<?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/robustness-to-natural-adversarial-examples-on-naturalbench</loc><lastmod>2026-02-27T11:03:11.363Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ood-generalization-on-oodcv</loc><lastmod>2026-02-27T11:03:11.334Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multispectral-semantic-segmentation-on-potsdam-evaluation-set</loc><lastmod>2026-02-26T05:54:01.663Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/e-commerce-short-video-understanding-on-e-vads-1-0-test</loc><lastmod>2026-02-26T06:02:40.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-retrieval-on-rvms-bench-1-0-test</loc><lastmod>2026-02-26T05:45:37.865Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-reasoning-on-twiff-bench</loc><lastmod>2026-06-05T08:53:36.448Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/context-aware-image-retrieval-on-disbench-overall</loc><lastmod>2026-02-26T05:41:39.391Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/context-aware-image-retrieval-on-disbench-intra-event</loc><lastmod>2026-02-26T05:41:39.355Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-appropriateness-classification-on-education</loc><lastmod>2026-02-26T05:42:49.664Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-appropriateness-classification-on-spa</loc><lastmod>2026-02-26T05:42:49.475Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-completion-on-bigcodebench-hard</loc><lastmod>2026-02-26T05:57:26.526Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-completion-on-bigcodebench-full</loc><lastmod>2026-02-26T05:57:26.510Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-completion-on-humaneval-pass-at-1</loc><lastmod>2026-02-26T05:57:26.494Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ipi-sanitization-on-jfleg-rte-unseen</loc><lastmod>2026-02-26T05:23:55.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoofing-attack-robustness-on-booksum</loc><lastmod>2026-02-26T05:24:54.592Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrase-attack-robustness-on-booksum</loc><lastmod>2026-02-26T05:24:54.563Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoofing-attack-robustness-on-c4-realnewslike</loc><lastmod>2026-02-26T05:24:54.538Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/paraphrase-attack-robustness-on-c4-realnewslike</loc><lastmod>2026-02-26T05:24:54.511Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoofing-attack-traceability-on-rtp-lx-test</loc><lastmod>2026-02-26T05:24:54.481Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spoofing-attack-traceability-on-realtoxicityprompts-test</loc><lastmod>2026-02-26T05:24:54.459Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-on-jailbreak</loc><lastmod>2026-02-26T05:50:01.136Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-attack-on-pems03</loc><lastmod>2026-02-26T05:51:45.122Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/backdoor-attack-on-weather</loc><lastmod>2026-02-26T05:51:45.105Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fingerprinting-on-ctcc-fingerprinting</loc><lastmod>2026-02-26T05:24:00.265Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tennis-pushing-on-vla-backdoor-evaluation-tasks</loc><lastmod>2026-02-26T06:05:11.172Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/peg-insertion-on-vla-backdoor-evaluation-tasks</loc><lastmod>2026-02-26T06:03:05.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/button-pressing-on-vla-backdoor-evaluation-tasks</loc><lastmod>2026-02-26T06:05:11.157Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/drawer-opening-on-vla-backdoor</loc><lastmod>2026-02-26T06:05:39.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/pick-and-place-on-vla-backdoor-evaluation-tasks</loc><lastmod>2026-02-26T06:03:05.184Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/robotic-manipulation-long-on-libero-long-1-0-test</loc><lastmod>2026-02-26T06:03:06.135Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-jailbreak-defense-on-mtj-pro</loc><lastmod>2026-02-26T05:59:03.962Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-attack-misdirection-on-mtj-pro-test</loc><lastmod>2026-02-26T05:59:03.945Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-repair-on-codefix</loc><lastmod>2026-02-26T05:45:20.182Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-accuracy-top-2-top-3-mse_l</loc><lastmod>2026-02-26T05:32:58.467Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/model-lineage-attestation-on-cifar100-caltech-pipeline-context</loc><lastmod>2026-02-26T06:05:57.798Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/secure-inference-on-mnist-test</loc><lastmod>2026-02-26T05:54:15.442Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ddos-attack-classification-on-ciciot-2023</loc><lastmod>2026-02-26T05:46:47.945Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ddos-attack-classification-on-cic-iot-2023</loc><lastmod>2026-02-26T05:46:47.