<?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/boolean-classification-on-police-incident-dataset</loc><lastmod>2026-02-26T05:34:14.444Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/contextual-reasoning-on-hellaswag</loc><lastmod>2026-06-19T06:51:59.547Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/world-knowledge-on-mmlu-em</loc><lastmod>2026-06-19T06:51:59.572Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-cmimc</loc><lastmod>2026-02-26T05:31:09.542Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/inference-latency-on-wikitext-103-squad-v2-and-openbookqa</loc><lastmod>2026-02-26T05:47:07.204Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/formal-theorem-proving-on-fate-h</loc><lastmod>2026-03-12T08:28:10.539Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-seeking-question-answering-on-simpleqa-no-web</loc><lastmod>2026-02-26T05:31:09.298Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-just-nlp-shared-task-legal-machine-translation-english-hindi-2025-test</loc><lastmod>2026-02-26T05:37:02.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chart-schema-parsing-on-cyclechart-bench-test</loc><lastmod>2026-02-26T06:00:45.164Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/nl2chart-on-cyclechart-bench</loc><lastmod>2026-02-26T06:00:45.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-ld50</loc><lastmod>2026-02-26T06:00:01.525Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-caco2</loc><lastmod>2026-02-26T06:00:01.452Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-aqsol</loc><lastmod>2026-02-26T06:00:01.391Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-spoken-question-answering-on-voicebench-s2t-test</loc><lastmod>2026-02-26T05:34:52.885Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-spoken-question-answering-on-openaudiobench-s2t-test</loc><lastmod>2026-02-26T05:34:53.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-instruction-following-on-vstyle-zh-2025</loc><lastmod>2026-02-26T05:54:34.978Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-instruction-following-on-vstyle-en-2025</loc><lastmod>2026-02-26T05:54:34.963Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/self-supervised-pretraining-on-libri-light-6k</loc><lastmod>2026-02-26T05:58:58.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/word-discovery-on-librispeech-other-dev</loc><lastmod>2026-02-26T05:49:37.361Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/word-discovery-on-librispeech-clean-dev</loc><lastmod>2026-02-26T05:49:37.329Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phonetic-discriminability-abx-on-librispeech-other-dev</loc><lastmod>2026-02-26T05:21:47.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phonetic-discriminability-abx-on-librispeech-clean-dev</loc><lastmod>2026-02-26T05:21:47.933Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-action-distribution-prediction-on-mental-health-support-user-action-distributions-160k</loc><lastmod>2026-02-26T05:36:38.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-c-bacteria</loc><lastmod>2026-02-26T05:21:47.790Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-bacillus</loc><lastmod>2026-02-26T05:21:47.764Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-r-bean</loc><lastmod>2026-02-26T05:21:47.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-tomato</loc><lastmod>2026-02-26T05:21:47.722Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-honeybee</loc><lastmod>2026-02-26T05:21:47.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-m-mazei</loc><lastmod>2026-02-26T05:21:47.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-yeast</loc><lastmod>2026-02-26T05:21:47.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-human</loc><lastmod>2026-02-26T05:21:47.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-mouse</loc><lastmod>2026-02-26T05:21:47.616Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/across-speaker-abx-on-3-languages-test</loc><lastmod>2026-02-26T05:35:10.249Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/within-speaker-abx-on-3-languages-test</loc><lastmod>2026-02-26T05:36:02.271Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/accuracy-on-ap-statistics-statistical-reasoning</loc><lastmod>2026-02-26T05:31:07.596Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-halueval-summarization-starling-lm-7b-alpha</loc><lastmod>2026-02-26T06:05:57.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-sextuple-extraction-on-panosent-1-0-val</loc><lastmod>2026-02-26T05:36:10.937Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-flipping-analysis-on-panosent-val</loc><lastmod>2026-02-26T05:42:32.187Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-plus-4-shot</loc><lastmod>2026-02-26T05:45:36.676Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-4-shot</loc><lastmod>2026-02-26T06:03:53.293Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-gsm8k-3-shot</loc><lastmod>2026-02-26T05:31:07.460Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-mmlu-5-shot</loc><lastmod>2026-02-26T05:34:02.474Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-hellaswag-10-shot</loc><lastmod>2026-02-26T06:03:53.