<?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/mortality-prediction-on-mimic-iii-v1-4-1000-patients</loc><lastmod>2026-02-26T05:25:41.317Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/claim-verification-on-human-evaluation-dataset-400-claims</loc><lastmod>2026-02-26T05:31:07.580Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-llm-labeled-polish-medical-data-oncology-1-0-test</loc><lastmod>2026-02-26T05:43:33.058Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-llm-labeled-polish-medical-data-pathology-1-0-test</loc><lastmod>2026-02-26T05:43:33.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-llm-labeled-polish-medical-data-radiology-1-0-test</loc><lastmod>2026-02-26T05:43:33.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-llm-labeled-polish-medical-data-hypertension-1-0-test</loc><lastmod>2026-02-26T05:43:32.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-llm-labeled-polish-medical-data-cardiology-1-0-test</loc><lastmod>2026-02-26T05:43:32.967Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-nlm-chem-unseen-out-of-domain</loc><lastmod>2026-02-26T05:58:33.522Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-nlm-gene-unseen-out-of-domain</loc><lastmod>2026-02-26T05:58:33.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-em-f1</loc><lastmod>2026-02-26T05:41:38.601Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-query-answering-on-clinical-narratives-item-level-test</loc><lastmod>2026-02-26T06:00:43.880Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-summary-generation-on-clinical-narratives-summary-level-test</loc><lastmod>2026-02-26T06:00:43.860Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/item-level-evaluation-on-item-level-qa-dataset</loc><lastmod>2026-02-26T06:00:36.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summary-level-evaluation-on-narrative-dataset-summary-level-qa</loc><lastmod>2026-02-26T06:00:36.977Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-aishell-wer</loc><lastmod>2026-02-26T06:08:30.538Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/training-efficiency-on-telechat3-438b-workload-train</loc><lastmod>2026-02-26T06:04:47.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-decoding-on-gsm8k-constrained</loc><lastmod>2026-02-26T05:39:47.428Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-lingual-sentence-classification-on-xnli-language-transfer-test</loc><lastmod>2026-02-26T06:09:07.228Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-estimation-on-truthfulqa-test</loc><lastmod>2026-02-26T05:36:38.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-estimation-on-gsm8k-test</loc><lastmod>2026-02-26T05:36:38.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-dialogue-generation-on-dailydialog-test</loc><lastmod>2026-02-26T06:08:53.993Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-detection-on-songsage-lyric-centric-evaluation-set</loc><lastmod>2026-02-26T05:31:06.320Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generate-song-title-on-songsage-lyric-centric-evaluation-set</loc><lastmod>2026-02-26T05:43:32.858Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/infer-artist-on-songsage-lyric-centric-test</loc><lastmod>2026-02-26T05:42:28.527Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/playlist-to-description-on-songsage-playlist-centric-evaluation-set</loc><lastmod>2026-02-26T05:41:57.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/playlist-to-tags-on-songsage-playlist-centric-evaluation-set</loc><lastmod>2026-02-26T05:58:33.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-query-rewrite-on-songsage-playlist-centric-evaluation-set</loc><lastmod>2026-02-26T05:59:29.880Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-7-1-0-test</loc><lastmod>2026-02-26T05:31:06.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-6-1-0-test</loc><lastmod>2026-02-26T05:31:06.177Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-5-1-0-test</loc><lastmod>2026-02-26T05:31:06.163Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-4-1-0-test</loc><lastmod>2026-02-26T05:31:06.148Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-3-1-0-test</loc><lastmod>2026-02-26T05:31:05.995Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-2-1-0-test</loc><lastmod>2026-02-26T05:31:05.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-determination-on-medical-coverage-documents-plan-sharp-1-1-0-test</loc><lastmod>2026-02-26T05:31:05.966Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bengali-text-to-ipa-transcription-on-dual-ipa-test</loc><lastmod>2026-02-26T05:39:07.898Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-on-usmle</loc><lastmod>2026-02-26T05:31:05.950Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-generation-on-zerog-corpus-cleaned</loc><lastmod>2026-02-26T05:40:40.884Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-generation-on-zerog-corpus-raw</loc><lastmod>2026-02-26T06:11:25.113Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-generation-on-legislative-corpus-clean</loc><lastmod>2026-02-26T06:11:25.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personality-trait-steering-on-trait-openness</loc><lastmod>2026-02-26T05:54:16.