<?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/spoken-dialogue-system-sds-semantic-quality-evaluation-on-eval2000-test</loc><lastmod>2026-02-26T06:00:43.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-quality-evaluation-on-eval2000</loc><lastmod>2026-02-26T06:07:51.372Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ntrex-en-jp-test</loc><lastmod>2026-02-26T05:39:45.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ntrex-en-fr-test</loc><lastmod>2026-02-26T05:39:45.700Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ntrex-en-es-test</loc><lastmod>2026-02-26T05:39:45.686Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-ntrex-en-ar-test</loc><lastmod>2026-02-26T05:39:45.672Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/benchmark-quality-evaluation-on-vlsafetybencher</loc><lastmod>2026-02-26T05:48:51.034Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-understanding-and-code-generation-on-llama-1b-evaluation-suite-v3-2</loc><lastmod>2026-02-26T05:23:37.490Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/few-shot-language-evaluation-on-arc-hellaswag-mmlu-truthfulqa-and-winogrande</loc><lastmod>2026-02-26T05:23:37.731Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-on-mbpp-plus</loc><lastmod>2026-02-26T05:30:57.211Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-on-amc-12</loc><lastmod>2026-02-26T05:30:57.197Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-on-aime-extend</loc><lastmod>2026-02-26T05:30:57.179Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-sarcasm-explanation-on-mustard-speaker-dependent</loc><lastmod>2026-02-26T06:00:36.677Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-sarcasm-detection-on-mustard-speaker-dependent</loc><lastmod>2026-02-26T05:58:32.560Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-sarcasm-explanation-on-wits</loc><lastmod>2026-02-26T05:46:42.173Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relation-extraction-on-tacred-fs</loc><lastmod>2026-02-26T05:43:31.327Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-standard-nlp-benchmarks-em</loc><lastmod>2026-02-26T05:42:28.221Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-generation-on-standard-nlp-benchmarks</loc><lastmod>2026-02-26T05:37:01.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-standard-nlp-benchmarks</loc><lastmod>2026-02-26T05:55:10.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-tip</loc><lastmod>2026-02-26T05:58:32.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/singing-voice-transcription-on-mir-1k-vocal</loc><lastmod>2026-02-26T06:08:29.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/singing-voice-transcription-on-m4singer</loc><lastmod>2026-02-26T06:08:37.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-cv-zh-tw</loc><lastmod>2026-02-26T05:38:15.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-fleurs-yue</loc><lastmod>2026-02-26T05:38:15.165Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-fleurs-test</loc><lastmod>2026-03-12T08:33:13.080Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-identification-on-commonvoice-test</loc><lastmod>2026-03-12T08:33:13.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-longembed-6-test</loc><lastmod>2026-02-26T05:53:05.543Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-coir-8-test</loc><lastmod>2026-02-26T05:53:05.529Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-mteb-10-v2-test</loc><lastmod>2026-02-26T05:53:05.496Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-beir-15-test</loc><lastmod>2026-02-26T05:53:05.480Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-steering-on-mdlm-long-sequence-generation-512-length-test</loc><lastmod>2026-02-27T10:44:26.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toxicity-steering-on-mdlm-long-sequence-generation-512-length-test</loc><lastmod>2026-02-27T10:44:26.597Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-class-classification-on-banglaabuse-task-b</loc><lastmod>2026-02-26T05:51:27.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-reasoning-on-gpqa-diamond-out-of-distribution</loc><lastmod>2026-02-26T05:30:55.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-test-accuracy-token-count-latency</loc><lastmod>2026-02-26T05:30:55.895Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-amc23-aime24-aime25</loc><lastmod>2026-02-26T05:51:35.882Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-maj-debate-delta</loc><lastmod>2026-02-26T05:51:35.831Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-maj-debate-delta</loc><lastmod>2026-02-26T05:51:35.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-23-maj-debate-delta</loc><lastmod>2026-02-26T05:51:35.792Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-maj-debate-delta</loc><lastmod>2026-02-26T05:51:35.805Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/maze-navigation-on-maze-navigation</loc><lastmod>2026-02-26T06:05:10.083Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-text-generation-on-lccc-test</loc><lastmod>2026-02-26T05:43:30.