<?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/safety-evaluation-on-multijail-ar-test</loc><lastmod>2026-02-26T06:03:37.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-multijail-ko-test</loc><lastmod>2026-02-26T06:03:37.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-multijail-en-test</loc><lastmod>2026-02-26T06:03:37.626Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-do-not-answer-test</loc><lastmod>2026-02-26T05:23:51.879Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-safetybench-test</loc><lastmod>2026-02-26T05:30:59.695Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialect-identification-on-adi-17-test</loc><lastmod>2026-02-26T05:42:54.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/diffusion-language-model-watermarking-on-waterbench-600-prompts-2024</loc><lastmod>2026-02-26T05:55:10.419Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-language-reasoning-on-winoground</loc><lastmod>2026-02-26T06:04:22.628Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-sugarcrepe</loc><lastmod>2026-02-27T11:03:11.885Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-avg-at-3-accuracy</loc><lastmod>2026-02-26T05:36:31.396Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-avg-at-16-accuracy</loc><lastmod>2026-02-26T05:36:05.968Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-avg-at-16-accuracy</loc><lastmod>2026-02-26T05:49:43.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-avg-at-3-accuracy</loc><lastmod>2026-02-26T05:36:31.381Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-avg-at-3-accuracy</loc><lastmod>2026-02-26T06:09:07.677Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/access-control-enforcement-on-multiper-enterprise</loc><lastmod>2026-02-26T05:57:14.008Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-sql-on-synthesized-business-logic-driven-dataset</loc><lastmod>2026-02-26T06:04:23.611Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-searchgymbench-complex-qa-1-0-test</loc><lastmod>2026-02-26T05:30:58.803Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-searchgymbench-simple-qa-1-0-test</loc><lastmod>2026-02-26T05:30:58.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/grade-school-reasoning-on-gsm-hard</loc><lastmod>2026-02-26T05:57:34.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-model-agreement-evaluation-on-rebuttal-rm-dataset-1-0-test</loc><lastmod>2026-02-26T05:35:07.207Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/legal-retrieval-on-turkish-legal</loc><lastmod>2026-02-26T05:48:34.902Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-correlation-analysis-on-substanreview</loc><lastmod>2026-02-26T06:04:35.675Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/story-generation-on-english-story-generation-egypt</loc><lastmod>2026-02-26T05:39:30.359Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/story-generation-on-english-story-generation-indonesia</loc><lastmod>2026-02-26T05:40:07.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/story-generation-on-english-story-generation-china</loc><lastmod>2026-02-26T05:39:30.516Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/empathetic-dialogue-evaluation-on-chinese-empathetic-dialogue-test</loc><lastmod>2026-02-26T05:53:31.204Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-level-information-extraction-on-multimuc-averaged-across-languages</loc><lastmod>2026-02-26T05:43:31.590Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-level-information-extraction-on-muc</loc><lastmod>2026-02-26T05:43:31.574Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-overall-performance-test</loc><lastmod>2026-02-26T05:54:21.948Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-rewardbench-2-test</loc><lastmod>2026-02-26T06:00:52.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-evaluation-on-arena-hard-v0-1</loc><lastmod>2026-02-26T05:35:01.093Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sarcasm-ranking-on-hub</loc><lastmod>2026-02-26T06:01:06.777Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sarcasm-matching-on-hub</loc><lastmod>2026-02-26T05:51:39.209Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/record-linkage-on-dblp-scholar</loc><lastmod>2026-02-26T05:43:31.313Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-code-compliance-on-overall-mean</loc><lastmod>2026-02-26T05:40:34.754Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-code-compliance-on-python-py</loc><lastmod>2026-02-26T05:40:34.736Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-code-compliance-on-java</loc><lastmod>2026-02-26T05:40:34.724Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-code-compliance-on-c-plus-plus</loc><lastmod>2026-02-26T05:40:34.711Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-code-compliance-on-c</loc><lastmod>2026-02-26T05:40:34.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/abstraction-and-reasoning-on-arc-agi</loc><lastmod>2026-03-30T06:33:34.