<?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/local-image-retrieval-image-to-image-on-ilias</loc><lastmod>2026-02-26T06:10:03.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/local-image-retrieval-text-to-image-on-ilias</loc><lastmod>2026-02-26T06:10:03.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/local-image-retrieval-text-to-image-on-reircoco</loc><lastmod>2026-02-26T06:01:26.631Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/local-image-retrieval-text-to-image-on-sorce-1k</loc><lastmod>2026-02-26T06:01:26.619Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-text-to-image-generation-on-t2i-compbench-plus-plus-test</loc><lastmod>2026-04-07T09:56:19.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-video-grounding-on-qvhighlights-timelens-test</loc><lastmod>2026-02-26T06:01:20.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-video-grounding-on-charades-timelens-test</loc><lastmod>2026-02-26T05:59:21.312Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ood-detection-on-svhn</loc><lastmod>2026-06-09T09:23:38.262Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-vocabulary-object-goal-navigation-on-hm3d-ovon-test</loc><lastmod>2026-03-31T12:37:09.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-generation-on-vbench-60s</loc><lastmod>2026-06-16T06:47:34.578Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-visual-understanding-on-hr-bench-8k</loc><lastmod>2026-02-26T06:03:54.452Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/closed-loop-planning-on-navsim-v1</loc><lastmod>2026-06-05T08:10:37.903Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-report-generation-on-iu-xray</loc><lastmod>2026-02-26T06:00:44.037Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medical-text-qa-suite</loc><lastmod>2026-02-26T05:50:02.456Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/monocular-visual-odometry-on-vivid-in_unst_local</loc><lastmod>2026-02-26T05:24:12.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/monocular-visual-odometry-on-vivid-in_rob_global</loc><lastmod>2026-02-26T05:24:12.362Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lvef-estimation-on-echonet-pediatric</loc><lastmod>2026-02-26T05:49:19.918Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-restoration-on-reds30</loc><lastmod>2026-02-26T05:56:45.723Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/geometry-problem-solving-on-formalgeo7k</loc><lastmod>2026-02-26T06:07:08.153Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-reconstruction-on-imagenet-1k</loc><lastmod>2026-05-08T08:35:47.343Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-image-spatial-reasoning-on-mindcube-tiny-test</loc><lastmod>2026-02-26T05:35:01.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-generation-on-flickr30k-2015-test</loc><lastmod>2026-06-23T11:52:32.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-generation-on-coco-2014-val</loc><lastmod>2026-07-07T06:42:56.115Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-rsvqa-hr-test</loc><lastmod>2026-02-26T05:46:14.734Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-perception-on-cv-bench</loc><lastmod>2026-06-09T06:35:32.115Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-image-generation-on-unigenbench</loc><lastmod>2026-02-26T06:07:52.956Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-enron-acc-asr</loc><lastmod>2026-02-26T05:21:50.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-yelp-acc-asr</loc><lastmod>2026-02-26T05:31:20.165Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-classification-on-twit</loc><lastmod>2026-02-26T05:31:20.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intrusion-detection-on-intrusion-detection-in-internet-of-vehicles-dataset</loc><lastmod>2026-02-26T05:31:19.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-llama3-1-405b-1-0-test</loc><lastmod>2026-02-26T05:23:54.692Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-gpt-4o-mini-1-0-test</loc><lastmod>2026-02-26T05:23:54.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-gpt-4o-1-0-test</loc><lastmod>2026-02-26T05:23:54.648Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-gpt-4-turbo-1-0-test</loc><lastmod>2026-02-26T05:23:54.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-advbench-gpt-4-1-0-test</loc><lastmod>2026-02-26T05:23:54.607Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/objective-c-type-recovery-on-motif-bench</loc><lastmod>2026-02-26T05:36:04.789Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-multiple-choice-question-answering-on-redsage-mcq-test</loc><lastmod>2026-02-26T05:51:22.121Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overall-cybersecurity-performance-on-cybersecurity-multi-benchmark-suite</loc><lastmod>2026-02-26T05:54:31.167Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-knowledge-and-malware-extraction-analysis-on-secure</loc><lastmod>2026-02-26T05:47:41.