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/steganographic-secret-extraction-on-wikitext-103-w-test</loc><lastmod>2026-02-26T05:31:16.801Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/federated-learning-classification-on-mnist-test</loc><lastmod>2026-02-26T05:31:16.409Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/image-classification-on-mnist-vit-lite-variant-test</loc><lastmod>2026-02-26T05:31:16.390Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/federated-image-classification-on-fashion-mnist-test</loc><lastmod>2026-02-26T05:31:16.374Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/masked-language-modeling-fine-tuning-on-arxiv-fine-tuning</loc><lastmod>2026-02-26T05:50:53.393Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/privacy-amplification-on-cifar-10-train</loc><lastmod>2026-02-26T05:50:53.373Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/partial-code-vulnerability-detection-on-sven</loc><lastmod>2026-02-27T10:57:36.642Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unknown-attack-detection-on-iot-23</loc><lastmod>2026-02-26T05:37:58.422Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/unknown-attack-detection-on-ciciot-2023</loc><lastmod>2026-02-26T05:37:28.213Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speculative-decoding-evaluation-on-ood-mean</loc><lastmod>2026-02-26T06:04:41.780Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-mathematical-reasoning-on-mgsm-efficiency-metrics</loc><lastmod>2026-02-26T06:04:42.670Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-retrieval-on-niah-multivalue</loc><lastmod>2026-02-26T06:04:41.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/planning-style-reasoning-on-acp-prog-gen</loc><lastmod>2026-02-26T06:04:41.752Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-centric-vision-language-understanding-on-ocr-bench</loc><lastmod>2026-02-27T09:33:57.707Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-deduction-test</loc><lastmod>2026-02-26T05:31:13.531Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-math-supergpqa-bbeh-and-mmlu-pro</loc><lastmod>2026-02-26T05:54:28.747Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-olympiad-minerva-gsm8k-amc-aime24-test</loc><lastmod>2026-02-26T05:54:35.056Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/exact-match-on-big-bench-hard-bbh</loc><lastmod>2026-02-26T05:42:30.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-instruction-following-on-frontalk-single-turn-1-0-test</loc><lastmod>2026-02-26T05:55:15.382Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/throughput-measurement-on-llama-2-13b</loc><lastmod>2026-02-26T06:06:26.123Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-reasoning-on-tempreason-l3-in-domain-test</loc><lastmod>2026-02-26T05:41:39.221Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-reasoning-on-tempreason-l2-in-domain-test</loc><lastmod>2026-02-26T05:41:39.204Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-avg-at-8</loc><lastmod>2026-02-26T05:36:33.457Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-large-language-model-evaluation-on-core-capabilities-aggregate</loc><lastmod>2026-02-26T05:35:54.193Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-translation-on-code-translation-dataset</loc><lastmod>2026-02-26T05:38:03.965Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-pass-at-1-percent</loc><lastmod>2026-02-26T05:57:25.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/chain-of-thought-reasoning-on-cot-collection</loc><lastmod>2026-02-26T05:39:40.257Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-openbookqa-composite-score</loc><lastmod>2026-02-26T05:39:40.239Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-220k</loc><lastmod>2026-02-26T05:39:40.223Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-composite-score</loc><lastmod>2026-02-26T05:39:40.206Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-ability-on-alpaca-test</loc><lastmod>2026-02-26T05:34:52.817Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-test-accuracy</loc><lastmod>2026-02-26T05:49:42.954Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-ability-on-vicuna-eval-test</loc><lastmod>2026-02-26T06:08:15.903Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/information-seeking-on-browsecomp-standard-full</loc><lastmod>2026-02-26T05:57:25.653Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-understanding-on-mmar-test</loc><lastmod>2026-02-26T05:57:48.854Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-aime-25-avg-at-32</loc><lastmod>2026-05-28T08:54:11.076Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematics-on-aime-24</loc><lastmod>2026-05-28T08:54:11.050Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cross-corpus-ranking-on-cross-corpus-dataset</loc><lastmod>2026-02-26T05:36:30.019Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-language-understanding-on-12-task-evaluation-suite-test</loc><lastmod>2026-02-26T05:35:51.181Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-text-generation-on-factscore</loc><lastmod>2026-07-09T07:52:02.236Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-performance</loc><lastmod>2026-02-26T05:57:48.883Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-trickme</loc><lastmod>2026-02-26T05:31:05.901Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-grace</loc><lastmod>2026-02-26T05:31:05.882Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-guess</loc><lastmod>2026-02-26T05:31:05.866Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/confidence-estimation-on-20q</loc><lastmod>2026-02-26T05:31:05.847Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-autoformalization-on-mathverse-solid-geometry</loc><lastmod>2026-02-26T05:39:37.422Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-sst2-deletion-insertion-robustness</loc><lastmod>2026-02-27T10:54:03.897Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentiment-classification-on-imdb-robustness-metrics</loc><lastmod>2026-02-27T10:54:03.863Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-unlearning-on-tofu-5-percent-forget</loc><lastmod>2026-02-26T05:48:46.284Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/db-task-on-lifelong-agent-bench-task</loc><lastmod>2026-06-17T07:17:18.959Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-trustllm</loc><lastmod>2026-03-18T09:15:19.859Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-296-204-test</loc><lastmod>2026-02-26T05:34:57.219Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-qasper-1200-251-test</loc><lastmod>2026-02-26T05:34:57.200Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/preference-alignment-on-prism</loc><lastmod>2026-02-26T06:08:58.