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-on-xbench</loc><lastmod>2026-03-17T11:41:33.704Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-accuracy-token-efficiency-and-runtime</loc><lastmod>2026-02-26T05:26:45.577Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-accuracy-runtime-tokens</loc><lastmod>2026-02-26T05:30:55.815Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-accuracy-and-efficiency</loc><lastmod>2026-02-26T05:30:55.786Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/circuit-localization-on-mechanistic-interpretability-benchmark-mib</loc><lastmod>2026-02-26T05:46:52.997Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-reasoning-on-mmsu-s-t-only</loc><lastmod>2026-02-26T05:30:55.478Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-text-question-answering-on-llamaq-triviaqa-webq-and-obqa-average</loc><lastmod>2026-02-26T05:30:55.445Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-23-accuracy-pass-at-1</loc><lastmod>2026-02-26T05:30:55.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-pass-at-1</loc><lastmod>2026-02-26T05:30:55.016Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-reconstruction-on-english-read-by-japanese-accented-speech-2007-ood</loc><lastmod>2026-02-26T06:08:29.295Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-reconstruction-on-japanese-versatile-speech-unseen-language-speech-2019-ood</loc><lastmod>2026-02-26T06:08:29.278Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-reconstruction-on-gigaspeech-noisy-speech-2021-ood</loc><lastmod>2026-02-26T06:08:29.245Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-temporal-point-process-prediction-on-taxi-pro-test</loc><lastmod>2026-02-27T10:44:26.236Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-temporal-point-process-prediction-on-danmakutpp-test</loc><lastmod>2026-02-27T10:44:26.208Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-goemotions</loc><lastmod>2026-02-26T06:01:13.856Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-deep-research-evaluation-on-deepresearch-bench-100-phd-level-research-tasks</loc><lastmod>2026-02-26T05:39:40.856Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-text-safety-classification-on-mssbench-embodied</loc><lastmod>2026-02-26T05:25:43.415Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-text-safety-classification-on-mssbench-chat</loc><lastmod>2026-02-26T05:25:43.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-text-safety-classification-on-vlguard</loc><lastmod>2026-02-26T05:25:43.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-text-safety-classification-on-vscbench</loc><lastmod>2026-02-26T05:25:40.958Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-classification-on-safeqa-english</loc><lastmod>2026-02-26T05:25:40.937Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-classification-on-sea-safeguardbench</loc><lastmod>2026-02-26T05:25:40.917Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/response-classification-on-sea-safeguardbench-english</loc><lastmod>2026-02-26T05:25:40.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-classification-on-seals-sea</loc><lastmod>2026-02-26T05:25:40.876Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-proof-reward-modeling-on-proof-rm-imo-cmo-usamo-2024-2025-test</loc><lastmod>2026-02-26T05:30:53.639Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-proof-reward-modeling-on-opc-test</loc><lastmod>2026-02-26T05:30:53.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bias-penalized-accuracy-evaluation-on-low-resource-languages-lrls</loc><lastmod>2026-02-26T05:37:23.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bias-penalized-accuracy-evaluation-on-high-resource-languages-hrls</loc><lastmod>2026-02-26T05:37:48.214Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/bias-penalized-accuracy-evaluation-on-english</loc><lastmod>2026-02-26T05:37:48.196Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-fava-annotations-test</loc><lastmod>2026-02-26T05:26:05.585Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-search-reasoning-on-xbench-deepsearch2505</loc><lastmod>2026-02-26T06:03:50.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-svamp-accuracy-sharp-length</loc><lastmod>2026-02-26T05:30:52.946Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-ax-g</loc><lastmod>2026-02-26T05:30:51.554Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-ax-b</loc><lastmod>2026-02-26T05:30:51.536Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-multi-domain-education-spoken-thesis-science-microblog-test</loc><lastmod>2026-02-26T05:37:11.324Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tool-use-on-tau-2-bench-gpt-4-1-simulator-setting</loc><lastmod>2026-02-26T06:02:09.807Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-natural-questions-ppl</loc><lastmod>2026-02-26T05:55:10.314Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-triviaqa-ppl</loc><lastmod>2026-02-26T05:55:10.298Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-jbb-behaviors</loc><lastmod>2026-02-26T06:03:37.903Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-s-eval-attack</loc><lastmod>2026-02-26T06:03:37.889Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-s-eval-base</loc><lastmod>2026-02-26T06:03:37.872Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-qa-on-open-ended-qa</loc><lastmod>2026-02-26T05:58:30.