<?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/security-smell-detection-on-combined-puppet-ansible-chef-oracle-test</loc><lastmod>2026-02-26T05:51:28.172Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/security-smell-detection-on-chef-oracle-test</loc><lastmod>2026-02-26T05:58:34.671Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/security-smell-detection-on-ansible-oracle-test</loc><lastmod>2026-02-26T05:58:34.657Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/security-smell-detection-on-puppet-oracle-test</loc><lastmod>2026-02-26T05:58:34.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/intrusion-detection-on-cidds</loc><lastmod>2026-02-26T05:37:43.732Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-prefilling-attacks-qwen2-5-14b-instruct</loc><lastmod>2026-02-26T05:23:53.734Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-detection-on-out-of-loop-evaluation-dataset-test</loc><lastmod>2026-02-26T05:48:49.681Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phishing-url-detection-on-iscx-random-balanced-subset-of-1-000-urls</loc><lastmod>2026-02-26T05:43:34.572Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phishing-url-detection-on-ebbu-random-balanced-subset-of-1-000-urls</loc><lastmod>2026-02-26T05:43:34.560Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/phishing-url-detection-on-hp-random-balanced-1-000-urls</loc><lastmod>2026-02-26T05:43:34.544Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-llama-4</loc><lastmod>2026-02-26T05:23:53.614Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-llama-3-1</loc><lastmod>2026-02-26T05:23:53.596Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-deepseek-v3-2</loc><lastmod>2026-02-26T05:35:05.548Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-qwen-max</loc><lastmod>2026-02-26T05:23:53.579Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-gemini-pro-3</loc><lastmod>2026-02-26T05:23:53.559Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreaking-on-claude-4-5</loc><lastmod>2026-02-26T05:23:53.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/threshold-digital-signature-on-ml-dsa-fips-204</loc><lastmod>2026-03-24T17:10:19.051Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-class-classification-on-cic-malmemanalysis-2022-test</loc><lastmod>2026-02-26T05:31:16.358Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-cic-malmemanalysis-2022-test</loc><lastmod>2026-02-26T05:31:16.340Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/webpage-attack-detection-on-websentinel-dataset</loc><lastmod>2026-02-26T05:44:51.712Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-injection-attack-on-agentdojo-slack-suite</loc><lastmod>2026-02-26T05:37:40.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-cancer</loc><lastmod>2026-02-26T05:31:15.785Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/graph-multi-sample-attribute-inference-attack-on-pokec-n-to-pokec-z-transfer</loc><lastmod>2026-02-26T05:21:47.570Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-recovery-attack-on-zsre-test</loc><lastmod>2026-02-26T06:07:07.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-recovery-attack-on-counterfact-test</loc><lastmod>2026-02-26T06:07:07.753Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/external-memory-extraction-attack-detection-on-pokemon</loc><lastmod>2026-02-26T05:26:07.621Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/external-memory-extraction-attack-detection-on-healthmagiccare</loc><lastmod>2026-02-26T05:26:07.595Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-vlm-evaluation</loc><lastmod>2026-02-26T05:38:26.508Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-on-qwen-vl-2-5</loc><lastmod>2026-02-26T05:38:33.214Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-on-llava</loc><lastmod>2026-02-26T05:38:33.196Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-imperceptibility-on-adversarial-attack-evaluation-set</loc><lastmod>2026-02-26T06:03:24.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-kimi-vl</loc><lastmod>2026-02-26T05:38:33.180Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-blip-2</loc><lastmod>2026-02-26T05:38:33.161Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-openflamingo</loc><lastmod>2026-02-26T05:38:33.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-internvl3</loc><lastmod>2026-02-26T05:38:33.128Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arithmetic-reasoning-on-game-of-24-95-test</loc><lastmod>2026-02-26T06:05:10.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/offline-speech-translation-on-mcif-test</loc><lastmod>2026-02-26T06:09:03.216Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/classification-on-jd-com-query-product-relevance-test</loc><lastmod>2026-02-26T05:58:34.244Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coding-on-codeforces</loc><lastmod>2026-06-02T07:38:07.395Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-translation-on-vistra-v1-test</loc><lastmod>2026-02-26T06:09:13.848Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-penalized-efficiency-evaluation-on-dream-instruct</loc><lastmod>2026-02-26T05:59:07.