<?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/fine-grained-narrative-classification-on-indi-prop-caa-1-0-test</loc><lastmod>2026-02-26T05:52:45.342Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/article-bias-classification-on-farmer-s-protest-indi-prop-test</loc><lastmod>2026-02-26T05:52:45.324Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-language-understanding-on-ruler-128k</loc><lastmod>2026-03-30T06:37:40.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-generalization-on-countdown-and-ood-tasks-overall-test</loc><lastmod>2026-02-26T05:31:13.277Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-word-problems-on-gsm8k-ood</loc><lastmod>2026-02-26T05:31:13.260Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-question-answering-on-csqa-ood</loc><lastmod>2026-02-26T05:31:13.247Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arithmetic-reasoning-on-long-multiplication-2-3-4-5-digit-ood</loc><lastmod>2026-02-26T05:31:13.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/character-reasoning-on-letter-cd-4-5-ood</loc><lastmod>2026-02-26T05:31:13.220Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/word-reasoning-on-acronym-4-5-ood</loc><lastmod>2026-02-26T05:31:13.206Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-countdown-4-5-6-arg-held-out-difficulties-test</loc><lastmod>2026-02-26T05:31:13.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prefilling-profiling-on-wikitext-test</loc><lastmod>2026-02-26T06:06:28.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-emma-bench</loc><lastmod>2026-02-26T05:39:07.026Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/style-alignment-on-thomas-hardy-test</loc><lastmod>2026-02-26T06:04:51.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/style-alignment-on-charles-dickens-test</loc><lastmod>2026-02-26T05:52:24.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/style-alignment-on-jane-austen-test</loc><lastmod>2026-02-26T05:52:24.285Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-on-long-mt-bench-plus</loc><lastmod>2026-02-26T05:31:12.467Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/persona-based-dialogue-on-convai2-test</loc><lastmod>2026-02-26T05:46:35.961Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/argumentative-fallacy-detection-on-argumentative-fallacy-detection-afd</loc><lastmod>2026-02-26T05:51:28.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stance-detection-on-mitweet-12-facets</loc><lastmod>2026-02-26T05:31:12.043Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-retrieval-on-ruler-4k-128k-sweep-with-latency</loc><lastmod>2026-02-26T06:02:10.527Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-longbench-e-functional-metrics-and-latency</loc><lastmod>2026-02-26T06:04:23.584Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-modeling-on-ruler-test</loc><lastmod>2026-02-26T05:34:02.082Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/close-ended-qa-on-pubmedqa</loc><lastmod>2026-02-26T05:31:11.504Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-livecodebench-v3</loc><lastmod>2026-02-26T05:57:25.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-interaction-question-answering-on-siqa-normalized-pll-score</loc><lastmod>2026-04-24T08:13:43.004Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/linguistic-probing-on-blimp</loc><lastmod>2026-02-26T05:57:48.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-acc-tpf-tps-speedup-vs-ar</loc><lastmod>2026-02-26T05:31:10.418Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/harmful-rate-evaluation-on-mm-safetybench-ocr-test</loc><lastmod>2026-02-26T05:46:58.842Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/end-to-end-translation-on-navigation</loc><lastmod>2026-02-26T05:31:09.510Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unlearning-on-tofu</loc><lastmod>2026-02-26T05:58:59.718Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/end-to-end-qps-improvement-on-deepdiverv2-38b-system-stack-serving-evaluation-tp8-tp2-deployment</loc><lastmod>2026-02-26T05:59:07.973Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-formulation-of-design-requirements-on-d_hq-test</loc><lastmod>2026-02-26T05:34:57.878Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-bfcl-single-turn</loc><lastmod>2026-02-26T05:54:01.626Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-moderation-on-guareval-prompt</loc><lastmod>2026-02-26T05:43:33.299Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/crosslingual-claim-retrieval-on-development-dataset-dev</loc><lastmod>2026-02-26T05:59:29.900Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/monolingual-claim-retrieval-on-dataset-dev</loc><lastmod>2026-02-26T06:01:19.462Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-average-1-0-full-dataset</loc><lastmod>2026-02-26T05:31:08.321Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-refusal-persona-1-0-full-dataset</loc><lastmod>2026-02-26T05:31:08.305Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-factually-wrong-persona-1-0</loc><lastmod>2026-02-26T05:31:08.287Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-contradictory-persona-1-0</loc><lastmod>2026-02-26T05:31:08.271Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-off-focus-persona-1-0</loc><lastmod>2026-02-26T05:31:08.