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/poem-generation-on-poem</loc><lastmod>2026-02-26T05:59:09.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-step-reasoning-on-gsm8k-test</loc><lastmod>2026-02-26T05:57:24.224Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/time-series-forecasting-on-solar-mse</loc><lastmod>2026-02-27T10:42:53.620Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-performance-on-average</loc><lastmod>2026-02-26T05:36:17.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-performance-on-math</loc><lastmod>2026-02-26T05:36:17.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-performance-on-actions</loc><lastmod>2026-02-26T05:35:33.033Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-performance-on-database</loc><lastmod>2026-02-26T05:36:17.252Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-performance-on-code</loc><lastmod>2026-02-26T05:36:17.233Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-23-acc-at-16</loc><lastmod>2026-02-26T05:26:56.993Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/numerical-comparison-on-cross-notation-comparison-held-out</loc><lastmod>2026-02-26T06:08:13.638Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinnerchief-if-wiki</loc><lastmod>2026-02-26T05:43:55.940Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinnerchief-if-theses</loc><lastmod>2026-02-26T05:42:51.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinnerchief-if-arxiv</loc><lastmod>2026-02-26T05:43:55.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinnerchief-df-wiki</loc><lastmod>2026-02-26T05:43:55.907Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinnerchief-df-theses</loc><lastmod>2026-02-26T05:42:55.765Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinnerchief-df-arxiv</loc><lastmod>2026-02-26T05:43:55.887Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinbot-wiki</loc><lastmod>2026-02-26T05:43:55.868Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinbot-theses-test</loc><lastmod>2026-02-26T05:43:55.852Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-paraphrased-plagiarism-detection-on-spinbot-arxiv</loc><lastmod>2026-02-26T05:43:55.834Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-estimation-on-en-ml</loc><lastmod>2026-02-26T05:57:44.429Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/named-entity-recognition-on-humset</loc><lastmod>2026-02-26T05:42:32.560Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-hop-specific-f1-breakdown</loc><lastmod>2026-02-26T05:21:39.767Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-augmented-reasoning-on-gaia-text</loc><lastmod>2026-02-26T05:47:56.736Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-average-math-gsm8k-aime-2025</loc><lastmod>2026-02-26T06:06:05.983Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-generation-on-chartcheck-test</loc><lastmod>2026-02-26T06:00:36.574Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-generation-on-aichartclaim-test</loc><lastmod>2026-02-26T06:00:36.558Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-generation-on-chartcheck</loc><lastmod>2026-02-26T06:00:43.310Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-generation-on-aichartclaim</loc><lastmod>2026-02-26T06:00:43.291Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-generation-on-chartcheck-1-0-test</loc><lastmod>2026-02-26T06:00:36.527Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/explanation-generation-on-aichartclaim-1-0-test</loc><lastmod>2026-02-26T06:00:36.507Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generation-scoring-on-gemma-scope-sae-latents</loc><lastmod>2026-02-26T05:46:27.964Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sae-latent-interpretation-on-goodfire-saes-test</loc><lastmod>2026-02-26T05:46:27.949Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sae-latent-interpretation-on-llama-scope-saes-test</loc><lastmod>2026-02-26T05:46:27.933Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-multipl-e-mbpp</loc><lastmod>2026-06-12T08:04:19.571Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/consulting-and-recommendations-on-consulting-and-recommendations-benchmark</loc><lastmod>2026-02-26T05:35:50.747Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-reasoning-on-math500-avg-at-16-pass-at-16</loc><lastmod>2026-02-26T05:57:35.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/emotion-classification-on-goe</loc><lastmod>2026-02-26T05:30:49.750Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-translation-on-audio-ntrex-4l-long-form-test</loc><lastmod>2026-02-26T05:37:00.811Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-to-speech-translation-on-europarl-st-short-form-test</loc><lastmod>2026-02-26T05:37:00.