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-on-mmlu-pro-pass-at-1</loc><lastmod>2026-04-28T09:09:30.053Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-steering</loc><lastmod>2026-02-26T06:05:45.632Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/efficiency-aware-code-generation-on-effibench-x-c-plus-plus</loc><lastmod>2026-02-26T05:42:34.729Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/efficiency-aware-code-generation-on-effibench-x-python</loc><lastmod>2026-02-26T05:42:34.713Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-and-reasoning-on-triviaqa</loc><lastmod>2026-04-21T07:25:09.335Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-conversation-on-pcogalignbench-ls2</loc><lastmod>2026-02-26T05:48:08.434Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-conversation-on-pcogalignbench-ls1</loc><lastmod>2026-02-26T05:48:08.416Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-conversation-on-mmrole-ood</loc><lastmod>2026-02-26T05:48:09.894Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-conversation-on-mmrole-id</loc><lastmod>2026-02-26T05:48:09.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/analogy-solving-on-sat-problems</loc><lastmod>2026-02-27T10:48:00.204Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/analogy-solving-on-green-s-analogy-far-analogy</loc><lastmod>2026-02-27T10:48:00.175Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/analogy-solving-on-green-s-analogy-near-analogy</loc><lastmod>2026-02-27T10:48:00.141Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-level-tool-invocation-safety-detection-on-agentdojo-traj</loc><lastmod>2026-02-26T05:31:01.052Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-level-tool-invocation-safety-detection-on-asb-traj</loc><lastmod>2026-02-26T05:31:01.034Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-level-tool-invocation-safety-detection-on-agentharm-traj</loc><lastmod>2026-02-26T05:31:01.015Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/story-completion-on-xstorycloze</loc><lastmod>2026-02-27T10:47:28.401Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/simultaneous-machine-translation-on-acl60-60-en-de-eval</loc><lastmod>2026-02-26T05:37:02.021Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-on-machine-translation-parallel-data-test</loc><lastmod>2026-02-26T05:38:41.400Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-grailqa-overall</loc><lastmod>2026-02-26T05:46:36.047Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermark-detection-on-ten-exam-benchmark-1-0-test</loc><lastmod>2026-02-26T05:40:48.550Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/watermarking-prevention-on-ten-exam-benchmark-1-0-test</loc><lastmod>2026-02-26T05:58:58.035Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cultural-pluralism-alignment-on-wvs-world-values-survey</loc><lastmod>2026-02-26T05:42:05.943Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cultural-pluralism-alignment-cultural-knowledge-on-blend</loc><lastmod>2026-02-26T05:42:06.111Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/visual-question-answering-on-mme</loc><lastmod>2026-06-01T07:39:50.481Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-truthfulqa-1-0-test</loc><lastmod>2026-02-26T05:21:42.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-avg-at-16-accuracy</loc><lastmod>2026-03-25T15:16:05.873Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/embodied-instruction-following-on-eb-alfred-1-0-test</loc><lastmod>2026-02-26T06:05:36.928Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/causal-discovery-on-alarm-d-37-e-46-medium-scale-test</loc><lastmod>2026-02-26T05:58:38.923Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-future-prediction-on-futureomni-1-0-overall</loc><lastmod>2026-02-26T05:34:11.805Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-bbq-test</loc><lastmod>2026-02-26T05:34:30.652Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multiple-choice-reasoning-on-gpqa-full-dataset</loc><lastmod>2026-03-25T14:23:30.613Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-question-answering-on-locomo</loc><lastmod>2026-02-26T05:52:58.586Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-question-answering-on-locomo-overall-all-categories-1-0</loc><lastmod>2026-02-26T05:41:43.443Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-question-answering-on-locomo-single-hop-1-0</loc><lastmod>2026-02-26T05:41:38.082Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-question-answering-on-locomo-open-domain-1-0</loc><lastmod>2026-02-26T05:41:38.065Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-question-answering-on-locomo-temporal-1-0</loc><lastmod>2026-02-26T05:41:38.048Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-horizon-question-answering-on-locomo-multi-hop-1-0</loc><lastmod>2026-02-26T05:41:37.885Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-question-answering-on-locomo-overall</loc><lastmod>2026-02-26T05:36:19.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-question-answering-on-locomo-single-hop</loc><lastmod>2026-02-26T05:43:31.660Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-question-answering-on-locomo-open-domain</loc><lastmod>2026-02-26T05:42:46.766Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-question-answering-on-locomo-temporal</loc><lastmod>2026-02-26T05:43:31.643Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-question-answering-on-locomo-multi-hop</loc><lastmod>2026-02-26T05:43:31.