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personality-trait-steering-on-trait-neuroticism</loc><lastmod>2026-02-26T06:07:38.450Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personality-trait-steering-on-trait-extraversion</loc><lastmod>2026-02-26T06:07:38.433Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personality-trait-steering-on-trait-conscientiousness</loc><lastmod>2026-02-26T06:07:38.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personality-trait-steering-on-trait-agreeableness</loc><lastmod>2026-02-26T06:07:38.399Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-model-inference-on-stories100m-110m-parameters</loc><lastmod>2026-02-26T06:06:34.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-question-answering-on-causal-rivers-real-world-zero-shot</loc><lastmod>2026-02-26T05:21:49.540Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/complexity-prediction-on-lmsys-chat-1m</loc><lastmod>2026-02-26T06:00:28.299Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/complexity-prediction-on-hotpotqa</loc><lastmod>2026-02-26T06:00:28.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/complexity-prediction-on-mmlu-plus-mmlu-pro-plus-gsm8k</loc><lastmod>2026-02-26T06:00:28.267Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coverage-based-alignment-on-iclr-50-submissions-2026</loc><lastmod>2026-02-26T06:04:48.331Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/score-based-alignment-on-iclr-2026-50-submissions</loc><lastmod>2026-02-26T05:59:14.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-indonesian-synthetic-clean-speech-test</loc><lastmod>2026-02-26T06:08:30.357Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-indonesian-synthetic-stuttered-speech-test</loc><lastmod>2026-02-26T06:08:30.345Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-chinese-english-translation-test</loc><lastmod>2026-02-26T05:21:46.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-policy-preservation-implicit-query-on-doc-pp-mistral-ocr-1-0-test</loc><lastmod>2026-02-26T05:45:10.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-policy-preservation-explicit-query-on-doc-pp-mistral-ocr-1-0-test</loc><lastmod>2026-02-26T05:45:10.837Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ted-talks-arabic-english-ar-en-test</loc><lastmod>2026-02-26T05:37:02.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ted-talks-hebrew-english-he-en-test</loc><lastmod>2026-02-26T05:37:02.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ted-talks-italian-english-it-en-test</loc><lastmod>2026-02-26T05:37:02.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ted-talks-german-english-de-en-test</loc><lastmod>2026-02-26T05:37:02.235Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-quality-evaluation-on-webgen-bench</loc><lastmod>2026-02-26T06:08:53.972Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-visualization-on-pandasplotbench-test</loc><lastmod>2026-02-26T05:39:27.820Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-mmteb</loc><lastmod>2026-02-26T05:50:03.429Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-20-diverse-prompts-fineweb-10bt-derived-test</loc><lastmod>2026-02-26T05:41:12.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/three-class-hinglish-classification-on-hinglish-24k-test</loc><lastmod>2026-02-26T05:31:03.696Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-generation-on-commongen</loc><lastmod>2026-02-26T05:31:03.435Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-deduction-on-spy</loc><lastmod>2026-02-26T05:31:03.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-games-on-matrix-games</loc><lastmod>2026-02-26T05:31:03.397Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-experience-evaluation-on-deepseek-v3-generated-dialogues-human-evaluation</loc><lastmod>2026-02-26T05:47:16.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fhir-resource-assembly-on-mimic-iv-demo-v2-2-test</loc><lastmod>2026-02-26T06:04:13.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relation-extraction-on-mimic-iv-demo-v2-2-test</loc><lastmod>2026-02-26T05:59:46.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-mimic-iv-demo-v2-2-test</loc><lastmod>2026-02-26T05:53:09.823Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sociocultural-clustering-on-d3-binary</loc><lastmod>2026-02-26T05:25:21.944Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sociocultural-clustering-on-dices-990-ordinal</loc><lastmod>2026-02-26T05:54:22.