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-arc-c-0-shot</loc><lastmod>2026-02-26T06:03:53.242Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomedical-named-entity-recognition-on-bc2gm</loc><lastmod>2026-02-26T06:04:49.173Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomedical-named-entity-recognition-on-bc5cdr-disease-strict-match-f1</loc><lastmod>2026-02-26T06:04:49.021Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/introduction-generation-on-50-acl-papers-test</loc><lastmod>2026-02-26T06:00:58.148Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biblical-quotation-detection-on-biblical-quotation-detection-dataset</loc><lastmod>2026-02-26T05:43:32.953Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-quality-evaluation-on-alpacaeval-elom-gpt4-test</loc><lastmod>2026-02-26T05:41:31.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-tokenization-on-seed-tts-eval-en</loc><lastmod>2026-02-26T05:55:02.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-tokenization-on-seed-tts-eval-zh</loc><lastmod>2026-02-26T05:55:03.098Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-guidebench</loc><lastmod>2026-05-14T09:43:52.557Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-agent-on-finintentr</loc><lastmod>2026-02-26T06:03:53.210Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-reasoning-on-finreason</loc><lastmod>2026-02-26T06:03:53.194Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-knowledge-capability-on-fin-eva</loc><lastmod>2026-02-26T06:03:53.163Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-decoding-on-logicbench</loc><lastmod>2026-02-26T05:39:47.416Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fitness-prediction-on-proteingym</loc><lastmod>2026-02-26T06:04:36.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-mlc-slm-eval</loc><lastmod>2026-02-26T06:08:38.857Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/word-level-pronunciation-assessment-on-speechocean762</loc><lastmod>2026-02-26T05:54:53.499Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-pass-at-1-pass-at-5-nfe-speed</loc><lastmod>2026-02-26T05:57:25.444Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-arc-c-arc-e-hellaswag-obqa-piqa-winogrande-test</loc><lastmod>2026-02-26T05:23:39.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-truthfulqa</loc><lastmod>2026-02-26T05:37:18.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-conversation-on-no-convai2-nlebench-test</loc><lastmod>2026-02-26T05:37:02.425Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-factuality-verification-on-hotpotqa</loc><lastmod>2026-02-26T05:31:04.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-factuality-verification-on-triviaqa</loc><lastmod>2026-02-26T05:31:04.651Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-navigation-and-action-on-gui-odyssey</loc><lastmod>2026-02-26T06:07:45.237Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-navigation-and-action-on-androidcontrol</loc><lastmod>2026-02-26T06:07:45.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-on-aitz-androidcontrol-and-gui-odyssey</loc><lastmod>2026-02-26T05:36:28.572Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-on-gui-odyssey</loc><lastmod>2026-02-26T06:07:45.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-on-androidcontrol</loc><lastmod>2026-02-26T06:07:44.995Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vocal-event-detection-on-wesr-bench-macro-avg-1-0</loc><lastmod>2026-02-26T05:58:33.300Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vocal-event-detection-on-wesr-bench-1-0</loc><lastmod>2026-02-26T05:58:33.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vocal-event-detection-on-wesr-bench-1-0-test</loc><lastmod>2026-02-26T05:58:33.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-generation-and-interaction-on-medical-speech-dialogue-benchmark</loc><lastmod>2026-02-26T06:07:51.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-graphrag-benchmark-novel</loc><lastmod>2026-02-26T05:45:07.406Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-f1-acc</loc><lastmod>2026-02-26T05:41:38.424Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-response-generation-on-keem-memories-1-0-test</loc><lastmod>2026-02-26T05:57:55.116Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-popqa-em</loc><lastmod>2026-02-26T05:41:38.387Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extractive-question-answering-on-piaf-1-2</loc><lastmod>2026-02-26T05:59:05.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/target-group-identification-on-blp-task-1-subtask-1b-2025-test</loc><lastmod>2026-02-26T05:43:55.