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-text-generation-on-weibo-test</loc><lastmod>2026-02-26T05:43:30.950Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-text-generation-on-douban-test</loc><lastmod>2026-02-26T05:43:30.932Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-text-generation-on-lccc</loc><lastmod>2026-02-26T05:47:12.849Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-text-generation-on-weibo</loc><lastmod>2026-02-26T05:47:12.828Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/short-text-generation-on-douban</loc><lastmod>2026-02-26T05:47:12.809Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-question-answering-on-average-llamaq-triviaqa-webq</loc><lastmod>2026-02-26T05:30:55.463Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-speech-on-voxpopuli</loc><lastmod>2026-02-26T06:08:29.342Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-speech-on-ls-clean</loc><lastmod>2026-02-26T06:09:00.800Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-task-evaluation-on-mt-bench-writing-roleplay-humanities-subset</loc><lastmod>2026-02-26T06:09:02.743Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-limo</loc><lastmod>2026-02-26T05:48:35.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sensorimotor-association-prediction-on-nonce-word-human-study-lancaster-sensorimotor-norms-1-0</loc><lastmod>2026-02-26T05:57:42.269Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/assistant-tasks-on-gaia-official</loc><lastmod>2026-02-26T05:42:28.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-comp-math</loc><lastmod>2026-02-26T05:30:54.227Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/latency-evaluation-on-multinews</loc><lastmod>2026-02-26T05:42:00.570Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/latency-evaluation-on-narrativeqa</loc><lastmod>2026-02-26T05:42:00.553Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-trait-automated-essay-scoring-on-asap-plus-plus-32-data-setting-test</loc><lastmod>2026-02-26T05:54:34.535Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-essay-scoring-on-asap-plus-plus-32-data-setting-test</loc><lastmod>2026-02-26T05:59:08.320Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/guide-target-element-selection-on-guideweb</loc><lastmod>2026-02-26T05:58:32.468Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intent-and-guide-text-generation-on-guideweb</loc><lastmod>2026-02-26T05:47:16.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-mcv-accent-unseen-all-600h-test</loc><lastmod>2026-02-26T06:08:29.198Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-mcv-accent-seen-all-600h-test</loc><lastmod>2026-02-26T06:08:29.183Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-hitab-subset-test</loc><lastmod>2026-02-26T05:41:37.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/table-question-answering-on-aitqa-test</loc><lastmod>2026-02-26T05:41:37.626Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-trait-automated-essay-scoring-on-asap-prompt-8-test</loc><lastmod>2026-02-26T05:46:57.777Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-trait-automated-essay-scoring-on-asap-prompt-7-test</loc><lastmod>2026-02-26T05:46:57.794Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/budgeted-subset-selection-on-dolly-15-percent-retention-train</loc><lastmod>2026-02-26T06:03:33.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/budgeted-subset-selection-on-dolly-5-percent-retention</loc><lastmod>2026-02-26T06:03:33.729Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/budgeted-subset-selection-on-alpaca-5-percent-retention</loc><lastmod>2026-02-26T06:03:33.713Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grounded-referring-expression-comprehension-on-grec-testb</loc><lastmod>2026-02-26T05:53:00.520Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grounded-referring-expression-comprehension-on-grec-testa</loc><lastmod>2026-02-26T05:53:00.506Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trait-based-automatic-essay-scoring-on-asap-plus-plus-prompt-1-test</loc><lastmod>2026-02-26T05:59:08.305Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stem-and-reasoning-on-visualpuzzle</loc><lastmod>2026-02-26T05:30:52.458Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-2wikimultihopqa-subsampled-to-300-q-and-a-instances</loc><lastmod>2026-02-26T05:37:55.627Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime25-accuracy</loc><lastmod>2026-02-26T05:30:51.745Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-squad-2k</loc><lastmod>2026-02-26T05:34:56.993Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-squad-1k</loc><lastmod>2026-02-26T05:34:56.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-squad-512</loc><lastmod>2026-02-26T05:34:56.902Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-answer-f1-score</loc><lastmod>2026-02-26T05:34:56.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-question-answering-on-ms-marco-v2</loc><lastmod>2026-02-26T05:34:56.977Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-question-answering-on-ms-marco-v1</loc><lastmod>2026-02-26T05:43:53.