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-evaluation-on-sceva</loc><lastmod>2026-02-26T05:49:46.577Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-benchmarking-on-scben-en</loc><lastmod>2026-02-26T05:41:59.487Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-knowledge-evaluation-on-cymtc-500</loc><lastmod>2026-02-26T05:40:09.310Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-threat-intelligence-analysis-on-cti-bench</loc><lastmod>2026-02-26T05:49:46.562Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-language-understanding-and-reasoning-on-open-llm-leaderboard-lighteval-test</loc><lastmod>2026-02-26T05:51:52.701Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-watermarking-on-ljspeech-2017</loc><lastmod>2026-02-26T06:03:33.068Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/secure-code-generation-on-cyberseceval-scg</loc><lastmod>2026-02-26T06:03:37.496Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-audio-retrieval-on-clotho-v2-test</loc><lastmod>2026-06-19T08:44:03.526Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-to-text-retrieval-on-clotho-v2-test</loc><lastmod>2026-06-19T08:44:03.605Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-information-retention-on-mine-1</loc><lastmod>2026-05-14T09:30:42.901Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-lcb-percent-avg-at-4</loc><lastmod>2026-02-26T05:21:46.640Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-percent-avg-at-4</loc><lastmod>2026-02-26T05:36:32.379Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-reasoning-on-gpqa-diamond-avg-at-4</loc><lastmod>2026-02-26T05:36:32.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-percent-avg-at-4</loc><lastmod>2026-02-26T05:36:32.362Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-commonsense-reasoning-on-commonsense-reasoning-benchmarks-llama-2-13b</loc><lastmod>2026-02-26T05:37:53.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-perplexity-evaluation-zero-shot</loc><lastmod>2026-02-26T05:55:12.127Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-olympiadbench</loc><lastmod>2026-07-03T06:16:42.796Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-average-popqa-nq-hotpotqa-2wiki-musique</loc><lastmod>2026-02-26T05:41:39.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-to-video-temporal-grounding-on-chronusav</loc><lastmod>2026-07-07T07:56:26.005Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-to-audio-temporal-grounding-on-chronusav</loc><lastmod>2026-07-07T07:56:25.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-audio-temporal-grounding-on-chronusav</loc><lastmod>2026-07-07T07:56:25.960Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-longbench-difficulty-and-length-aggregation</loc><lastmod>2026-02-26T05:54:28.799Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-carp-en</loc><lastmod>2026-06-30T08:23:01.928Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-score</loc><lastmod>2026-02-26T06:03:53.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-bolmo-evaluation-suite-mc-stem-7b</loc><lastmod>2026-02-26T05:49:44.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/metric-correlation-analysis-on-synthetic-perturbation-sets-test</loc><lastmod>2026-02-26T06:04:38.683Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-en-ja-2023-dev</loc><lastmod>2026-02-26T05:38:42.271Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-on-harmbench-example-based-llama3-8b</loc><lastmod>2026-04-16T06:55:54.789Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-qmsum-val</loc><lastmod>2026-02-26T06:00:43.963Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-govreport-val</loc><lastmod>2026-02-26T06:00:43.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-instruction-following-on-taskcraft</loc><lastmod>2026-02-26T05:57:50.945Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-x-test</loc><lastmod>2026-06-23T11:52:01.602Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/proactive-next-utterance-prediction-on-crosswoz-test</loc><lastmod>2026-02-26T05:48:09.442Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/proactive-next-utterance-prediction-on-wildchat-test</loc><lastmod>2026-02-26T05:48:09.424Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/proactive-next-utterance-prediction-on-sharegpt-test</loc><lastmod>2026-02-26T05:48:09.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/proactive-next-utterance-prediction-on-lmsys-test</loc><lastmod>2026-02-26T05:48:09.391Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-seeking-on-xbench-2505-full</loc><lastmod>2026-02-26T06:11:14.958Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/massive-multi-discipline-audio-understanding-on-mmau</loc><lastmod>2026-03-20T09:39:34.662Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-m-am-and-g8-am-accuracy</loc><lastmod>2026-02-26T05:34:16.506Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-wmt-2025-test</loc><lastmod>2026-02-26T06:09:03.270Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-200-xx-xx-2022</loc><lastmod>2026-02-26T06:09:03.