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rater-rationale-clustering-on-vp-value-ordinal-test</loc><lastmod>2026-02-26T05:54:22.571Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rater-rationale-clustering-on-vp-value-binary-test</loc><lastmod>2026-02-26T05:54:22.555Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rater-rationale-clustering-on-vp-right-binary-test</loc><lastmod>2026-02-26T05:54:22.541Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rater-rationale-clustering-on-vp-duty-ordinal-test</loc><lastmod>2026-02-26T05:54:22.527Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-learning-on-anthropic-hh-rlhf-plus-vi-preference-test</loc><lastmod>2026-02-26T05:54:25.556Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-vp-plus-schwartz-binary-test</loc><lastmod>2026-02-26T05:54:22.515Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rater-rationale-clustering-on-vp-right-ordinal-test</loc><lastmod>2026-02-26T05:54:22.503Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rater-rationale-clustering-on-vp-duty-binary-test</loc><lastmod>2026-02-26T05:54:22.487Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/implicit-analysis-on-iotoxicat-implicit-catalan-test</loc><lastmod>2026-02-26T05:31:02.856Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-hate-speech-english-test</loc><lastmod>2026-02-26T05:31:02.816Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toponym-retrieval-on-mehdie-average-across-5-testsets-test</loc><lastmod>2026-02-26T05:59:29.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/competitive-programming-on-livecodebench-v2</loc><lastmod>2026-02-26T06:03:52.399Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constituency-parsing-on-etstoel-test</loc><lastmod>2026-02-26T05:57:18.164Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotional-support-conversation-seeker-simulation-on-esc</loc><lastmod>2026-02-26T05:48:37.802Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-urdu-question-answering</loc><lastmod>2026-02-26T06:03:52.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-urdu-sentiment-analysis</loc><lastmod>2026-02-26T06:04:17.065Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-urdu</loc><lastmod>2026-02-26T06:03:52.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-japanese-english</loc><lastmod>2026-02-26T05:50:16.584Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-czech-german</loc><lastmod>2026-02-26T05:50:16.570Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-serbian</loc><lastmod>2026-02-26T05:50:16.553Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-chinese</loc><lastmod>2026-02-26T05:50:16.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-czech-ukrainian</loc><lastmod>2026-02-26T05:50:16.524Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-swahili</loc><lastmod>2026-02-26T05:50:16.512Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-korean</loc><lastmod>2026-02-26T05:50:16.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-marathi</loc><lastmod>2026-02-26T05:50:16.488Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-german</loc><lastmod>2026-02-26T05:50:16.474Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-mqm-human-evaluation-english-italian</loc><lastmod>2026-02-26T05:50:16.459Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/skill-extraction-on-real-world-job-advertisements</loc><lastmod>2026-02-26T05:25:41.294Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-plus-ko</loc><lastmod>2026-02-26T06:03:52.040Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-on-kmmlu-redux</loc><lastmod>2026-02-26T06:03:52.025Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-on-kmmlu</loc><lastmod>2026-02-26T06:03:52.010Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-code</loc><lastmod>2026-02-26T05:35:58.351Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-spanish</loc><lastmod>2026-02-26T05:35:58.335Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-japanese</loc><lastmod>2026-02-26T05:36:26.488Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-chinese</loc><lastmod>2026-02-26T05:35:58.318Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-english-reasoning</loc><lastmod>2026-02-26T05:35:58.302Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-english-general</loc><lastmod>2026-02-26T05:36:26.473Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-korean-math</loc><lastmod>2026-02-26T05:36:26.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-korean-reasoning</loc><lastmod>2026-02-26T05:36:26.440Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tokenization-on-korean-general</loc><lastmod>2026-02-26T05:36:26.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-simulation-quality-assessment-on-turn-level-human-evaluation-set-adversarial-test</loc><lastmod>2026-02-26T06:08:53.739Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-simulation-quality-assessment-on-session-level-human-evaluation-set-adversarial-test</loc><lastmod>2026-02-26T06:08:53.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-difficulty-estimation-on-naep-grade-12</loc><lastmod>2026-02-26T06:04:35.724Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-difficulty-estimation-on-naep-grade-8</loc><lastmod>2026-02-26T06:04:35.