<?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/semantic-tagging-on-usas-irish-test</loc><lastmod>2026-02-26T06:06:46.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-tagging-on-usas-finnish-test</loc><lastmod>2026-02-26T06:06:46.789Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-tagging-on-usas-chinese-test</loc><lastmod>2026-02-26T06:06:46.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/motivational-interviewing-dialogue-generation-on-annomi-test</loc><lastmod>2026-02-26T05:39:23.989Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/donation-amount-prediction-on-persuasion-for-good-test</loc><lastmod>2026-02-26T05:50:53.314Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/post-argument-rating-regression-on-anthropic-dataset-september-2024</loc><lastmod>2026-02-26T05:50:53.297Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/glossing-on-multilingual-held-out-test</loc><lastmod>2026-02-26T05:52:56.933Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-translation-on-lowtranseval-test</loc><lastmod>2026-02-26T05:31:00.066Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/patient-message-response-drafting-on-ippm</loc><lastmod>2026-02-26T05:39:48.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-generation-on-bioasq</loc><lastmod>2026-02-26T05:30:59.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-augmented-generation-on-crag</loc><lastmod>2026-02-26T05:45:18.781Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-cambignq</loc><lastmod>2026-02-26T06:00:43.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-paqa</loc><lastmod>2026-02-26T06:00:43.799Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-search-on-qulac</loc><lastmod>2026-02-26T06:00:43.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-analysis-on-sst-2-roc-auc-pr-auc</loc><lastmod>2026-02-26T06:00:28.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detection-on-longform</loc><lastmod>2026-02-26T06:04:07.152Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detection-on-t-f</loc><lastmod>2026-02-26T05:45:47.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/detection-on-mcq</loc><lastmod>2026-02-26T05:40:48.532Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prevention-on-longform</loc><lastmod>2026-02-26T06:04:07.137Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prevention-on-t-f</loc><lastmod>2026-02-26T06:09:17.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prevention-on-mcq</loc><lastmod>2026-02-26T06:09:17.654Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/triple-classification-on-yago3-10-test</loc><lastmod>2026-03-18T07:39:16.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/triple-classification-on-fb15k-237-test</loc><lastmod>2026-02-26T05:30:59.169Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-udhr</loc><lastmod>2026-02-26T05:51:27.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-smol</loc><lastmod>2026-02-26T05:51:27.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-mcs-350</loc><lastmod>2026-02-26T05:51:31.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-mafand</loc><lastmod>2026-02-26T05:51:27.580Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-fineweb2</loc><lastmod>2026-02-26T05:51:27.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-bloom</loc><lastmod>2026-02-26T05:51:27.544Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-afroscope</loc><lastmod>2026-02-26T05:51:34.788Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-quality-assessment-on-s2s-arena</loc><lastmod>2026-02-26T05:39:48.689Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-quality-assessment-on-speakbench</loc><lastmod>2026-02-26T05:39:48.672Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-report-generation-on-ehrxqa</loc><lastmod>2026-02-26T05:37:18.802Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/style-transfer-on-carma-arabic-corpus</loc><lastmod>2026-02-26T05:59:12.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fake-news-detection-on-gossipcop-reformed-neutral-sentiment-test</loc><lastmod>2026-02-26T05:30:58.637Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fake-news-detection-on-reformed-politifact-neutral-sentiment-test</loc><lastmod>2026-02-26T05:30:58.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text2cypher-on-text2cypher-avg-english-spanish-turkish</loc><lastmod>2026-02-26T06:00:43.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text2cypher-on-text2cypher-turkish-test</loc><lastmod>2026-02-26T06:00:43.545Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text2cypher-on-text2cypher-spanish-test</loc><lastmod>2026-02-26T06:00:43.525Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text2cypher-on-text2cypher-english-test</loc><lastmod>2026-02-26T06:00:43.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/topic-classification-on-sib-176-languages</loc><lastmod>2026-02-26T06:03:51.641Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-qa-12-languages</loc><lastmod>2026-02-26T06:03:51.