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-200-en-xx-2022</loc><lastmod>2026-02-26T06:09:03.243Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-zh-xx-on-flores-200-2022</loc><lastmod>2026-02-26T06:09:03.229Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-accuracy-on-tau2-bench</loc><lastmod>2026-06-30T10:35:59.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-problem-solving-on-scibench</loc><lastmod>2026-02-26T05:57:35.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-neko-test</loc><lastmod>2026-02-26T06:09:03.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/aspect-term-extraction-on-laptop-2014-test</loc><lastmod>2026-02-26T05:43:32.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constituency-parsing-on-trappen-middle-dutch-test</loc><lastmod>2026-02-26T05:43:32.402Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constituency-parsing-on-tafel-middle-dutch-test</loc><lastmod>2026-02-26T05:43:32.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constituency-parsing-on-crm-middle-dutch-test</loc><lastmod>2026-02-26T05:42:46.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-mimotable</loc><lastmod>2026-02-26T05:31:02.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-reasontabqa-1-0-test</loc><lastmod>2026-02-26T05:31:02.574Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/subjective-medical-ethics-evaluation-on-subjective-medical-ethics-test</loc><lastmod>2026-02-26T06:02:20.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-mmlu-prox-health</loc><lastmod>2026-02-26T05:34:30.225Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-global-mmlu-medical-multilingual</loc><lastmod>2026-02-26T05:34:30.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-knowledge-graph-question-answering-on-qald-en-10</loc><lastmod>2026-06-02T07:52:46.725Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bias-evaluation-on-kobbq</loc><lastmod>2026-03-23T10:11:35.460Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trustworthiness-evaluation-on-llm-trustworthiness-benchmark</loc><lastmod>2026-03-23T10:11:35.491Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/turn-taking-on-full-duplex-bench</loc><lastmod>2026-04-15T10:05:51.134Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multitask-language-understanding-on-global-mmlu-lite</loc><lastmod>2026-06-08T06:39:58.733Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-grailqa-zero-shot</loc><lastmod>2026-02-26T05:46:35.848Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-grailqa-compositional</loc><lastmod>2026-02-26T05:46:35.833Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-grailqa-i-i-d</loc><lastmod>2026-02-26T05:46:35.819Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-ag-news</loc><lastmod>2026-05-26T12:26:11.746Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/acceptance-prediction-on-iclr-2024-2025-and-neurips-2023-2024-test</loc><lastmod>2026-02-26T05:30:59.553Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/average-rating-prediction-on-research-paper-rating-dataset-test</loc><lastmod>2026-02-26T05:50:53.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-flow-control-on-confaide-tier-3-infoflow-control</loc><lastmod>2026-02-26T05:48:33.833Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-expectation-estimation-on-confaide-tier-2-infoflow-expectation</loc><lastmod>2026-02-26T06:04:15.495Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-sensitivity-estimation-on-confaide-tier-1-info-sensitivity</loc><lastmod>2026-02-26T06:04:15.476Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/answer-generation-on-topiocqa</loc><lastmod>2026-02-26T05:43:32.132Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-resistance-behavior-dataset-5-fold-cv-test</loc><lastmod>2026-02-26T05:58:48.095Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fine-grained-classification-on-resistance-behavior-dataset-5-fold-cv-test</loc><lastmod>2026-02-26T05:45:18.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/theory-of-mind-on-tombench-ood</loc><lastmod>2026-02-26T05:41:58.298Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-reasoning-on-motivebench-ood-test</loc><lastmod>2026-02-26T05:34:53.861Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/social-intelligence-reasoning-on-cognitive-genome-in-domain-1-0-test</loc><lastmod>2026-02-26T05:47:30.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-editing-on-canitedit</loc><lastmod>2026-02-26T05:57:24.864Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-editing-on-aider-whole-format</loc><lastmod>2026-02-26T05:35:59.217Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-naturalcodebench</loc><lastmod>2026-02-26T05:53:02.497Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-visual-deepfake-detection-on-fakeavceleb</loc><lastmod>2026-05-01T08:49:51.159Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-segmentation-on-choi-s-dataset-3-11</loc><lastmod>2026-02-26T05:58:04.