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hate-speech-detection-on-blp-task-1-subtask-1a-2025</loc><lastmod>2026-02-26T05:43:55.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extractive-question-answering-on-mlqa-chinese-test</loc><lastmod>2026-02-26T05:36:43.244Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-xl-sum-chinese-test</loc><lastmod>2026-02-26T05:36:43.386Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/extractive-question-answering-on-mlqa-arabic-test</loc><lastmod>2026-02-26T05:36:43.229Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overall-reasoning-performance-on-locomo-test</loc><lastmod>2026-02-26T05:48:08.808Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-on-locomo-test</loc><lastmod>2026-02-26T05:48:08.792Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-on-locomo-test</loc><lastmod>2026-02-26T05:48:08.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-reasoning-on-locomo-test</loc><lastmod>2026-02-26T05:48:08.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-reasoning-on-locomo-test</loc><lastmod>2026-02-26T05:48:08.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-adjuvant-held-out-test</loc><lastmod>2026-02-26T05:36:43.007Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/citation-grounded-summarization-on-citation-grounded-summarization-test</loc><lastmod>2026-02-26T05:45:07.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/entity-linking-on-newseye-f1-per-language</loc><lastmod>2026-02-26T05:42:53.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-noisy-test</loc><lastmod>2026-02-27T10:47:29.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-mandarin</loc><lastmod>2026-02-26T05:38:15.857Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-on-mmlu-average-accuracy</loc><lastmod>2026-02-26T05:50:01.733Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-bbh-gpqa-and-musr-suite</loc><lastmod>2026-02-26T05:36:37.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-unified-korean-benchmark-instruction-following</loc><lastmod>2026-02-26T05:47:55.635Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-on-unified-korean-benchmark-general-knowledge</loc><lastmod>2026-02-26T05:47:46.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-unified-korean-benchmark-reasoning</loc><lastmod>2026-02-26T05:47:55.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/comprehension-on-unified-korean-benchmark-comprehension</loc><lastmod>2026-02-26T05:47:41.530Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/concept-retrieval-on-elsst-concept-retrieval-synthetic-test</loc><lastmod>2026-02-26T05:50:27.356Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-on-click</loc><lastmod>2026-02-26T06:03:52.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-on-kmmlu-pro</loc><lastmod>2026-02-26T06:03:53.067Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-ability-model-merging-on-wizardmath-tulu-2-and-wizardlm-test</loc><lastmod>2026-02-26T05:51:39.398Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/character-motivation-recognition-on-cross-mr</loc><lastmod>2026-02-26T05:31:00.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/persona-driven-decision-making-on-lifechoice</loc><lastmod>2026-02-26T05:31:00.942Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/therapeutic-response-generation-on-mental-healthcare-support-dataset</loc><lastmod>2026-02-26T05:37:02.089Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-language-modeling-on-sstorycloze</loc><lastmod>2026-02-26T05:31:00.906Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-language-modeling-on-storycloze-stopic</loc><lastmod>2026-02-26T05:31:00.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-as-a-judge-evaluation-on-100-romanian-synthetic-prompts-test</loc><lastmod>2026-02-26T05:45:22.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-alignment-correlation-on-lmsys-search-arena-test</loc><lastmod>2026-02-26T05:57:40.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-toys-2018-test</loc><lastmod>2026-02-26T06:01:33.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-beauty-2018-test</loc><lastmod>2026-02-26T06:01:33.439Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-sports-2018-test</loc><lastmod>2026-02-26T06:01:33.418Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-baby-products-2023-test</loc><lastmod>2026-02-26T06:01:33.399Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sequential-recommendation-on-amazon-beauty-2023-test</loc><lastmod>2026-02-26T06:01:33.386Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-search-on-clariq</loc><lastmod>2026-02-26T06:00:43.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/topic-modeling-on-banking77</loc><lastmod>2026-02-26T05:59:03.555Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/event-detection-on-maven</loc><lastmod>2026-02-26T05:51:33.