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/choice-of-plausible-alternatives-on-copa-11-languages</loc><lastmod>2026-02-26T06:03:51.604Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/part-of-speech-tagging-on-pos-80-languages</loc><lastmod>2026-02-26T06:03:51.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-ner-136-languages</loc><lastmod>2026-02-26T05:54:34.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-natural-language-processing-on-aggregate-234-languages</loc><lastmod>2026-02-26T06:03:51.565Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/risk-of-bias-assessment-in-medical-systematic-reviews-on-cochraneforest-test</loc><lastmod>2026-02-26T05:39:29.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-tweet-paraphrasing-on-lamp</loc><lastmod>2026-03-10T07:42:55.404Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-news-headline-generation-on-lamp</loc><lastmod>2026-03-10T07:42:55.378Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-good-credit-score</loc><lastmod>2026-02-26T05:24:52.243Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-room-occupancy</loc><lastmod>2026-02-26T05:24:52.221Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-blood-donation</loc><lastmod>2026-02-26T05:24:52.198Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-liver-disease</loc><lastmod>2026-02-26T05:24:52.179Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-anomaly-detection-on-n24news</loc><lastmod>2026-02-26T05:25:41.068Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/psychological-counseling-evaluation-on-core-evaluation-set-n-180-test</loc><lastmod>2026-02-26T06:02:03.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-deep-search-on-browsecomp-plus</loc><lastmod>2026-02-26T05:57:33.748Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-1983-2025-combined</loc><lastmod>2026-02-26T05:30:57.863Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-multi-turn-evaluation-on-nitibench</loc><lastmod>2026-02-26T05:30:57.815Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speaking-style-consistency-on-eval2000-test</loc><lastmod>2026-02-26T05:41:58.431Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-vietnamese-bahnar-translation-test</loc><lastmod>2026-02-26T05:37:10.511Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/content-validation-on-tiktok-health-videos</loc><lastmod>2026-02-26T05:42:51.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/child-automatic-speech-recognition-on-myst-1h</loc><lastmod>2026-02-26T06:08:29.931Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/child-automatic-speech-recognition-on-myst-5h</loc><lastmod>2026-02-26T06:08:29.918Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/child-automatic-speech-recognition-on-myst-10h</loc><lastmod>2026-02-26T06:08:29.905Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/child-automatic-speech-recognition-on-myst-full</loc><lastmod>2026-02-26T06:08:29.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-clean-plus-indoor-noise-seen-noise-test</loc><lastmod>2026-02-26T06:08:29.844Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-librispeech-clean-plus-outdoor-noise-unseen-test</loc><lastmod>2026-02-26T06:08:29.828Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phoneme-recognition-on-librispeech-clean-100h-noise-augmented-test</loc><lastmod>2026-02-26T05:55:00.685Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phoneme-recognition-on-librispeech-clean-plus-indoor-noise-100h-noise-augmented-test</loc><lastmod>2026-02-26T05:55:00.669Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phoneme-recognition-on-librispeech-clean-outdoor-100h-noise-augmented-test</loc><lastmod>2026-02-26T05:55:00.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/demographic-distribution-prediction-on-costa-rica-census</loc><lastmod>2026-02-26T05:52:38.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/demographic-distribution-prediction-on-chile-census</loc><lastmod>2026-02-26T05:52:38.174Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/demographic-distribution-prediction-on-armenia-census</loc><lastmod>2026-02-26T05:35:01.518Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/demographic-distribution-prediction-on-nepal-census</loc><lastmod>2026-02-26T05:39:07.381Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/demographic-distribution-prediction-on-uganda-census</loc><lastmod>2026-02-26T05:37:29.615Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/demographic-distribution-prediction-on-india-census</loc><lastmod>2026-02-26T05:46:27.579Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/record-linkage-on-multilingual-parties-40-percent-test</loc><lastmod>2026-02-26T05:30:56.902Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/record-linkage-on-organization-40-percent-test</loc><lastmod>2026-02-26T05:30:56.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/record-linkage-on-candidate-voter-test</loc><lastmod>2026-02-26T05:30:56.869Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/record-linkage-on-city-matching-40-percent-test</loc><lastmod>2026-02-26T05:30:56.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-intelligibility-assessment-on-tamil</loc><lastmod>2026-02-26T05:26:41.