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/quality-penalized-efficiency-evaluation-on-dream-base</loc><lastmod>2026-02-26T05:59:07.942Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/persuasive-technique-classification-on-indi-prop-farmer-s-protest</loc><lastmod>2026-02-26T05:52:45.306Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-toolbench-dataset</loc><lastmod>2026-02-26T06:02:58.838Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-merge-dataset</loc><lastmod>2026-02-26T06:02:58.824Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-serving-on-toolbench</loc><lastmod>2026-02-26T05:41:55.185Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-serving-on-merge-dataset</loc><lastmod>2026-02-26T05:41:55.162Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-adobe-lightroom-test</loc><lastmod>2026-02-26T05:31:13.158Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/clustering-on-openai-codex-test</loc><lastmod>2026-02-26T05:31:13.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/binary-classification-on-pink-slime-ps-vs-regular-local-news-ln</loc><lastmod>2026-02-26T05:31:12.745Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/generalization-reasoning-on-aggregate-emma-visulogic-zebra-cot</loc><lastmod>2026-02-26T06:07:29.061Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-zebra-cot</loc><lastmod>2026-02-26T05:47:39.482Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-simplification-overall-rewriting-on-newsela-out-of-domain</loc><lastmod>2026-02-26T05:48:07.200Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-simplification-overall-rewriting-on-simpa-out-of-domain</loc><lastmod>2026-02-26T05:48:07.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-simplification-lexical-paraphrasing-on-simpa-out-of-domain</loc><lastmod>2026-02-26T06:02:46.975Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/writing-capability-evaluation-on-writingbench-november-2025-official-leaderboard</loc><lastmod>2026-02-26T05:54:35.041Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-long-form-generation-on-topic-writing</loc><lastmod>2026-02-26T06:00:37.376Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-long-form-generation-on-abstract-generation</loc><lastmod>2026-02-26T06:00:37.359Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-long-form-generation-on-product-review</loc><lastmod>2026-02-26T06:00:37.342Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-long-form-generation-on-longlamp-topic-writing-user-based</loc><lastmod>2026-02-26T06:00:37.327Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-long-form-generation-on-longlamp-abstract-generation-user-based-split</loc><lastmod>2026-02-26T06:00:37.310Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-long-form-generation-on-longlamp-product-review-user-based-split</loc><lastmod>2026-02-26T06:00:37.291Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pathogen-detection-on-aquamicro12k-test</loc><lastmod>2026-02-26T06:10:01.034Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-conversation-on-mt-eval</loc><lastmod>2026-02-26T05:31:12.451Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/opinion-simulation-on-world-values-survey-wvs-test</loc><lastmod>2026-02-26T05:45:55.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-opinion-simulation-on-wvs-religion</loc><lastmod>2026-02-26T06:08:43.404Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-opinion-simulation-on-wvs-politics</loc><lastmod>2026-02-26T06:08:43.387Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/user-opinion-simulation-on-wvs-gender</loc><lastmod>2026-02-26T06:08:43.998Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-perplexity-evaluation-dataset</loc><lastmod>2026-02-26T05:55:10.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-visual-question-answering-on-m3d</loc><lastmod>2026-02-26T05:58:05.840Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-flenqa-3000-tokens</loc><lastmod>2026-02-26T05:31:12.273Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-flenqa-2000-tokens</loc><lastmod>2026-02-26T05:31:12.258Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/next-token-prediction-on-pre-training-corpus-train</loc><lastmod>2026-02-26T06:06:33.330Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/arithmetic-on-ari-add-test</loc><lastmod>2026-02-26T05:34:05.748Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sign-language-subtitle-alignment-on-bobsl-test</loc><lastmod>2026-02-26T05:43:59.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sign-language-subtitle-alignment-on-bobsl-val</loc><lastmod>2026-02-26T05:43:59.103Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-knowledge-on-mpararel-english-all</loc><lastmod>2026-02-27T10:55:35.024Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/linguistic-acceptability-on-blimp-english-all</loc><lastmod>2026-02-27T10:55:34.962Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-domain-language-modeling-on-mgsm-humaneval-and-medmcqa-composite-test</loc><lastmod>2026-02-26T05:35:54.924Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medmcqa-translated-test</loc><lastmod>2026-02-26T05:34:30.246Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/morphological-alignment-on-english-300-mb-corpora</loc><lastmod>2026-02-26T05:52:56.917Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compression-on-300-mb-monolingual-corpora</loc><lastmod>2026-02-26T06:07:33.480Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-accuracy-only</loc><lastmod>2026-02-26T05:31:10.682Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-on-safety-evaluation-suite</loc><lastmod>2026-02-26T06:03:53.913Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-problem-solving-on-math-score</loc><lastmod>2026-02-26T06:03:53.