Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/creative-writing-on-arenahard-creative-writing-v2-0</loc><lastmod>2026-02-26T06:08:41.135Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/creative-writing-on-creative-writing-eq-bench-v3</loc><lastmod>2026-02-26T05:41:31.554Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/theorem-based-question-answering-on-theoremqa</loc><lastmod>2026-05-08T10:47:50.160Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-translation-on-cangjie-bench</loc><lastmod>2026-02-26T05:21:42.289Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-cangjie-bench</loc><lastmod>2026-02-26T05:31:00.050Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-average-amc23-arc-c-gpqa-gsm8k</loc><lastmod>2026-02-26T05:40:38.509Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-acc-length</loc><lastmod>2026-02-26T05:31:00.028Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-arc-c-acc-length</loc><lastmod>2026-02-26T05:30:59.997Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conflict-resolution-on-calconflictbench-1-0-test</loc><lastmod>2026-02-26T05:36:10.151Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/answer-generation-on-coral</loc><lastmod>2026-02-26T05:42:46.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-value-alignment-benchmark-1-0-chinese</loc><lastmod>2026-02-26T06:04:30.757Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pairwise-classification-on-pmr-real-total</loc><lastmod>2026-02-26T05:30:59.152Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pairwise-classification-on-pmr-real-hard</loc><lastmod>2026-02-26T05:30:59.135Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pairwise-classification-on-pmr-real-med</loc><lastmod>2026-02-26T05:30:59.116Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pairwise-classification-on-pmr-real-easy</loc><lastmod>2026-02-26T05:30:59.102Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-diagnostic-reasoning-benchmark-1-0-test</loc><lastmod>2026-02-26T05:46:47.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rationale-generation-on-sst-2-cola-and-hatexplain-test</loc><lastmod>2026-02-26T06:06:25.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-quality-correlation-analysis-on-teacher-generated-reasoning-datasets-average-across-students</loc><lastmod>2026-02-26T06:04:36.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-quality-correlation-analysis-on-teacher-generated-reasoning-datasets-qwen-2-5-3b-student</loc><lastmod>2026-02-26T06:04:36.575Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-quality-correlation-analysis-on-teacher-generated-reasoning-datasets-qwen-3-4b-student</loc><lastmod>2026-02-26T06:04:36.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-quality-correlation-analysis-on-teacher-generated-reasoning-datasets-qwen-2-5-7b-student</loc><lastmod>2026-02-26T06:04:36.561Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-quality-correlation-analysis-on-teacher-generated-reasoning-datasets-llama-3-1-8b-student</loc><lastmod>2026-02-26T06:04:36.544Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-quality-correlation-analysis-on-teacher-generated-reasoning-datasets-qwen-3-14b-student</loc><lastmod>2026-02-26T06:04:36.530Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-acecoder-87k</loc><lastmod>2026-02-26T05:30:58.703Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-subset-of-acecoder-87k</loc><lastmod>2026-02-26T05:30:58.687Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/polymer-science-response-quality-evaluation-on-external-polymer-benchmarks-blk-chemd-llml-1-0-test</loc><lastmod>2026-02-26T05:37:52.448Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trust-game-on-whitt-2021</loc><lastmod>2026-02-26T05:40:42.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trust-game-on-carlin-and-love</loc><lastmod>2026-02-26T05:40:42.469Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dictator-game-on-whitt</loc><lastmod>2026-02-26T05:40:42.421Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dictator-game-on-iyengar-and-westwood</loc><lastmod>2026-02-26T05:40:42.452Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-image-classification-on-remote-sensing-domain-suite</loc><lastmod>2026-02-26T05:35:15.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-anomaly-detection-on-bbcnews</loc><lastmod>2026-02-26T05:25:41.018Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-deep-research-on-deepresearch-bench-test</loc><lastmod>2026-02-26T05:54:34.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-level-information-extraction-on-muc-english-4</loc><lastmod>2026-02-26T05:51:19.701Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-evaluation-financial-on-loong-fin</loc><lastmod>2026-02-26T05:45:14.781Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-evaluation-on-lb-v2-all</loc><lastmod>2026-02-26T05:34:05.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-tasks-mc-qa-sum-on-bench</loc><lastmod>2026-02-26T05:49:44.032Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-sarcasm-detection-on-mustard-speaker-independent-original</loc><lastmod>2026-02-26T05:43:31.345Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-coding-on-swe-bench-multilingual</loc><lastmod>2026-05-28T07:43:54.423Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-aishell-2-test</loc><lastmod>2026-02-26T05:38:16.966Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relation-extraction-on-i2b2-three-site-experiment-test</loc><lastmod>2026-02-26T06:04:49.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-i2b2-three-site-experiment-test</loc><lastmod>2026-02-26T06:04:49.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relation-extraction-on-i2b2-two-site-experiment-test</loc><lastmod>2026-02-26T06:04:49.243Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-i2b2-two-site-experiment-test</loc><lastmod>2026-02-26T06:04:49.207Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-retrieval-on-ruler-4k-to-256k-sweep</loc><lastmod>2026-06-19T08:18:09.366Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-information-retrieval-on-qrecc-test</loc><lastmod>2026-02-26T05:59:39.278Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-information-retrieval-on-topiocqa-test</loc><lastmod>2026-02-26T05:59:39.259Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-search-on-browsecomp-plus</loc><lastmod>2026-02-26T06:03:51.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mandela-effect-evaluation-on-manbench</loc><lastmod>2026-02-26T05:42:11.183Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/evaluator-reliability-assessment-on-globalhealthatlas-100-human-annotated-scores-1-0-test</loc><lastmod>2026-02-26T05:49:09.981Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/autoencoding-on-explanatory-sentences-test</loc><lastmod>2026-02-26T05:37:01.