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-intelligibility-assessment-on-italian</loc><lastmod>2026-02-26T05:26:41.846Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-intelligibility-assessment-on-spanish</loc><lastmod>2026-02-26T05:26:41.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-intelligibility-assessment-on-english</loc><lastmod>2026-02-26T05:26:41.808Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-news-multilingual-15-languages-test</loc><lastmod>2026-02-26T06:08:29.782Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-fleurs-30-languages-test</loc><lastmod>2026-02-26T06:08:29.763Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-fleurs-20-languages-test</loc><lastmod>2026-02-26T06:08:29.747Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-fleurs-12-languages-test</loc><lastmod>2026-02-26T06:08:29.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-mlc-slm-11-languages-test</loc><lastmod>2026-02-26T06:08:29.711Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-commonvoice-13-languages-test</loc><lastmod>2026-06-16T08:36:58.741Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-common-sense-reasoning-on-piqa-hellaswag-wsc-boolq-race-h</loc><lastmod>2026-02-26T05:55:04.493Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-accuracy-and-length</loc><lastmod>2026-02-26T05:30:56.212Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-halueval-qa_samples</loc><lastmod>2026-02-26T05:43:31.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-pubmedqa-f1</loc><lastmod>2026-02-26T05:42:46.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-drop-history</loc><lastmod>2026-02-26T05:43:31.029Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-financebench-test</loc><lastmod>2026-02-26T05:43:30.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-yale-new-haven-health-ynhh-clinical-notes-three-site-experiment-test</loc><lastmod>2026-02-26T06:04:48.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-yale-new-haven-health-ynhh-clinical-notes-two-site-experiment-test</loc><lastmod>2026-02-26T06:04:48.984Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/missing-premise-test-on-mip-math</loc><lastmod>2026-02-26T05:30:55.880Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/missing-premise-test-on-gsm8k-mip</loc><lastmod>2026-02-26T05:30:55.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-squad-em-tokens-k</loc><lastmod>2026-02-26T05:41:37.821Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-em-tokens-k</loc><lastmod>2026-02-26T05:41:37.804Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-knowledge-on-mmlu-pro</loc><lastmod>2026-02-26T05:41:37.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-knowledge-on-mmlu</loc><lastmod>2026-02-26T05:41:37.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-evaluation-on-arc-hellaswag-lambada-piqa-sciq-winogrande-triviaqa-webqs-mmlu-gsm8k</loc><lastmod>2026-02-26T05:23:38.222Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialect-identification-on-mdialbench-rbt_model-1-0-turn-8</loc><lastmod>2026-02-26T05:30:55.543Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialect-identification-on-mdialbench-rbt_model-1-0-turn-4</loc><lastmod>2026-02-26T05:30:55.528Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialect-identification-on-mdialbench-rbt_model-turn-2-1-0</loc><lastmod>2026-02-26T05:30:55.512Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialect-identification-on-mdialbench-rbt_model-1-0-turn-1</loc><lastmod>2026-02-26T05:30:55.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speaker-diarization-on-english</loc><lastmod>2026-02-26T05:40:14.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speaker-diarization-on-chinese-hard</loc><lastmod>2026-02-26T05:40:14.547Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speaker-diarization-on-chinese</loc><lastmod>2026-02-26T05:40:14.532Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategic-ai-persuasion-receiver-on-mixtalk-combined</loc><lastmod>2026-02-26T05:37:26.912Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategic-ai-persuasion-receiver-on-mixtalk-large-environment</loc><lastmod>2026-02-26T05:37:26.895Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategic-ai-persuasion-receiver-on-mixtalk-small-environment</loc><lastmod>2026-02-26T05:37:26.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategic-ai-persuasion-sender-on-mixtalk-combined</loc><lastmod>2026-02-26T05:37:26.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategic-ai-persuasion-sender-on-mixtalk-large-environment</loc><lastmod>2026-02-26T05:37:26.945Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/strategic-ai-persuasion-sender-on-mixtalk-small-environment</loc><lastmod>2026-02-26T05:37:26.861Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoken-medical-question-answering-on-medmcqa-test</loc><lastmod>2026-02-26T05:59:05.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoken-medical-question-answering-on-medqa-test</loc><lastmod>2026-02-26T05:59:05.