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-partial-vague-persona-1-0</loc><lastmod>2026-02-26T05:31:08.243Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-ambiguous-query-clarification-on-clarifymt-bench-precise-persona-1-0</loc><lastmod>2026-02-26T05:31:08.229Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-information-extraction-and-classification-on-meddialog-cn-1000-labeled-samples-1-0-test</loc><lastmod>2026-02-26T05:49:46.490Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/true-false-question-answering-on-tmqa</loc><lastmod>2026-06-18T08:26:39.200Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/silicon-sampling-alignment-on-anes-test</loc><lastmod>2026-02-26T05:36:13.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-pregnancy-outcomes-twitter-dataset-test</loc><lastmod>2026-02-26T05:58:33.540Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-intelligence-evaluation-on-agi-eval</loc><lastmod>2026-05-20T06:56:26.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extractive-question-answering-on-five-extractive-qa-datasets-aggregated</loc><lastmod>2026-02-26T05:38:55.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sarcasm-detection-on-iac-v1-iac-v2-and-semeval-2018-average</loc><lastmod>2026-02-26T05:31:06.730Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/protein-generation-evaluation-set-30k-samples</loc><lastmod>2026-02-26T06:11:20.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/topic-segmentation-on-videoaula-val</loc><lastmod>2026-02-26T05:43:32.820Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/topic-segmentation-on-ami-test</loc><lastmod>2026-02-26T05:43:32.805Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-pmdc-maximum-discrepancy-samples</loc><lastmod>2026-02-26T06:00:57.406Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-hle-no-tools</loc><lastmod>2026-07-07T10:25:37.874Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personal-information-privacy-assessment-on-pipa</loc><lastmod>2026-02-26T06:03:52.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-question-answering-on-arc-challenge-chinese</loc><lastmod>2026-02-26T06:03:52.484Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graded-semantic-change-detection-on-semeval-subtask-2-2020</loc><lastmod>2026-02-26T05:35:50.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-judgment-on-ral2m-covidqa-expertqa-hagrid-hotpotqa-msmarco-test</loc><lastmod>2026-02-26T05:31:05.346Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-analytic-geometry-solid-geometry</loc><lastmod>2026-02-26T05:39:37.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-analytic-geometry-plane-geometry</loc><lastmod>2026-02-26T05:39:37.763Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-synthetic-geometry-plane-geometry</loc><lastmod>2026-02-26T05:39:37.744Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-phyx-thermodynamics</loc><lastmod>2026-02-26T05:39:37.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-phyx-electromagnetism</loc><lastmod>2026-02-26T05:39:37.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-phyx-mechanics</loc><lastmod>2026-02-26T05:39:37.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-phyx-modern</loc><lastmod>2026-02-26T05:39:37.556Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-mathverse-function</loc><lastmod>2026-02-26T05:39:37.541Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-mathverse-plane-geometry</loc><lastmod>2026-02-26T05:39:37.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dementia-prognosis-on-asan-medical-center-dataset</loc><lastmod>2026-02-26T05:31:05.264Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-ragtruth-llama-13b</loc><lastmod>2026-02-26T06:01:13.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-ragtruth-llama-7b</loc><lastmod>2026-02-26T06:01:13.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-americasnlp-2023-dev</loc><lastmod>2026-02-26T06:09:12.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/exploration-on-alfworld</loc><lastmod>2026-04-13T10:04:08.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unlearning-on-tofu-forget01</loc><lastmod>2026-02-26T05:45:30.072Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-squad-em-f1-trigger-ratio</loc><lastmod>2026-02-26T05:41:38.486Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-trigger-ratio</loc><lastmod>2026-02-26T05:41:38.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-em-f1-trigger-ratio</loc><lastmod>2026-02-26T05:41:38.442Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fake-news-detection-on-advfake-news-please-test</loc><lastmod>2026-02-26T06:00:23.