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-difficulty-estimation-on-naep-grade-4</loc><lastmod>2026-02-26T06:04:32.932Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/slot-value-extraction-on-proprietary-vietnamese-bfsi-debt-collection-test</loc><lastmod>2026-02-26T05:34:45.646Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/argument-persuasiveness-prediction-on-persuasion-for-good</loc><lastmod>2026-02-26T06:00:01.314Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/argument-persuasiveness-prediction-on-anthropic</loc><lastmod>2026-02-26T06:00:01.288Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-eng-mri</loc><lastmod>2026-02-27T10:47:29.020Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-mri-eng</loc><lastmod>2026-02-27T10:47:28.992Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/turn-taking-behavior-analysis-on-nguyen-2023-evaluation</loc><lastmod>2026-02-26T05:46:53.473Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-xsum-auc-and-tpr-at-1-percent-fpr-variants</loc><lastmod>2026-02-26T05:25:21.535Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-wikitext-comprehensive-metrics</loc><lastmod>2026-02-26T05:25:21.515Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-fidelity-on-user-study-complex</loc><lastmod>2026-02-26T06:08:53.710Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-fidelity-on-user-study-general</loc><lastmod>2026-02-26T06:08:53.696Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-user-study-complex</loc><lastmod>2026-02-26T06:08:53.683Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-user-study-general</loc><lastmod>2026-02-26T06:08:53.667Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/distributional-alignment-on-modplural-test</loc><lastmod>2026-02-26T05:47:36.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/steerable-alignment-on-modplural-test</loc><lastmod>2026-02-26T05:30:59.518Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overton-alignment-on-modplural-test</loc><lastmod>2026-02-26T06:08:10.431Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pre-training-on-fineweb-124m-transformer-val</loc><lastmod>2026-02-26T06:07:38.272Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-math-reasoning-1-5b-model-val</loc><lastmod>2026-02-26T06:08:06.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clinical-intent-alignment-on-healthbench</loc><lastmod>2026-02-26T05:38:21.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-medqa-test</loc><lastmod>2026-02-26T05:26:06.577Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/part-of-speech-tagging-on-turkish-pos-datasets-2-datasets-average</loc><lastmod>2026-02-26T05:55:08.847Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-mednli-turkish</loc><lastmod>2026-02-26T05:53:13.117Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-textual-similarity-on-turkish-sts-dataset</loc><lastmod>2026-02-26T06:03:33.358Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-turkish-qa-2-datasets-average</loc><lastmod>2026-02-26T05:59:05.740Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-turkish-ner-2-datasets-average</loc><lastmod>2026-02-26T05:53:09.836Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-turkish-classification-datasets-6-datasets-average</loc><lastmod>2026-02-26T05:38:27.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-language-understanding-on-turkish-non-retrieval-tasks-consolidated</loc><lastmod>2026-02-26T05:54:25.523Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-essay-scoring-on-asap-2-0-and-ellipse</loc><lastmod>2026-02-26T05:59:08.205Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-movie-tagging-on-lamp</loc><lastmod>2026-02-26T06:00:44.956Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-anomaly-detection-on-liar2</loc><lastmod>2026-02-26T05:25:41.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-anomaly-detection-on-emailspam</loc><lastmod>2026-02-26T05:25:41.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-question-answering-on-locomo-adversarial</loc><lastmod>2026-02-26T05:41:38.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/moral-foundation-coefficient-comparison-in-sacrificial-judgments-on-crone-and-laham-human-benchmark</loc><lastmod>2026-02-26T06:11:25.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/exploratory-counseling-on-expert-evaluation-dialogue</loc><lastmod>2026-02-26T05:59:07.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/counseling-response-generation-on-psyprobe-user-evaluation</loc><lastmod>2026-02-26T05:39:29.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/icd-9-cm-code-extraction-on-technetium-i-test</loc><lastmod>2026-02-26T05:52:48.297Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-cluster-level-summaries-held-out-set</loc><lastmod>2026-02-26T06:00:43.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audiovisual-dialogue-description-on-diadembench-multi-shot</loc><lastmod>2026-02-26T05:59:47.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audiovisual-dialogue-description-on-diadembench-single-shot</loc><lastmod>2026-02-26T05:59:47.016Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multitask-language-understanding-on-mmlu-f_clean-o-5</loc><lastmod>2026-02-26T05:26:50.633Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-o-5-f_clean</loc><lastmod>2026-02-26T05:34:15.604Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-en-dzo</loc><lastmod>2026-02-26T05:39:45.644Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reviewer-recommendation-on-lr-bench</loc><lastmod>2026-02-26T06:08:50.