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoken-medical-question-answering-on-mmlu-test</loc><lastmod>2026-02-26T05:39:24.007Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-browsing-on-browsecomp-official</loc><lastmod>2026-02-26T05:42:28.103Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-retrieval-on-mteb-retrieval</loc><lastmod>2026-02-26T06:03:42.007Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/behavior-steering-on-attribute-steering-evaluation-open-ended-generation-qwen3-14b-based</loc><lastmod>2026-02-26T06:08:44.351Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/difficulty-assessment-on-competition-level-datasets-sample-of-300-questions</loc><lastmod>2026-02-26T05:40:20.231Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/computer-using-agent-task-on-wasp-1-0-test</loc><lastmod>2026-02-26T05:54:58.455Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/computer-using-agent-task-on-os-harm-1-0-test</loc><lastmod>2026-02-26T05:54:58.437Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/repository-reconstruction-on-repocraft-gold-projects</loc><lastmod>2026-02-26T05:40:02.229Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-training-throughput-on-qwen2-5-7b-128k-context-train</loc><lastmod>2026-02-26T06:06:26.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-training-throughput-on-qwen2-5-7b-64k-context-train</loc><lastmod>2026-02-26T06:06:26.326Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-on-mmmu-pro</loc><lastmod>2026-02-26T06:03:50.718Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/budgeted-subset-selection-on-ni-20-15-percent-retention-train</loc><lastmod>2026-02-26T06:07:30.020Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/budgeted-subset-selection-on-alpaca-15-percent-retention-train</loc><lastmod>2026-02-26T06:07:30.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/budgeted-subset-selection-on-ni-20-5-percent-retention</loc><lastmod>2026-02-26T06:03:33.745Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asynchronous-planning-on-nl-train</loc><lastmod>2026-02-26T05:30:53.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-classification-on-instructor</loc><lastmod>2026-02-26T06:01:13.820Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-gpqa-diamond-out-of-domain</loc><lastmod>2026-02-26T05:30:53.058Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-healthbench-500-conversation-out-of-domain</loc><lastmod>2026-02-26T05:46:26.049Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-medqa-in-domain</loc><lastmod>2026-02-26T05:30:53.038Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-math500-in-domain</loc><lastmod>2026-02-26T05:30:53.021Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-question-answering-on-askoverconfidence</loc><lastmod>2026-02-26T05:30:52.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/persona-grounded-dialogue-on-focus-test</loc><lastmod>2026-02-26T05:39:28.468Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-and-reasoning-on-upstream-tasks-suite-textvqa-pope-vqav2-mm-vet-scienceqa-img-mmbench-gqa-seed-bench</loc><lastmod>2026-02-26T05:26:29.561Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/continual-learning-on-sequential-5-cl-tasks-rs-med-ad-sci-fin</loc><lastmod>2026-02-26T06:00:48.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tool-use-on-spreadsheetbench</loc><lastmod>2026-02-26T06:05:10.018Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/function-calling-on-bfcl-v4-accuracy</loc><lastmod>2026-02-26T05:30:52.793Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-performance-on-acebench-zh</loc><lastmod>2026-02-26T05:30:52.776Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-retrieval-on-chinesesimpleqa</loc><lastmod>2026-02-26T05:30:52.762Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-retrieval-on-simpleqa</loc><lastmod>2026-02-26T05:30:52.744Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-understanding-on-videomme-with-subtitles</loc><lastmod>2026-02-26T05:30:52.644Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-vqa-on-cv-bench</loc><lastmod>2026-02-26T05:30:52.612Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-vqa-on-blink</loc><lastmod>2026-02-26T05:30:52.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-vqa-on-simplevqa</loc><lastmod>2026-02-26T05:30:52.563Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-understanding-on-chartxiv-rq</loc><lastmod>2026-02-26T05:30:52.546Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stem-and-reasoning-on-vlmareblind</loc><lastmod>2026-02-26T05:30:52.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stem-and-reasoning-on-visulogic</loc><lastmod>2026-02-26T05:30:52.478Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-com-2-hard-intervention-test</loc><lastmod>2026-02-26T05:30:51.693Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-mgsm-thai</loc><lastmod>2026-02-26T06:03:52.418Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-based-decision-making-on-2-bench-retail-telecom-airline</loc><lastmod>2026-02-26T06:02:09.