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-based-multi-step-reasoning-on-mean-of-webqsp-cwq-gsm8k-mwp-and-dr-spider-test</loc><lastmod>2026-02-26T05:46:10.758Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/essay-scoring-on-asap-plus-plus-five-fold-averaged-results</loc><lastmod>2026-02-26T05:54:34.857Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/essay-scoring-on-asap-sas-prompts-3-4-7-8-9</loc><lastmod>2026-02-26T05:59:08.338Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-mquake</loc><lastmod>2026-02-26T05:49:51.014Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intervention-on-mami</loc><lastmod>2026-02-26T06:11:17.796Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-on-mami</loc><lastmod>2026-02-26T06:11:17.777Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intervention-on-fhm</loc><lastmod>2026-02-26T06:11:17.760Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-on-fhm</loc><lastmod>2026-02-26T06:11:17.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-lcb-test</loc><lastmod>2026-02-26T05:31:04.048Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-to-optimization-on-wireopt-nc2c-test</loc><lastmod>2026-02-26T06:05:10.333Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-to-optimization-on-complexor-test</loc><lastmod>2026-02-26T06:05:39.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-to-optimization-on-nlp4lp-test</loc><lastmod>2026-02-26T06:05:10.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-to-optimization-on-nl4opt-test</loc><lastmod>2026-02-26T06:05:10.304Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/acronym-disambiguation-on-gladis</loc><lastmod>2026-02-26T05:34:17.024Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-summarization-on-govreport-test</loc><lastmod>2026-02-26T06:00:36.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-kodcode-test</loc><lastmod>2026-02-26T05:31:03.547Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-de-en-0-shot</loc><lastmod>2026-02-26T06:11:20.516Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-en-de-0-shot</loc><lastmod>2026-02-26T06:11:20.336Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arithmetic-reasoning-on-gsm8k-4-shot-cot</loc><lastmod>2026-02-26T05:31:03.056Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-intensive-qa-on-triviaqa-5-shot</loc><lastmod>2026-02-26T05:42:31.836Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-intensive-qa-on-squad-5-shot</loc><lastmod>2026-02-26T05:41:42.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-intensive-qa-on-naturalquestions-nq-5-shot</loc><lastmod>2026-02-26T05:41:42.968Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/review-score-generation-on-aaai-2025</loc><lastmod>2026-02-26T05:35:42.653Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/review-score-generation-on-iclr-2025</loc><lastmod>2026-02-26T05:35:42.638Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/review-score-generation-on-icml-2025</loc><lastmod>2026-02-26T05:36:21.469Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/review-score-generation-on-neurips-2025</loc><lastmod>2026-02-26T05:36:21.454Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/review-score-generation-on-acl-2025</loc><lastmod>2026-02-26T05:36:21.439Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tasks-on-tau2-retail</loc><lastmod>2026-02-26T06:03:56.507Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tasks-on-tau2-airline</loc><lastmod>2026-02-26T06:03:56.492Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chat-preference-on-arena-hard-v2</loc><lastmod>2026-03-04T08:22:14.650Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/expert-level-science-question-answering-on-gpqa-diamond</loc><lastmod>2026-04-23T10:07:50.383Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-full-test</loc><lastmod>2026-02-26T05:41:38.325Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-concurrentqa-test</loc><lastmod>2026-02-26T05:41:38.305Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-multiple-choice-question-answering-on-head-qa-test</loc><lastmod>2026-02-26T05:31:02.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-multiple-choice-question-answering-on-frenchmedmcqa-test</loc><lastmod>2026-02-26T05:31:02.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-multiple-choice-question-answering-on-rumeddanet-test</loc><lastmod>2026-02-26T05:31:02.180Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-multiple-choice-question-answering-on-igakuqa-japan-s-medical-licensure-exams-2018-2022-test</loc><lastmod>2026-02-26T05:31:02.164Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-multiple-choice-question-answering-on-medqa-usmle-chinese-test-set</loc><lastmod>2026-02-26T05:31:02.151Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-segmentation-on-superdialseg</loc><lastmod>2026-02-26T05:58:04.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-on-mbpp-1-000-example-test</loc><lastmod>2026-02-26T05:57:55.047Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-on-gsm8k-1-000-example-test</loc><lastmod>2026-02-26T05:55:10.