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/nested-named-entity-recognition-on-chilean-waiting-list</loc><lastmod>2026-02-26T05:58:33.028Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rating-prediction-on-yelp-test</loc><lastmod>2026-06-11T06:45:46.876Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-evaluation-on-coreflect-simulation-iteration-t-1-1-0</loc><lastmod>2026-02-26T05:54:04.004Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-evaluation-on-coreflect-1-0-iteration-3</loc><lastmod>2026-02-26T05:54:03.990Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-evaluation-on-coreflect-iteration-2-test</loc><lastmod>2026-02-26T05:54:03.972Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-reasoning-on-sugarcrepe-test</loc><lastmod>2026-02-26T06:04:22.823Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-reasoning-on-naturalbench-test</loc><lastmod>2026-02-26T06:04:22.807Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-reasoning-on-mme-test</loc><lastmod>2026-02-26T06:04:22.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-reasoning-on-hallusionbench-test</loc><lastmod>2026-02-26T06:04:22.773Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-reasoning-on-beaf-test</loc><lastmod>2026-02-26T06:04:22.756Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-14-region</loc><lastmod>2026-02-26T05:30:59.501Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/6-continent-classification-test</loc><lastmod>2026-02-26T05:30:59.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/nationality-classification-on-99-country-nationality-dataset</loc><lastmod>2026-02-26T05:30:59.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-level-anomaly-detection-on-grammar-test</loc><lastmod>2026-02-26T05:26:06.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-level-anomaly-detection-on-review-test</loc><lastmod>2026-02-26T05:26:06.744Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-level-anomaly-detection-on-sms_spam-test</loc><lastmod>2026-02-26T05:26:06.721Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/token-level-anomaly-detection-on-grammar-test</loc><lastmod>2026-02-26T05:26:06.696Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/token-level-anomaly-detection-on-review-test</loc><lastmod>2026-02-26T05:26:06.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/token-level-anomaly-detection-on-sms-spam-test</loc><lastmod>2026-02-26T05:26:06.649Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-ifbench-test</loc><lastmod>2026-02-26T05:30:58.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-arabic-preference-test</loc><lastmod>2026-02-26T05:30:58.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-evalbiasbench</loc><lastmod>2026-02-26T05:30:58.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-popqa-em-atc</loc><lastmod>2026-02-26T05:36:26.409Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/character-component-tagging-on-jane-eyre</loc><lastmod>2026-02-26T05:49:28.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-meditod</loc><lastmod>2026-02-26T05:26:06.557Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-ddxplus</loc><lastmod>2026-02-26T05:26:06.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/masked-language-modeling-on-turkish-datasets-composite-test</loc><lastmod>2026-02-26T05:49:55.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/object-grounding-on-dior</loc><lastmod>2026-02-26T06:09:38.616Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-learning-on-timely-eval</loc><lastmod>2026-02-26T05:48:33.756Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-reasoning-on-timely-eval</loc><lastmod>2026-02-26T06:09:06.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-reasoning-on-timely-eval</loc><lastmod>2026-02-26T05:49:42.891Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-translation-fra2en-on-cvss-t</loc><lastmod>2026-02-26T05:37:10.526Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-translation-en2fra-on-cvss-t</loc><lastmod>2026-02-26T05:37:01.874Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-translation-on-cvss-c-fra2en</loc><lastmod>2026-02-26T05:37:01.828Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-translation-en2fra-on-cvss-c</loc><lastmod>2026-02-26T05:37:01.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/disease-progression-prediction-on-l-mimic-test</loc><lastmod>2026-02-27T10:45:27.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/disease-diagnosis-on-l-mimic-test</loc><lastmod>2026-02-27T10:45:27.645Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-report-generation-on-l-mimic-whole-report-test</loc><lastmod>2026-02-27T10:45:27.583Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-anomaly-detection-on-moviereview</loc><lastmod>2026-02-26T05:25:41.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-understanding-on-glue-test-sst-2-rte-qnli-subset</loc><lastmod>2026-02-26T06:03:31.377Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-evaluation-of-explanation-interpretability-on-clinical-expert-evaluation-questionnaire-qualitative-survey-n-28-likert-scale</loc><lastmod>2026-02-26T05:47:17.014Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embedding-to-section-reconstruction-emb2sec-on-pubmedrct-test</loc><lastmod>2026-02-26T06:04:13.