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/role-playing-on-role-playing-evaluation-minor-characters</loc><lastmod>2026-02-26T05:47:41.499Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stem-question-answering-on-gpqa-main</loc><lastmod>2026-02-26T05:30:51.100Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/caption-generation-on-electronic-sheep</loc><lastmod>2026-02-26T05:21:39.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/funny-caption-generation-on-humor-in-ai</loc><lastmod>2026-02-26T05:21:39.718Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-random-5-problems</loc><lastmod>2026-02-26T06:04:41.119Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/runtime-controllability-on-pact-test</loc><lastmod>2026-02-26T05:39:36.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/runtime-controllability-on-cosapien-test</loc><lastmod>2026-02-26T05:34:52.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-seeking-on-deepwide-search-benchmark</loc><lastmod>2026-02-26T05:39:30.788Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-on-mbpp-base-and-extended-out-of-distribution</loc><lastmod>2026-02-26T05:30:50.778Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-on-humaneval-base-and-extended-out-of-distribution</loc><lastmod>2026-02-26T05:30:50.761Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-phybench</loc><lastmod>2026-02-26T05:30:50.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-mmlu-redux-acc-tok-lat</loc><lastmod>2026-02-26T05:30:50.725Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/synthetic-in-context-reasoning-on-mad</loc><lastmod>2026-05-20T07:38:24.236Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/abstractive-summarization-on-tofueval</loc><lastmod>2026-02-26T05:54:34.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrase-detection-on-qqp-w-types</loc><lastmod>2026-02-26T05:30:50.597Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrase-detection-on-qqp-w-o-types</loc><lastmod>2026-02-26T05:30:50.585Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrase-type-detection-on-etpc</loc><lastmod>2026-02-26T05:30:50.573Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-2-hop-qa-parametric-knowledge</loc><lastmod>2026-02-26T05:30:50.424Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-2-hop-qa-full-knowledge</loc><lastmod>2026-02-26T05:26:45.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-ruler-hqa-1-75m-context-length</loc><lastmod>2026-02-26T06:04:51.535Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-sudoku-9x9</loc><lastmod>2026-02-26T05:30:50.071Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-alignment-on-alpaca-7b-test</loc><lastmod>2026-02-26T05:46:20.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-response-generation-on-bitext-retail-banking-llm-chatbot-test</loc><lastmod>2026-02-26T05:37:00.849Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-human-evaluation</loc><lastmod>2026-02-26T05:39:29.879Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/verification-classification-on-talk-moves-n-6-110-held-out-test</loc><lastmod>2026-02-26T05:58:30.614Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sae-label-evaluation-on-goodfire-sae-latents-held-out</loc><lastmod>2026-02-26T05:46:27.980Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/research-automation-on-researchrubrics</loc><lastmod>2026-02-26T06:03:50.275Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-analysis-on-data-analysis-benchmark</loc><lastmod>2026-02-26T05:36:31.255Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-aime-2025-avg-at-16-pass-at-16</loc><lastmod>2026-02-26T05:22:27.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-aime-2024-avg-at-16-pass-at-16</loc><lastmod>2026-02-26T06:09:07.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-evaluation-on-figstep-average</loc><lastmod>2026-02-26T05:35:10.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memory-discrimination-on-gid-1k</loc><lastmod>2026-02-26T05:26:45.425Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/patient-simulation-on-client-therapist-interactions-bad-therapist-persona</loc><lastmod>2026-02-26T05:45:08.165Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/patient-simulation-on-client-therapist-interactions-cbt-therapist-persona</loc><lastmod>2026-02-26T05:45:08.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-ruler-mrcr-and-nolima</loc><lastmod>2026-02-26T05:35:50.551Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-nolima</loc><lastmod>2026-02-26T05:34:01.829Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-ruler-64k-and-128k-contexts</loc><lastmod>2026-02-26T06:00:52.155Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-simplification-on-cve-test</loc><lastmod>2026-02-26T05:44:49.770Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-and-reranking-on-locomo-test</loc><lastmod>2026-02-26T06:01:39.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-tps-latency-accuracy</loc><lastmod>2026-02-26T06:06:00.681Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-latency-throughput-length-steps</loc><lastmod>2026-02-26T06:06:24.963Z</lastmod></url></urlset>