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-llm-jailbreaking-on-advbench-gpt-oss-20b-target-test</loc><lastmod>2026-02-26T05:23:51.825Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-llm-jailbreaking-on-advbench-qwen-3-14b-target-test</loc><lastmod>2026-02-26T05:23:51.803Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-llm-jailbreaking-on-advbench-gemma-3-12b-target-test</loc><lastmod>2026-02-26T05:23:51.773Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/black-box-llm-jailbreaking-on-advbench-llama-3-2-11b-target-test</loc><lastmod>2026-02-26T05:23:51.742Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-math500-exact-match-accuracy-ngen-128-256-512</loc><lastmod>2026-02-26T05:42:32.823Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-gsm8k-ngen-exact-match-accuracy</loc><lastmod>2026-02-26T05:42:32.171Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/symbolic-planning-on-countdown</loc><lastmod>2026-02-26T05:42:32.809Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/symbolic-planning-on-4x4-sudoku</loc><lastmod>2026-02-26T05:34:21.157Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalization-on-qwen2-5-14b-wealth-seeking</loc><lastmod>2026-02-26T06:08:44.369Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalization-on-qwen2-5-14b-power-seeking</loc><lastmod>2026-02-26T05:58:10.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-lclf-qa-1-0-test</loc><lastmod>2026-02-26T06:01:13.802Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-alignment-on-base-model-evaluation-set</loc><lastmod>2026-02-26T06:08:53.594Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/english-to-hindi-summarization-on-mildsum-test</loc><lastmod>2026-02-26T06:00:40.419Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-average-amc23-minerva-olympiad-math500-aime24-aime25</loc><lastmod>2026-02-27T10:42:22.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-generated-text-detection-on-detectrl-google-palm</loc><lastmod>2026-02-26T05:26:05.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-generated-text-detection-on-detectrl-llama-2-70b</loc><lastmod>2026-02-26T05:26:05.126Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/wealth-management-chatbot-response-generation-on-bitext-wealth-management-llm-chatbot-test</loc><lastmod>2026-02-26T05:37:00.831Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-reasoning-on-mmlu</loc><lastmod>2026-02-26T05:30:49.890Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-language-understanding-on-c-simpleqa</loc><lastmod>2026-02-26T06:03:50.301Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-score</loc><lastmod>2026-02-26T06:03:50.288Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-in-domain-reasoning-suite-math-olympiad-amc-aime</loc><lastmod>2026-02-26T05:49:43.038Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-round-chat-retrieval-on-mrcr</loc><lastmod>2026-05-22T07:41:58.893Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overall-on-standard-evaluation-suite</loc><lastmod>2026-02-26T05:35:50.535Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-cost-acc-eff</loc><lastmod>2026-02-26T05:39:57.153Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-v5-880-samples</loc><lastmod>2026-02-26T05:39:57.139Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-translation-on-covost-2-en-ar-original</loc><lastmod>2026-02-26T05:37:00.500Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-translation-on-covost-2-en-ca-original</loc><lastmod>2026-02-26T05:37:00.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-qa-on-situatedqa-nq-300</loc><lastmod>2026-02-26T05:30:49.512Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-domain-qa-on-ambigqa-nq-300</loc><lastmod>2026-02-26T05:26:45.383Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-llm-alignment-evaluation-on-personalrewardbench-test</loc><lastmod>2026-02-26T05:52:22.965Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-personalrewardbench-test</loc><lastmod>2026-02-26T05:51:22.057Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-incorrect-step-identification-on-mmmu-mathvision-mathverse-vo-dynamath-wemath-overall</loc><lastmod>2026-02-27T10:42:22.771Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-incorrect-step-identification-on-wemath</loc><lastmod>2026-02-27T10:42:22.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-incorrect-step-identification-on-dynamath</loc><lastmod>2026-02-27T10:42:22.869Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-incorrect-step-identification-on-mathverse-vo</loc><lastmod>2026-02-27T10:42:22.843Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-incorrect-step-identification-on-mathvision</loc><lastmod>2026-02-27T10:42:22.