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-aharoni-and-goldberg-medical-law-it-and-subtitles-2020-test</loc><lastmod>2026-02-26T05:37:01.249Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-evaluation-on-user-fingertip-type-ii</loc><lastmod>2026-02-26T05:23:46.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-evaluation-on-user-fingertip-type-i</loc><lastmod>2026-02-26T05:23:46.384Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mobile-agent-task-execution-on-e-dataset-test</loc><lastmod>2026-02-26T06:05:51.632Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-average-accuracy</loc><lastmod>2026-02-26T05:30:57.015Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-mix-dataset</loc><lastmod>2026-02-26T05:34:20.322Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/issue-resolution-on-swe-bench-sphinx-verified-test</loc><lastmod>2026-02-26T05:30:56.964Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/issue-resolution-on-swe-bench-sympy-verified-test</loc><lastmod>2026-02-26T05:30:56.946Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/issue-resolution-on-swe-bench-django-verified-test</loc><lastmod>2026-02-26T05:30:56.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-mlc-slm-test</loc><lastmod>2026-02-26T05:30:56.576Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-mls-test</loc><lastmod>2026-02-26T05:30:56.539Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-mc1-mc2-metrics</loc><lastmod>2026-02-26T05:49:44.160Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factuality-evaluation-on-slimpajama</loc><lastmod>2026-02-26T05:58:07.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factuality-evaluation-on-factuality-benchmarks-aggregate-including-factscore-halueval-test</loc><lastmod>2026-02-26T05:45:57.079Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generation-quality-and-coherence-evaluation-on-slimpajama-quality-evaluation-test</loc><lastmod>2026-02-26T05:45:54.410Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-realtoxicityprompts-test</loc><lastmod>2026-02-26T06:03:37.938Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modelling-on-mathematical-expression-len-test</loc><lastmod>2026-02-26T05:42:28.206Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modelling-on-mathematical-expression-eq-conv-test</loc><lastmod>2026-02-26T05:42:28.191Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-domain-language-modeling-and-reasoning-on-multi-domain-evaluation-suite-general-code-math-mid-training</loc><lastmod>2026-02-26T05:45:56.006Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-error-correction-on-medmcqa-test</loc><lastmod>2026-02-26T06:08:29.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-error-correction-on-medqa-test</loc><lastmod>2026-02-26T06:08:29.214Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-error-correction-on-mmlu-test</loc><lastmod>2026-02-26T05:39:24.025Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/task-completion-on-internal-task-benchmark</loc><lastmod>2026-02-26T05:36:07.742Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-pass-at-1-maj-at-128-deepconf-at-128-chronos-at-128</loc><lastmod>2026-02-26T05:57:24.521Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-model-alignment-and-mixing-on-math-chat-if-and-general-qa-tasks-llama-3-1-8b-test</loc><lastmod>2026-02-26T05:51:39.386Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-routing-on-mmlu-pro-non-stem</loc><lastmod>2026-02-26T05:25:35.657Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-challenge-zh-en</loc><lastmod>2026-02-26T05:37:00.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-challenge-en-zh</loc><lastmod>2026-02-26T05:37:00.934Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-legal-inquiry-on-taiwanese-criminal-case-abstract-case-c</loc><lastmod>2026-02-26T05:39:38.188Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-legal-inquiry-on-taiwanese-criminal-case-complex-case-b</loc><lastmod>2026-02-26T05:39:38.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-legal-inquiry-on-taiwanese-criminal-case-simple-case-a</loc><lastmod>2026-02-26T05:39:38.161Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-russian-kazakh-competition-server-test</loc><lastmod>2026-02-26T06:09:11.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-russian-bashkir-competition-server-test</loc><lastmod>2026-02-26T06:09:11.901Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/predictive-modeling-of-garden-path-processing-on-reading-paradigm-data-eye-tracking-spr-and-maze-cross-validation</loc><lastmod>2026-02-26T05:40:39.779Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-language-understanding-on-include-5-shot</loc><lastmod>2026-02-26T05:30:52.142Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-language-understanding-on-mmmlu-5-shot</loc><lastmod>2026-02-26T05:30:52.124Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-output-prediction-on-cruxeval-o-1-shot</loc><lastmod>2026-02-26T05:30:52.111Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-input-prediction-on-cruxeval-i-1-shot</loc><lastmod>2026-02-26T05:30:52.094Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-plus-0-shot</loc><lastmod>2026-02-26T05:30:52.076Z</lastmod></url></urlset>