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-pass-at-16</loc><lastmod>2026-02-26T05:57:35.485Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-science-sci-semeval-2016-task-13</loc><lastmod>2026-02-26T05:39:07.426Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-pass-at-1-and-pass-at-3</loc><lastmod>2026-02-26T05:57:25.104Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc12-pass-at-1-pass-at-3</loc><lastmod>2026-02-26T05:57:25.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/psychological-simulation-evaluation-on-humanllm-evaluation-suite-averaged-1-0-id-ood-and-mixed</loc><lastmod>2026-02-26T05:46:53.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-arc-hard-chat-m-ori</loc><lastmod>2026-02-27T10:47:28.091Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-language-understanding-on-global-mmlu-lite-m-ori</loc><lastmod>2026-02-27T10:47:28.064Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/simultaneous-machine-translation-on-acl60-60-en-ja-eval</loc><lastmod>2026-02-26T05:37:02.070Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/simultaneous-machine-translation-on-acl60-60-en-zh-eval</loc><lastmod>2026-02-26T05:37:02.054Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/simultaneous-machine-translation-on-acl60-60-english-japanese-en-ja-val</loc><lastmod>2026-02-26T05:37:02.036Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-selection-on-spider-2018-test</loc><lastmod>2026-02-26T05:36:25.502Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-supergpqa-law</loc><lastmod>2026-02-26T05:30:58.917Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stance-detection-on-delta-stance</loc><lastmod>2026-02-26T05:51:35.277Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/legal-information-extraction-and-entailment-on-coliee</loc><lastmod>2026-02-26T05:35:50.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/legal-language-understanding-on-lexglue</loc><lastmod>2026-02-26T05:48:35.898Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/thai-document-parsing-on-in-house-thai-document-corpus-government-forms</loc><lastmod>2026-02-26T05:48:35.862Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relational-triplet-extraction-on-webnlg-rebel-and-wiki-nre-combined</loc><lastmod>2026-02-26T05:54:29.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/character-component-tagging-on-pride-and-prejudice</loc><lastmod>2026-02-26T05:49:28.202Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-legal</loc><lastmod>2026-02-26T05:48:34.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-xquad-1-0-test</loc><lastmod>2026-02-26T05:43:44.899Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-naturalness-assessment-on-cvss-t</loc><lastmod>2026-02-26T06:07:51.387Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-translation-fra2en-on-cvss-t</loc><lastmod>2026-02-26T05:37:10.558Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-translation-en2fra-on-cvss-t</loc><lastmod>2026-02-26T05:37:10.542Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-naturalness-assessment-on-cvss-c</loc><lastmod>2026-02-26T06:07:51.668Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-translation-fra2en-on-cvss-c</loc><lastmod>2026-02-26T05:37:01.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-translation-en2fra-on-cvss-c</loc><lastmod>2026-02-26T05:37:01.843Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-correlation-analysis-on-rottenreview</loc><lastmod>2026-02-26T06:04:35.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-question-answering-on-lamp-qa</loc><lastmod>2026-02-26T05:34:09.075Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-jungle-chess</loc><lastmod>2026-02-26T05:25:13.799Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-metonymy-interpretation-on-vimet-overall-1-0-full</loc><lastmod>2026-02-26T05:30:58.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-metonymy-interpretation-on-vimet-stylistic-1-0</loc><lastmod>2026-02-26T05:30:57.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-metonymy-interpretation-on-vimet-naturalistic-1-0</loc><lastmod>2026-02-26T05:30:57.971Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-arabculture-native-prompts-test</loc><lastmod>2026-02-26T05:30:57.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medmcqa-val</loc><lastmod>2026-06-26T08:26:15.529Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-dragonball-dragsinglezh-test</loc><lastmod>2026-02-26T06:01:13.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hierarchical-text-classification-on-books</loc><lastmod>2026-02-26T05:51:27.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/technical-problem-solving-on-arena-hard</loc><lastmod>2026-02-26T06:08:53.635Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/16-types-multiclass-personality-classification-on-pandora</loc><lastmod>2026-02-26T05:43:31.558Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/16-types-multiclass-personality-classification-on-kaggle</loc><lastmod>2026-02-26T05:43:52.788Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/4-dimensional-binary-personality-classification-on-kaggle</loc><lastmod>2026-02-26T05:51:27.227Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/key-information-extraction-on-cord-v1-test</loc><lastmod>2026-02-26T05:22:34.206Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/key-information-extraction-on-sroie-v1-test</loc><lastmod>2026-02-26T05:22:34.