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/first-incorrect-step-identification-on-mmmu</loc><lastmod>2026-02-27T10:42:22.793Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-generation-on-empathetic-dialogue</loc><lastmod>2026-02-26T05:57:15.555Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-generation-on-dailydialog</loc><lastmod>2026-02-26T05:57:15.538Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empathetic-experience-evaluation-on-30-scenarios-test</loc><lastmod>2026-02-26T05:41:49.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empathetic-intervention-on-epm-q</loc><lastmod>2026-02-26T05:54:21.204Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empathetic-dialogue-interaction-on-epm-q-model-wise-means</loc><lastmod>2026-02-26T05:59:45.940Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-deception-evaluation-on-mm-deceptionbench-primary-1-0</loc><lastmod>2026-02-26T05:58:30.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-average-diffusion-steps-and-reduction</loc><lastmod>2026-02-26T05:35:22.198Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-diffusion-steps-and-reduction</loc><lastmod>2026-02-26T05:36:08.827Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-countdown-average-diffusion-steps</loc><lastmod>2026-02-26T05:35:22.184Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/co-speech-gesture-generation-on-human-evaluation-user-study</loc><lastmod>2026-02-26T05:53:34.182Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rag-completeness-on-qasper-test</loc><lastmod>2026-02-26T05:52:08.844Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rag-completeness-on-asqa-test</loc><lastmod>2026-02-26T05:47:52.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/rag-completeness-on-alce-test</loc><lastmod>2026-02-26T05:52:08.861Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-reconstruction-on-pathogenic-attack</loc><lastmod>2026-02-26T05:51:16.026Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-reconstruction-on-f8-cruiser</loc><lastmod>2026-02-26T06:01:45.968Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-reconstruction-on-lotka-volterra</loc><lastmod>2026-02-26T06:01:45.951Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paper-to-code-reproduction-on-paperbench-code-icml-2024-dev</loc><lastmod>2026-02-26T05:35:50.519Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-manipulation-on-libero-specialized-suites-and-diverse-suite</loc><lastmod>2026-02-26T05:52:38.768Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-pass-at-16-avg-at-16</loc><lastmod>2026-02-26T05:57:35.314Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc23-pass-at-16-avg-at-16</loc><lastmod>2026-02-26T05:57:35.300Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime25-pass-at-16-avg-at-16</loc><lastmod>2026-02-26T05:57:35.288Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-arc-1-sampled-15-reasoning-task-instances-chollet-2019</loc><lastmod>2026-02-26T06:06:05.056Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/idh1-mutation-prediction-on-tcga-lgg-5-folds</loc><lastmod>2026-02-26T05:30:48.249Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-prompt-injection-defense-on-agentdojo-test</loc><lastmod>2026-02-26T05:24:01.534Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robot-manipulation-on-real-world-tasks-franka-emika-panda</loc><lastmod>2026-02-26T06:05:28.921Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-arm-manipulation-on-metaworld-hard-split</loc><lastmod>2026-02-26T06:05:09.499Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-arm-manipulation-on-metaworld-medium</loc><lastmod>2026-02-26T06:05:09.483Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-ability-evaluation-on-in-house-general-benchmark</loc><lastmod>2026-02-26T05:47:55.432Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/battery-soh-monitoring-on-b5-b6</loc><lastmod>2026-02-26T05:57:16.333Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-overall-average-results</loc><lastmod>2026-02-26T05:59:18.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b10-to-b9</loc><lastmod>2026-02-26T05:59:18.440Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b9-to-b10</loc><lastmod>2026-02-26T05:59:18.425Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b10-to-b5</loc><lastmod>2026-02-26T05:59:18.410Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b10</loc><lastmod>2026-02-26T05:59:18.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b9-to-b5</loc><lastmod>2026-02-26T05:59:18.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b9</loc><lastmod>2026-02-26T05:59:18.359Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b8-to-b5</loc><lastmod>2026-02-26T05:59:18.344Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b8</loc><lastmod>2026-02-26T05:59:18.328Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b7-to-b5</loc><lastmod>2026-02-26T06:00:01.224Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b7</loc><lastmod>2026-02-26T06:00:01.028Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b6-to-b5</loc><lastmod>2026-02-26T05:59:18.311Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b6</loc><lastmod>2026-02-26T05:59:18.