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/science-question-answering-on-gpqa-score-metric</loc><lastmod>2026-02-26T06:03:53.715Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-accuracy-tpf-tps-speedup</loc><lastmod>2026-02-26T06:05:56.323Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-tpf-tps-speedup-accuracy</loc><lastmod>2026-02-26T06:05:56.303Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-test-tpf-tps-speedup-solve-rate</loc><lastmod>2026-02-26T06:06:34.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-test-tpf-tps-speedup-solve-rate</loc><lastmod>2026-02-26T06:05:56.341Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/single-hop-qa-on-simplequestions</loc><lastmod>2026-02-26T05:31:10.330Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-qa-on-compwebq</loc><lastmod>2026-02-26T05:31:10.316Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-qa-on-webqsp</loc><lastmod>2026-02-26T05:31:10.304Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/metric-correlation-analysis-on-real-world-text-to-table-generation</loc><lastmod>2026-02-26T06:04:38.286Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/predicate-grounding-on-search-and-rescue-domain</loc><lastmod>2026-02-26T05:43:33.653Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/predicate-grounding-on-traffic-light-domain</loc><lastmod>2026-02-26T05:43:33.635Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-narrativeqa-helmet-benchmark</loc><lastmod>2026-02-26T05:43:33.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-metric-correlation-on-cogym-out-of-distribution</loc><lastmod>2026-02-26T05:47:53.020Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-metric-correlation-on-realhumaneval-out-of-distribution</loc><lastmod>2026-02-26T05:47:53.004Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-metric-correlation-on-evalgen-out-of-distribution</loc><lastmod>2026-02-26T05:47:52.987Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-metric-correlation-on-helpsteer2-in-distribution</loc><lastmod>2026-02-26T05:47:52.970Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/human-metric-correlation-on-simpeval-in-distribution</loc><lastmod>2026-02-26T05:47:52.951Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/location-extraction-on-india-crisis-tweets-evaluation-corpus-1-0-test</loc><lastmod>2026-02-26T05:58:33.899Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/early-rumor-detection-on-twitter-covid-19</loc><lastmod>2026-02-26T05:51:28.015Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/early-rumor-detection-on-beard</loc><lastmod>2026-02-26T05:51:27.998Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/early-rumor-detection-on-twitter</loc><lastmod>2026-02-26T05:51:27.986Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/early-rumor-detection-on-pheme-macro-f1-er</loc><lastmod>2026-02-26T05:51:27.973Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/regression-on-esol</loc><lastmod>2026-02-26T06:00:01.483Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoken-question-answering-on-ultraeval-audio-s2s</loc><lastmod>2026-02-26T05:34:53.015Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-processing-on-superb-per-wer-focus</loc><lastmod>2026-02-26T05:55:00.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoken-language-modeling-on-libri-light-6k</loc><lastmod>2026-02-26T06:11:19.794Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/discrete-unit-quality-evaluation-on-librispeech-960h</loc><lastmod>2026-02-26T05:21:47.888Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-research-on-adr-bench-finance-and-law</loc><lastmod>2026-02-26T06:04:07.908Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/de-novo-peptide-sequencing-on-9-species-test</loc><lastmod>2026-02-26T05:21:47.813Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/moral-alignment-on-cometh</loc><lastmod>2026-02-26T05:48:36.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-text-embedding-on-sea-languages-and-portuguese-benchmark-test</loc><lastmod>2026-02-26T06:08:46.081Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/e-commerce-text-embedding-retrieval-on-proprietary-e-commerce-dataset-v4-test</loc><lastmod>2026-02-26T05:35:51.086Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/morph-resolution-on-liveamr-test2</loc><lastmod>2026-02-26T05:26:45.724Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/morph-resolution-on-liveamr-test1</loc><lastmod>2026-02-26T05:31:07.385Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automated-grading-on-assistments-held-out-test</loc><lastmod>2026-02-26T05:50:53.