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chinese-idiom-cloze-completion-on-chid-held-out</loc><lastmod>2026-02-26T05:40:12.296Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-reasoning-on-openfin-held-out</loc><lastmod>2026-02-26T05:40:12.282Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/climate-question-answering-on-climaqa-held-out</loc><lastmod>2026-02-26T05:40:12.268Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecode-held-out</loc><lastmod>2026-02-26T05:40:12.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-held-out</loc><lastmod>2026-02-26T05:40:12.237Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/physics-problem-solving-on-physics-held-out</loc><lastmod>2026-02-26T05:40:12.221Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memory-discrimination-on-iid-10k</loc><lastmod>2026-02-26T05:30:49.588Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/memory-discrimination-on-bid-20k</loc><lastmod>2026-02-26T05:26:45.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-in-domain-reasoning-suite</loc><lastmod>2026-02-26T05:49:43.055Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-pass-at-1-accuracy-and-step-count</loc><lastmod>2026-02-26T05:57:33.377Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-live-transcription-scenario-apple-macbook-m3</loc><lastmod>2026-02-26T05:48:28.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-pair-wise-diversity-on-empathetic-dialogue-test</loc><lastmod>2026-02-26T05:58:30.591Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-pair-wise-diversity-on-dailydialog-test</loc><lastmod>2026-02-26T05:58:30.567Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-logic-alignment-on-empathetic-dialogue</loc><lastmod>2026-02-26T05:46:11.094Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-logic-alignment-on-dailydialog</loc><lastmod>2026-02-26T05:46:42.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-json-generation-on-json-generation-dataset</loc><lastmod>2026-02-26T06:04:49.990Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-gpqa-test</loc><lastmod>2026-02-26T05:30:49.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/delivery-task-on-delivery-task-5000-step-simulation</loc><lastmod>2026-02-26T05:59:00.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-navigation-on-webshop-leaderboard</loc><lastmod>2026-02-26T05:46:03.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/function-calling-on-bfcl-multi-turn-base-v3-val</loc><lastmod>2026-02-26T05:36:32.991Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interactive-web-shopping-and-navigation-on-webshop-val</loc><lastmod>2026-02-26T05:36:32.975Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-violation-detection-on-pku-saferlhf</loc><lastmod>2026-02-26T05:26:45.360Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-recovery-on-nonlinear-dynamics-models</loc><lastmod>2026-02-26T05:36:09.911Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unsafe-content-detection-on-vlguard</loc><lastmod>2026-02-26T05:43:30.295Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-safety-moderation-on-safesora</loc><lastmod>2026-02-26T05:43:30.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-safety-moderation-on-safewatch</loc><lastmod>2026-02-26T05:43:30.242Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paper-to-code-reproduction-on-paperbench-code-dev</loc><lastmod>2026-04-09T23:43:28.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constraint-satisfaction-reasoning-on-zebralogic</loc><lastmod>2026-02-26T05:41:53.240Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-pass-at-8-pass-at-16-pass-at-32</loc><lastmod>2026-02-26T05:57:36.517Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-pass-at-8-pass-at-16-pass-at-32</loc><lastmod>2026-02-26T05:57:36.501Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-23-pass-at-8-pass-at-16-pass-at-32</loc><lastmod>2026-02-26T05:57:36.485Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-pass-at-8-pass-at-16-pass-at-32</loc><lastmod>2026-02-26T05:57:36.470Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-avg-at-k-sampling</loc><lastmod>2026-02-26T05:36:20.403Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-processing-workflow-generation-on-datagovbench-dag-level</loc><lastmod>2026-02-26T05:24:15.