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b4</loc><lastmod>2026-02-26T05:59:18.280Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b4-to-b5</loc><lastmod>2026-02-26T05:59:18.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b3</loc><lastmod>2026-02-26T06:00:01.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b3-to-b5</loc><lastmod>2026-02-26T06:00:00.995Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b2</loc><lastmod>2026-02-26T06:00:00.981Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b2-to-b5</loc><lastmod>2026-02-26T06:00:00.968Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b5-to-b1</loc><lastmod>2026-02-26T05:59:18.242Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/soh-estimation-on-battery-mission-profile-b1-to-b5</loc><lastmod>2026-02-26T06:00:00.952Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-dimensional-knapsack-problem-on-mkp-n-100-m-5-test</loc><lastmod>2026-02-26T05:54:11.548Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/capacitated-vehicle-routing-problem-on-cvrp-n-100-c-50-64-independent-instances-test</loc><lastmod>2026-02-26T05:54:11.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/capacitated-vehicle-routing-problem-on-cvrp-n-50-c-50-64-instances-test</loc><lastmod>2026-02-26T05:54:11.518Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/orienteering-problem-on-op-n-100-64-independent-instances-test</loc><lastmod>2026-02-26T05:54:11.503Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/orienteering-problem-on-op-n-50-64-independent-instances-test</loc><lastmod>2026-02-26T05:54:11.487Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mcts-aggregation-strategy-evaluation-on-narrow-corridor</loc><lastmod>2026-02-26T05:50:27.277Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mcts-aggregation-strategy-evaluation-on-wide-corridor</loc><lastmod>2026-02-26T05:50:27.262Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mcts-aggregation-strategy-evaluation-on-random-teleporter</loc><lastmod>2026-02-26T05:50:27.248Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mcts-aggregation-strategy-evaluation-on-pendulum</loc><lastmod>2026-02-26T05:50:27.234Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mcts-aggregation-strategy-evaluation-on-mountain-car</loc><lastmod>2026-02-26T05:50:27.220Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mcts-aggregation-strategy-evaluation-on-lunarlander</loc><lastmod>2026-02-26T05:50:27.207Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/property-based-retrieval-on-short-stories-test</loc><lastmod>2026-02-26T05:49:36.368Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/property-based-retrieval-on-biology-abstracts-test</loc><lastmod>2026-02-26T05:49:36.349Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/property-based-retrieval-on-the-pile-test</loc><lastmod>2026-02-26T05:49:36.332Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/property-based-retrieval-on-reasoning-traces-test</loc><lastmod>2026-02-26T05:49:36.315Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/property-based-retrieval-on-responses-test</loc><lastmod>2026-02-26T05:49:36.299Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/property-based-retrieval-on-prompts-test</loc><lastmod>2026-02-26T05:49:36.285Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-missing-information-detection-on-math-1-0-test</loc><lastmod>2026-02-26T05:54:25.430Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-missing-information-detection-on-gsm8k-v1-test</loc><lastmod>2026-02-26T05:54:25.413Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mobile-gui-automation-on-aw-extend</loc><lastmod>2026-02-26T06:05:09.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cell-type-identification-on-human-breast-cancer-hbc</loc><lastmod>2026-02-26T05:30:47.884Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cell-type-identification-on-mouse-brain-anterior-mba</loc><lastmod>2026-02-26T05:30:47.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cell-type-identification-on-mouse-embryo-e9-5</loc><lastmod>2026-02-26T05:30:47.847Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-svhn-test-accuracy-and-efficiency</loc><lastmod>2026-02-26T05:30:47.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-label-emotion-classification-on-depressionemo-test</loc><lastmod>2026-02-26T05:48:49.443Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-diagnosis-on-emotionx-test</loc><lastmod>2026-02-26T05:42:51.076Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-cause-pair-identification-on-reccon-test</loc><lastmod>2026-02-26T05:48:49.426Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-cause-pair-identification-on-peld-test</loc><lastmod>2026-02-26T05:48:49.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/analytical-reasoning-on-ar-lsat</loc><lastmod>2026-02-26T06:04:11.871Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-logiqa-selection-accuracy</loc><lastmod>2026-02-26T06:04:11.853Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-selection-accuracy</loc><lastmod>2026-02-26T06:04:11.837Z</lastmod></url></urlset>