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-on-swe-bench-verified</loc><lastmod>2026-06-24T08:58:03.733Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-beyondaime</loc><lastmod>2026-02-26T05:36:30.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-diagnosis-on-nejm</loc><lastmod>2026-02-26T06:02:29.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-flores-european-20-language-pairs</loc><lastmod>2026-02-26T05:35:51.005Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilinguality-on-wmt24-plus-plus-ko-de-es-ja-vi</loc><lastmod>2026-04-13T07:50:34.906Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-language-understanding-on-mmmlu-ko-de-es-ja</loc><lastmod>2026-04-13T07:50:34.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/utterance-level-pronunciation-assessment-on-speechocean762</loc><lastmod>2026-02-26T05:54:53.516Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/learner-dictionary-definition-generation-on-d3j-test</loc><lastmod>2026-02-26T06:07:44.163Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/topic-segmentation-on-lecturede-cross-validation</loc><lastmod>2026-02-26T05:43:32.839Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/document-contradiction-detection-on-contradoc-1-0-test</loc><lastmod>2026-02-26T05:41:30.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-on-cruxeval-i</loc><lastmod>2026-06-01T09:53:17.863Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/legal-question-answering-on-japanese-bar-examination-2024-reiwa-6</loc><lastmod>2026-02-26T05:54:25.606Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/acceptance-of-data-sharing-assessment-on-aods-scale-test</loc><lastmod>2026-02-26T05:52:23.038Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prosociality-assessment-on-psa-prosociality-scale-test</loc><lastmod>2026-02-26T05:52:23.024Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-attitude-assessment-on-iuipc-test</loc><lastmod>2026-02-26T05:52:23.008Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/korean-llm-evaluation-on-logickor-ko</loc><lastmod>2026-02-26T05:48:44.888Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/korean-language-understanding-on-kobest-ko</loc><lastmod>2026-02-26T05:47:55.667Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-compositional-generalization-on-skillbench</loc><lastmod>2026-02-26T06:04:25.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-research-report-generation-on-deepresearchgym-commercial-100</loc><lastmod>2026-02-26T05:47:46.926Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/aspect-based-sentiment-analysis-on-semeval-laptop-2014-test</loc><lastmod>2026-02-26T05:31:04.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-pass-at-1-accuracy-length-exceeding-ratio</loc><lastmod>2026-02-27T10:52:02.728Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-evaluation-on-reasoning-knowledge-and-biomedicine-combined-datasets-test</loc><lastmod>2026-02-27T10:52:01.916Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomedical-evaluation-on-pubmedqa-and-medqa-test</loc><lastmod>2026-02-27T10:52:02.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/financial-data-analysis-on-openfindata</loc><lastmod>2026-02-27T10:52:01.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/biomedicine-on-biomedicine-domain-bench</loc><lastmod>2026-02-27T10:52:02.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-on-knowledge-suite</loc><lastmod>2026-02-27T10:52:01.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-reasoning-suite-gsm8k-aime-humaneval-livecodebench</loc><lastmod>2026-02-27T10:52:02.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-gsm8k-math-aime2024-humaneval-and-livecodebench</loc><lastmod>2026-02-27T10:52:02.029Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-performance-on-performance-bench-reasoning-and-knowledge-average</loc><lastmod>2026-02-27T10:52:01.884Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-gsm8k-math-aime-humaneval-and-livecodebench-test</loc><lastmod>2026-02-27T10:52:02.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/comprehensive-reasoning-and-knowledge-benchmark-gsm8k-mmlu-humaneval-arc-gpqa</loc><lastmod>2026-02-27T10:52:01.997Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-performance-evaluation-on-performance-bench-aggregate</loc><lastmod>2026-02-27T10:52:01.851Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/dialogue-experience-evaluation-on-20-popular-topics-50-dialogues-per-topic</loc><lastmod>2026-02-26T05:47:16.823Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-hypothesis-selection-on-mboshi-test</loc><lastmod>2026-02-26T06:08:30.279Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-hypothesis-selection-on-kichwa-test</loc><lastmod>2026-02-26T06:08:30.263Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/asr-hypothesis-selection-on-khinalug-test</loc><lastmod>2026-02-26T06:08:30.248Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/membership-inference-attack-on-mimir</loc><lastmod>2026-02-26T06:08:50.027Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-avg-at-32</loc><lastmod>2026-02-26T05:36:31.560Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-avg-at-256</loc><lastmod>2026-02-26T05:35:55.106Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-avg-at-256</loc><lastmod>2026-02-26T05:35:54.972Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-language-model-evaluation-on-arena-hard-v2-0</loc><lastmod>2026-02-26T06:08:53.956Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-svamp-accuracy-by-context-size</loc><lastmod>2026-02-26T05:34:13.861Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-by-context-length</loc><lastmod>2026-02-26T05:34:00.702Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-performance-vs-context-size</loc><lastmod>2026-02-26T05:26:48.