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-segmentation-on-choi-s-dataset-9-11</loc><lastmod>2026-02-26T05:58:04.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-segmentation-on-choi-s-dataset-6-8</loc><lastmod>2026-02-26T05:58:04.622Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-segmentation-on-choi-s-dataset-3-5</loc><lastmod>2026-02-26T05:58:04.608Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-fleurs-tamil</loc><lastmod>2026-03-18T08:16:46.655Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tool-use-on-2-bench-retail-and-telecom</loc><lastmod>2026-02-26T05:54:38.294Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-drop-nfl</loc><lastmod>2026-02-26T05:43:31.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-covidqa</loc><lastmod>2026-02-26T05:42:46.695Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-ragtruth</loc><lastmod>2026-02-26T05:43:31.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-question-answering-on-llamaq</loc><lastmod>2026-07-08T08:02:38.464Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/academic-illustration-generation-on-paperbananabench</loc><lastmod>2026-06-01T07:55:00.323Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiad-bench-pass-at-1-at-16-avg-tokens-ae-score</loc><lastmod>2026-02-26T05:57:34.540Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-pass-at-1-at-16-token-cost-ae-score</loc><lastmod>2026-02-26T05:57:32.017Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-pass-at-1-avg-at-16</loc><lastmod>2026-02-26T05:57:32.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-performance-on-general-evaluation-suite</loc><lastmod>2026-02-26T05:30:54.181Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-avg-at-8-and-token-usage</loc><lastmod>2026-02-26T05:34:09.680Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-pass-at-1-token-usage</loc><lastmod>2026-02-26T05:34:23.130Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime25-accuracy-avg-at-8-token-usage</loc><lastmod>2026-02-26T05:34:09.659Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-accuracy-pass-at-1-and-token-usage</loc><lastmod>2026-02-26T05:34:23.111Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-ifbench</loc><lastmod>2026-02-26T05:30:54.107Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-accuracy-on-infobench</loc><lastmod>2026-02-26T05:30:54.091Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-followbench-accuracy</loc><lastmod>2026-02-26T05:30:54.058Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-proof-verification-on-proofbench</loc><lastmod>2026-04-07T11:05:59.385Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-longbench-summary-test</loc><lastmod>2026-03-20T08:57:14.525Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-msmarco-test</loc><lastmod>2026-02-26T05:43:30.869Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grounded-ecg-interpretation-on-ecg-grounding</loc><lastmod>2026-02-26T05:40:49.579Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/online-language-modeling-on-pg-19-whole-book</loc><lastmod>2026-02-26T05:55:12.146Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gec-metric-meta-evaluation-on-seeda-e-fluency-setting</loc><lastmod>2026-02-26T05:57:43.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-aggregate-gpqa-hle-mmlu-pro</loc><lastmod>2026-02-26T05:35:50.762Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-hle</loc><lastmod>2026-02-26T06:11:14.737Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-general</loc><lastmod>2026-02-26T05:57:23.910Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-accuracy-percent</loc><lastmod>2026-02-26T05:30:50.033Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-wng-l</loc><lastmod>2026-02-26T05:30:49.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-steuerex-1-0-n-115</loc><lastmod>2026-02-26T06:07:27.459Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-reasoning-on-language-task-suite-copa-hs-lb-obqa-piqa-race-sciq-arc-siqa-wg</loc><lastmod>2026-02-26T05:38:43.049Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-openwebtext-standard-test</loc><lastmod>2026-02-26T05:57:54.945Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-detectiveqa</loc><lastmod>2026-06-23T07:40:17.649Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-question-answering-on-lsat</loc><lastmod>2026-04-28T09:31:15.431Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-capability-estimation-on-general-capability-estimation-framework-1-0</loc><lastmod>2026-02-26T05:42:23.197Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-official-evaluation</loc><lastmod>2026-02-26T05:42:30.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-official-evaluation</loc><lastmod>2026-02-26T05:41:42.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-based-question-answering-on-toolqa-hard</loc><lastmod>2026-02-26T05:34:30.