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-datagovbench-operator-level</loc><lastmod>2026-02-26T05:24:15.371Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-inference-on-dataset-ii-all</loc><lastmod>2026-02-26T05:35:29.872Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-inference-on-dataset-double-los-ii</loc><lastmod>2026-02-26T05:36:13.798Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-inference-on-dataset-single-los-ii</loc><lastmod>2026-02-26T05:36:13.786Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-inference-on-dataset-nlos-ii</loc><lastmod>2026-02-26T05:36:13.772Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-property-optimization-on-single-property-optimization-test</loc><lastmod>2026-02-26T05:35:50.483Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-component-editing-on-molecular-component-editing</loc><lastmod>2026-02-26T05:35:56.326Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fill-probability-prediction-on-cac-40-futures-test</loc><lastmod>2026-02-26T05:59:45.845Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-generation-on-shenzhen-168-hours</loc><lastmod>2026-02-26T05:41:10.853Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/trajectory-generation-on-beijing-168-hours</loc><lastmod>2026-02-26T05:41:10.835Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structural-explanation-on-tree-grid</loc><lastmod>2026-02-26T05:58:30.295Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structural-explanation-on-tree-cycle</loc><lastmod>2026-02-26T05:58:30.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structural-explanation-on-ba-community</loc><lastmod>2026-02-26T05:58:30.253Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structural-explanation-on-ba-shapes</loc><lastmod>2026-02-26T05:58:30.235Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/vision-and-language-navigation-on-gsa-basic-test</loc><lastmod>2026-02-26T06:03:04.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-reasoning-on-arc-1-0-test</loc><lastmod>2026-06-12T07:17:37.576Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/out-of-domain-reasoning-on-gpqa</loc><lastmod>2026-02-26T05:36:33.319Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-avg-at-8-accuracy</loc><lastmod>2026-02-26T05:22:28.141Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-avg-at-8-accuracy</loc><lastmod>2026-02-26T05:36:33.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-reasoning-on-gpqa</loc><lastmod>2026-02-26T05:38:55.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-agent-reasoning-on-aime-24</loc><lastmod>2026-02-26T05:38:55.395Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learning-path-recommendation-on-assist09-l-5-test</loc><lastmod>2026-02-26T05:48:34.309Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learning-path-recommendation-on-assist09-l-10-test</loc><lastmod>2026-02-26T05:48:34.294Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learning-path-recommendation-on-assist09-l-20-test</loc><lastmod>2026-02-26T05:48:34.276Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learning-path-recommendation-on-junyi-l-5-test</loc><lastmod>2026-02-26T05:48:34.259Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learning-path-recommendation-on-junyi-l-10-test</loc><lastmod>2026-02-26T05:48:34.244Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learning-path-recommendation-on-junyi-l-20-test</loc><lastmod>2026-02-26T05:48:34.225Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/consistency-evaluation-on-decisionbench</loc><lastmod>2026-02-26T05:38:46.408Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/optical-character-recognition-on-cc-ocr</loc><lastmod>2026-02-26T05:30:45.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-tsqa</loc><lastmod>2026-02-26T05:30:45.956Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-mtbench-weather</loc><lastmod>2026-02-26T05:30:45.939Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-mtbench-finance</loc><lastmod>2026-02-26T05:30:45.922Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-tsqa</loc><lastmod>2026-02-26T05:49:09.810Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-mtbench-weather</loc><lastmod>2026-02-26T05:49:09.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-mtbench-finance</loc><lastmod>2026-02-26T05:49:09.780Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-tsqa</loc><lastmod>2026-02-26T05:30:45.908Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-timerbed</loc><lastmod>2026-02-26T05:30:45.893Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mtbench-weather</loc><lastmod>2026-02-26T05:30:45.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-mtbench-finance</loc><lastmod>2026-02-26T05:30:45.861Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dynamics-control-on-mountaincar-dynamics-explicit-structural-drift-drift-i</loc><lastmod>2026-02-26T06:05:09.306Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-frozenlake-topology-explicit-structural-drift-ii</loc><lastmod>2026-02-26T06:05:09.289Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-frozenlake-drift-i-topology-explicit-structural-drift</loc><lastmod>2026-02-26T06:05:09.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/navigation-on-frozenlake-explicit-structural-drift-source</loc><lastmod>2026-02-26T06:05:09.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-shopping-on-webshop-semantic-explicit-structural-drift-ii</loc><lastmod>2026-02-26T06:05:09.241Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-shopping-on-webshop-semantic-explicit-structural-drift-drift-i</loc><lastmod>2026-02-26T06:05:09.228Z</lastmod></url></urlset>