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-and-reasoning-on-mmlu-redux</loc><lastmod>2026-02-26T05:31:09.639Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-mmedbench-1-0-test</loc><lastmod>2026-02-26T05:39:07.791Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-test-acc-time</loc><lastmod>2026-02-26T05:31:01.716Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/domain-level-accuracy-estimation-on-stem-benchmarks-gsm8k-olympiadbench-math-scibench-etc-held-out</loc><lastmod>2026-02-26T05:42:38.521Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hypocritical-sycophancy-detection-on-sycophancy-dataset-knows-truth</loc><lastmod>2026-02-26T05:26:06.790Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/structured-summarization-on-nlpai4health-2025-test</loc><lastmod>2026-02-26T06:08:53.931Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/narrative-summarization-on-nlpai4health-2025-test</loc><lastmod>2026-02-26T06:08:53.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nlpai4health-2025-test</loc><lastmod>2026-02-26T06:08:53.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/society-and-culture-understanding-on-unified-korean-benchmark-society-and-culture</loc><lastmod>2026-03-20T10:04:57.170Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-assessment-on-strongreject</loc><lastmod>2026-02-26T05:57:58.696Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/disambiguation-and-completeness-on-ambigqa</loc><lastmod>2026-02-26T05:57:58.639Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/utility-assessment-on-mmlu-pro</loc><lastmod>2026-02-26T05:57:58.677Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factuality-assessment-on-truthfulqa-using-personalization-bias-pb</loc><lastmod>2026-02-26T05:57:58.658Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-ifbench-ifeval-ifeval-ko</loc><lastmod>2026-02-26T05:31:01.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-wordnet-sub-taxonomies</loc><lastmod>2026-02-26T05:50:17.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-medical-subject-headings-mesh</loc><lastmod>2026-02-26T05:50:17.197Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-food-semeval-2015-task-17</loc><lastmod>2026-02-26T05:52:16.394Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/taxonomy-expansion-on-semeval-2016-task-13-environment</loc><lastmod>2026-02-26T05:52:16.378Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/semantic-tagging-on-usas-english-test</loc><lastmod>2026-02-26T06:06:46.777Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-speech-on-common-voice-en-15</loc><lastmod>2026-02-26T06:08:30.046Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-to-speech-on-voxpopuli-en-v1-0</loc><lastmod>2026-02-26T06:08:37.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-super-gpqa-score-avg</loc><lastmod>2026-02-26T06:03:51.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-lcb</loc><lastmod>2026-02-26T06:03:51.958Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-phybench</loc><lastmod>2026-02-26T05:55:03.954Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/patient-simulation-on-ch-patientsim</loc><lastmod>2026-02-26T05:57:58.582Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/patient-simulation-on-ch-patientsim-test</loc><lastmod>2026-02-26T05:37:14.192Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/evidence-re-ranking-on-evidence-re-ranking</loc><lastmod>2026-02-26T06:01:51.200Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/claim-detection</loc><lastmod>2026-02-26T05:42:52.260Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stance-detection</loc><lastmod>2026-02-26T06:05:46.199Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/status-tracking-on-atod-complex-test</loc><lastmod>2026-02-26T06:04:46.492Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/goal-detection-on-atod-complex-test</loc><lastmod>2026-02-26T05:46:00.787Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/status-tracking-on-atod-medium-test</loc><lastmod>2026-02-26T06:04:46.478Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/goal-detection-on-atod-medium-test</loc><lastmod>2026-02-26T05:46:00.774Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fairness-evaluation-on-jigsaw</loc><lastmod>2026-02-26T05:37:48.265Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fairness-evaluation-on-crows-pair-fr</loc><lastmod>2026-02-26T06:03:18.169Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fairness-evaluation-on-crows-pair-en</loc><lastmod>2026-02-26T06:04:47.949Z</lastmod></url></urlset>