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/key-information-extraction-on-funsd-v1-test</loc><lastmod>2026-02-26T05:22:34.157Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sarcasm-understanding-on-mustard-plus-plus</loc><lastmod>2026-06-05T09:37:04.866Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalization-evaluation-on-prefeval-10-injected-adversarial-turns</loc><lastmod>2026-02-26T05:58:54.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/singing-voice-transcription-on-popcs</loc><lastmod>2026-05-07T08:49:34.213Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/singing-voice-transcription-on-opencpop</loc><lastmod>2026-05-07T08:49:34.242Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-cv-yue</loc><lastmod>2026-02-26T05:38:16.071Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-it0-it3</loc><lastmod>2026-02-26T05:47:30.836Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt-24-it0-it1-it2-it3</loc><lastmod>2026-02-26T05:47:30.942Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-acc-length</loc><lastmod>2026-02-26T05:30:56.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-accuracy</loc><lastmod>2026-02-26T05:30:55.166Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-level-confidence-prediction-on-wikibio</loc><lastmod>2026-02-26T05:26:05.660Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25</loc><lastmod>2026-02-26T05:57:24.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-infilling-on-santacoder-fim</loc><lastmod>2026-02-26T05:41:37.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cbt-conversation-generation-on-cbt-conversation-evaluation-dataset</loc><lastmod>2026-02-26T06:04:13.516Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-essay-scoring-on-asap-plus-plus-full-data-setting</loc><lastmod>2026-02-26T06:04:07.892Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-trait-automated-essay-scoring-on-asap-plus-plus-full-data</loc><lastmod>2026-02-26T05:54:34.517Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-web-data-extraction-on-swde-all-domains-test</loc><lastmod>2026-02-26T05:43:30.901Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-long-context-understanding-on-longbench</loc><lastmod>2026-02-26T05:59:08.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-and-general-on-hle-full</loc><lastmod>2026-02-26T06:04:04.202Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-broad-information-seeking-on-wideseekbench-test</loc><lastmod>2026-02-26T06:05:38.872Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-localization-on-mcqa-val</loc><lastmod>2026-02-26T05:30:53.585Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-localization-on-ravel-country-val</loc><lastmod>2026-02-26T05:30:53.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-localization-on-ravel-language-val</loc><lastmod>2026-02-26T05:30:53.552Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-localization-on-ravel-continent-val</loc><lastmod>2026-02-26T05:30:53.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-competition-level-benchmarks-average</loc><lastmod>2026-02-26T05:57:24.458Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-beyond-aime-pass-at-1-pass-at-32</loc><lastmod>2026-02-26T05:57:24.440Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-pass-at-1-pass-at-32</loc><lastmod>2026-02-26T05:57:24.426Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-pass-at-1-and-pass-at-32</loc><lastmod>2026-02-26T05:57:24.413Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-wmdp-bio-test</loc><lastmod>2026-02-26T05:37:49.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ecg-abnormality-detection-on-ptb-xl-super</loc><lastmod>2026-02-26T05:24:50.262Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/faithfulness-evaluation-on-qasper-yes-no-question-answering</loc><lastmod>2026-02-26T05:22:36.120Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-vqa-on-countbench</loc><lastmod>2026-03-10T09:47:15.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stem-reasoning-on-gpqa-diamond-5-shot</loc><lastmod>2026-02-26T05:31:07.494Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gec-metric-meta-evaluation-on-gmeg-data</loc><lastmod>2026-02-26T05:57:43.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-classification-on-semeval-task-1-english-2018-test</loc><lastmod>2026-02-26T05:51:27.107Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-infilling-on-mceval-multi-line</loc><lastmod>2026-02-26T05:47:39.295Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-infilling-on-mceval-single-line</loc><lastmod>2026-02-26T05:47:39.278Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-and-question-answering-on-deepsearch-qa</loc><lastmod>2026-03-18T06:44:53.020Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-paraphrase-detection-on-etpc</loc><lastmod>2026-02-26T05:30:50.558Z</lastmod></url></urlset>