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-sentiment140</loc><lastmod>2026-06-26T07:45:40.306Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-crowdflower</loc><lastmod>2026-06-11T08:14:02.358Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-vision-language-reasoning-on-human-evaluations-h</loc><lastmod>2026-02-26T06:03:50.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-vision-language-reasoning-on-original-benchmark-b</loc><lastmod>2026-02-26T06:03:50.955Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-vision-language-reasoning-on-a2eval-b</loc><lastmod>2026-02-26T06:03:50.934Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-on-omega</loc><lastmod>2026-02-27T10:43:54.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimization-modeling-on-mamo-complexlp</loc><lastmod>2026-02-26T05:34:33.183Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optimization-modeling-on-mamo-easylp</loc><lastmod>2026-02-26T05:34:33.170Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores200-en-fi</loc><lastmod>2026-02-26T06:09:12.000Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-en-fi-24</loc><lastmod>2026-02-26T06:09:11.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-attunement-on-mesc</loc><lastmod>2026-02-26T06:08:16.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counseling-quality-on-mesc</loc><lastmod>2026-02-26T05:39:40.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-logical-reasoning-on-visulogic</loc><lastmod>2026-04-21T13:17:49.072Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-as-a-judge-on-fairjudge-benchmark-1k-test</loc><lastmod>2026-02-26T05:34:46.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-as-a-judge-on-judgelm-test</loc><lastmod>2026-02-26T05:34:46.610Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-as-a-judge-on-pandalm-human-annotations-test</loc><lastmod>2026-02-26T05:34:46.595Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/streaming-speech-generation-on-streaming-generation-scenarios-0-6s-speech-chunk</loc><lastmod>2026-02-26T05:45:19.564Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-lambada-standard</loc><lastmod>2026-04-21T11:07:46.326Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-govreport-test</loc><lastmod>2026-04-28T10:36:00.807Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-test-accuracy-cost</loc><lastmod>2026-02-26T05:30:49.961Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-summarization-on-l-eval-sum</loc><lastmod>2026-02-26T05:59:07.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-l-eval-qa</loc><lastmod>2026-02-26T05:53:29.002Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-reasoning-on-bamboo-16k</loc><lastmod>2026-02-26T05:34:53.514Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-rbench-v</loc><lastmod>2026-02-26T05:54:34.285Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-centric-mindpower-reasoning-on-mindpower-video-input-test</loc><lastmod>2026-02-26T05:37:43.154Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pairwise-preference-evaluation-on-conversational-evaluation-suite-ai-companionship-and-role-play-test</loc><lastmod>2026-02-26T06:08:53.491Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-task-completion-on-appworld-leaderboard</loc><lastmod>2026-02-26T05:46:03.515Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-robustness-evaluation-on-dataset-of-200-scientific-papers-1-0-test</loc><lastmod>2026-02-26T05:38:01.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scene-synthesis-on-large-cloud-computing-scale-test</loc><lastmod>2026-02-26T05:57:13.737Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scene-synthesis-on-medium-cluster-computing-scale-test</loc><lastmod>2026-02-26T05:57:13.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scene-synthesis-on-small-edge-computing-scale-test</loc><lastmod>2026-02-26T05:57:13.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/radiology-report-generation-on-radvlm-mimic-cxr-test</loc><lastmod>2026-02-26T06:00:43.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-dialogue-on-tsedata</loc><lastmod>2026-02-26T05:30:47.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-ande</loc><lastmod>2026-02-26T05:30:47.573Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-class</loc><lastmod>2026-02-26T05:48:20.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/imputation-on-imput</loc><lastmod>2026-02-26T05:45:00.214Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/forecasting-on-forec</loc><lastmod>2026-02-26T05:45:00.194Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/anomaly-detection-on-sgad</loc><lastmod>2026-02-26T05:43:30.133Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-oerqa</loc><lastmod>2026-02-26T05:48:20.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-retrieval-on-stark-prime-synthetic-test</loc><lastmod>2026-02-26T05:46:31.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-retrieval-on-stark-mag-synthetic-test</loc><lastmod>2026-02-26T05:46:31.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-retrieval-on-stark-amazon-synthetic-test</loc><lastmod>2026-02-26T05:46:30.994Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mixed-integer-linear-programming-solving-on-set-covering-1000x500-easy</loc><lastmod>2026-05-12T15:40:17.784Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-analysis-on-daeval-verified</loc><lastmod>2026-02-26T05:30:46.785Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-analysis-on-dabstep-hard</loc><lastmod>2026-02-26T05:30:46.769Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-analysis-on-dabstep-easy</loc><lastmod>2026-02-26T05:30:46.751Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-analysis-on-qrdata-verified</loc><lastmod>2026-02-26T05:30:46.735Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bioinformatics-data-analysis-on-dsbio</loc><lastmod>2026-02-26T05:54:25.398Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geospatial-question-answering-on-mapeval-api</loc><lastmod>2026-02-26T05:54:22.875Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-research-on-hle-text-only-original-test</loc><lastmod>2026-02-26T05:57:23.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-hle-med-test</loc><lastmod>2026-02-26T05:30:46.379Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-gam-hard</loc><lastmod>2026-02-26T05:26:45.307Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-language-understanding-on-cmmlu-test</loc><lastmod>2026-02-26T05:38:38.656Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-webprmbench-average</loc><lastmod>2026-02-26T05:57:14.882Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-workarena</loc><lastmod>2026-02-26T05:57:15.048Z</lastmod></url></urlset>