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sarcasm-understanding-on-wits</loc><lastmod>2026-02-26T06:00:36.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sarcasm-understanding-on-mustard</loc><lastmod>2026-02-26T05:58:32.593Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-coding-on-terminalbench</loc><lastmod>2026-03-31T09:50:25.986Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-coding-on-swe-bench</loc><lastmod>2026-03-31T09:50:25.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-dialog-chinese-dialects</loc><lastmod>2026-02-26T06:08:29.613Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-dialog-cantonese</loc><lastmod>2026-02-26T06:08:29.596Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-dialog-mandarin</loc><lastmod>2026-02-26T06:08:29.439Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-tonguetwister</loc><lastmod>2026-02-26T06:08:29.422Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-extremenoise</loc><lastmod>2026-02-26T06:08:29.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-elders-and-kids</loc><lastmod>2026-02-26T06:08:29.392Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-dialog-accented-english</loc><lastmod>2026-02-26T06:08:29.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-cv-en</loc><lastmod>2026-02-26T06:08:29.357Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-model-evaluation-on-quality-factuality-and-safety-evaluation-suite-test</loc><lastmod>2026-02-26T05:45:57.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-redpajama-safety-evals-test</loc><lastmod>2026-02-26T06:03:38.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dense-text-embedding-on-mteb-v2-test</loc><lastmod>2026-02-26T05:39:14.069Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-retrieval-on-mteb-v2</loc><lastmod>2026-02-26T05:53:05.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-class-classification-on-mami-task-b</loc><lastmod>2026-02-26T05:51:34.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-task-planning-on-alfworld-standard-evaluation-set-134-tasks</loc><lastmod>2026-02-26T05:57:33.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-navigation-and-task-completion-on-webvoyager-live-websites</loc><lastmod>2026-02-26T06:05:36.767Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-fact-verification-on-hover-4-hop</loc><lastmod>2026-02-26T05:51:34.686Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-fact-verification-on-hover-3-hop</loc><lastmod>2026-02-26T05:51:27.159Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-fact-verification-on-hover-2-hop</loc><lastmod>2026-02-26T05:51:27.144Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-performance-on-bfcl-multi-turn-v4</loc><lastmod>2026-02-26T05:37:39.947Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-performance-on-tau-2-bench</loc><lastmod>2026-02-26T05:34:47.302Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-on-webwalker</loc><lastmod>2026-02-26T06:03:51.120Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-on-frames</loc><lastmod>2026-02-26T06:03:51.083Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-avg-at-6</loc><lastmod>2026-02-26T05:36:32.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-avg-at-6</loc><lastmod>2026-02-26T05:36:32.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-avg-at-6</loc><lastmod>2026-02-26T05:36:32.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/shortest-path-on-synthetic-benchmark</loc><lastmod>2026-02-26T05:30:55.733Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/edge-existence-on-synthetic-benchmark</loc><lastmod>2026-02-26T05:30:55.714Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reachability-on-fatemi-synthetic</loc><lastmod>2026-02-26T05:30:55.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/connected-nodes-on-fatemi-synthetic-benchmark</loc><lastmod>2026-02-26T05:30:55.679Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-degree-on-synthetic-benchmark-accuracy-absolute-error</loc><lastmod>2026-02-26T05:30:55.659Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/triangle-count-on-synthetic-benchmark</loc><lastmod>2026-02-26T05:30:55.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cycle-check-on-synthetic-benchmark</loc><lastmod>2026-02-26T05:30:55.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/edge-count-on-synthetic-benchmark</loc><lastmod>2026-02-26T05:30:55.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-count-on-synthetic-benchmark-1-0-test</loc><lastmod>2026-02-26T05:30:55.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-spatial-reasoning-on-scenegraphs-test</loc><lastmod>2026-02-26T05:30:55.577Z</lastmod></url></urlset>