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-question-answering-on-toolqa-easy-1-0</loc><lastmod>2026-02-26T06:09:04.681Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-docking-on-braf</loc><lastmod>2026-02-26T05:52:00.747Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-summarization-on-tvsum-single-ground-truth-test</loc><lastmod>2026-02-26T05:43:29.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-summarization-on-summe-single-ground-truth-test</loc><lastmod>2026-02-26T05:43:29.952Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/evaluation-of-metrics-alignment-with-human-judgment-on-radevalx</loc><lastmod>2026-06-16T07:10:25.169Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-reasoning-on-vsp</loc><lastmod>2026-06-02T08:27:17.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/online-bin-packing-problem-on-weibull-bpp-10k-500</loc><lastmod>2026-02-26T05:45:53.513Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/online-bin-packing-problem-on-weibull-bpp-10k-100</loc><lastmod>2026-02-26T05:45:53.537Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-mathematical-reasoning-on-geoqa-8k-test</loc><lastmod>2026-05-28T09:22:03.337Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiad-score</loc><lastmod>2026-02-26T06:03:51.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-evaluation-on-secbench</loc><lastmod>2026-02-26T05:30:45.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cybersecurity-knowledge-evaluation-on-mmlu-security</loc><lastmod>2026-02-26T05:30:45.399Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerability-prediction-on-cwe-prediction</loc><lastmod>2026-02-26T05:30:45.381Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cyber-threat-intelligence-reasoning-on-cti-reasoning</loc><lastmod>2026-02-26T06:03:49.555Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/attack-technique-extraction-on-ctibench-ate</loc><lastmod>2026-02-26T05:52:43.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vulnerability-severity-prediction-on-ctibench-vsp</loc><lastmod>2026-02-26T05:35:20.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/root-cause-mapping-on-ctibench-rcm</loc><lastmod>2026-02-26T06:03:49.537Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-question-answering-on-ctibench-mcqa</loc><lastmod>2026-02-26T06:03:49.519Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autonomous-driving-capability-on-drivebench</loc><lastmod>2026-02-26T05:57:46.760Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/high-level-reasoning-on-hle</loc><lastmod>2026-02-26T05:35:50.314Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-task-on-sudoku</loc><lastmod>2026-02-26T06:05:39.087Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-task-on-frozenlake</loc><lastmod>2026-02-26T06:04:54.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-task-on-blocksworld-sr-auv</loc><lastmod>2026-02-26T06:04:54.570Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-behavior-adaptation-on-webshop-ws-test</loc><lastmod>2026-02-26T05:48:45.366Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-behavior-adaptation-on-alfworld-aw-test</loc><lastmod>2026-02-26T05:48:45.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-behavior-adaptation-on-sudoku-su-test</loc><lastmod>2026-02-26T05:48:45.329Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-behavior-adaptation-on-frozenlake-fl-test</loc><lastmod>2026-02-26T05:48:45.312Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-behavior-adaptation-on-blocksworld-bw-test</loc><lastmod>2026-02-26T05:48:45.294Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-geo-at-rna</loc><lastmod>2026-02-26T05:49:48.675Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-geo-at-dna</loc><lastmod>2026-02-26T05:49:48.657Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-geo-at-protein</loc><lastmod>2026-02-26T05:49:48.640Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-reasoning-on-geo-at-molecule</loc><lastmod>2026-02-26T05:49:48.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-task-planning-on-alfworld-test</loc><lastmod>2026-02-26T06:05:36.909Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-covid-19-60-t</loc><lastmod>2026-02-26T06:00:00.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-covid-19-30-t</loc><lastmod>2026-02-26T06:00:00.844Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-israel-palestine-60-t</loc><lastmod>2026-02-26T06:00:00.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-israel-palestine-30-t</loc><lastmod>2026-02-26T06:00:00.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-u-s-election-60-t</loc><lastmod>2026-02-26T06:00:00.793Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-u-s-election-30-t</loc><lastmod>2026-02-26T06:00:00.775Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-dynamics-modeling-on-delhi-election-60-t</loc><lastmod>2026-02-26T06:00:00.748Z</lastmod></url></urlset>