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-tool-use-interaction-on-vitabench</loc><lastmod>2026-02-26T05:40:36.638Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-overall-macro-average</loc><lastmod>2026-02-26T05:33:57.275Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aicrypto</loc><lastmod>2026-02-26T05:30:57.616Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-financemath</loc><lastmod>2026-02-26T05:30:57.600Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-liar-raw</loc><lastmod>2026-02-26T05:58:32.795Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-kathbath-tamil</loc><lastmod>2026-02-26T06:08:34.231Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-wenetspeech-yue-long</loc><lastmod>2026-04-21T12:37:51.464Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-wenetspeech-yue-short</loc><lastmod>2026-04-21T12:37:51.436Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-tool-use-on-acebench-agent-task</loc><lastmod>2026-07-09T07:27:13.166Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-language-understanding-on-mmmlu-language-specific-averages</loc><lastmod>2026-07-07T07:39:17.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conversational-query-retrieval-on-topiocqa</loc><lastmod>2026-02-26T05:50:27.295Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/open-ended-information-seeking-on-infinity-chat-test</loc><lastmod>2026-02-26T05:40:32.201Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-level-5</loc><lastmod>2026-05-26T07:19:11.302Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-entailmentbank-test</loc><lastmod>2026-02-26T05:37:01.114Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-processbench</loc><lastmod>2026-07-02T08:11:10.134Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/cbt-conversation-generation-on-emollm-test</loc><lastmod>2026-02-26T05:37:43.977Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-gemma2-9b-base-max-256-tokens</loc><lastmod>2026-02-26T05:24:50.506Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-gemma2-9b-base-max-128-tokens</loc><lastmod>2026-02-26T05:24:50.486Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-llama3-8b-base-max-256-tokens</loc><lastmod>2026-02-26T05:24:50.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-llama3-8b-base-max-128-tokens</loc><lastmod>2026-02-26T05:24:50.445Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-c4-gemma2-9b-base-max-256-tokens</loc><lastmod>2026-02-26T05:24:50.423Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-c4-gemma2-9b-base-max-128-tokens</loc><lastmod>2026-02-26T05:24:50.402Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-c4-llama3-8b-base-max-256-tokens</loc><lastmod>2026-02-26T05:24:50.369Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-bit-llm-watermarking-on-c4-llama3-8b-base-max-128-tokens</loc><lastmod>2026-02-26T05:24:50.341Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-reconstruction-from-embeddings-on-pubmed</loc><lastmod>2026-02-26T05:37:14.174Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/text-reconstruction-from-embeddings-on-ms-marco</loc><lastmod>2026-02-26T05:37:14.155Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/repository-reconstruction-on-repocraft-test</loc><lastmod>2026-02-26T06:04:47.581Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mmi-scoring-on-mmi</loc><lastmod>2026-02-26T05:50:53.267Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-question-answering-on-novel-graphrag-bench</loc><lastmod>2026-02-26T05:48:09.344Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-form-question-answering-on-graphrag-bench-med</loc><lastmod>2026-02-26T05:48:08.345Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-2wikimultihopqa-llm-acc-cont-acc</loc><lastmod>2026-02-26T05:48:09.328Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-llm-acc-and-cont-acc</loc><lastmod>2026-02-26T05:48:08.332Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reasoning-on-aime24-aime25-hmmt25-average</loc><lastmod>2026-02-26T05:30:53.092Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-and-jailbreaking-attack-detection-on-maliciousinstruct</loc><lastmod>2026-02-26T05:26:05.490Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-and-jailbreaking-attack-detection-on-jailbreakbench</loc><lastmod>2026-02-26T05:26:05.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-and-jailbreaking-attack-detection-on-harmbench</loc><lastmod>2026-02-26T05:26:05.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-and-jailbreaking-attack-detection-on-beavertails</loc><lastmod>2026-02-26T05:26:05.431Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/adversarial-and-jailbreaking-attack-detection-on-advbench</loc><lastmod>2026-02-26T05:26:05.412Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agentic-performance-on-tau2-bench</loc><lastmod>2026-04-30T06:37:50.759Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-understanding-on-clothoaqa</loc><lastmod>2026-06-18T06:45:58.449Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/automatic-speech-recognition-on-wenetspeech-net</loc><lastmod>2026-03-26T13:58:43.404Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-vqa-on-hallusionbench</loc><lastmod>2026-05-22T08:15:19.260Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/stem-and-reasoning-on-mmmu-pro</loc><lastmod>2026-07-07T10:24:06.919Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/temporal-question-answering-on-timeqa-easy</loc><lastmod>2026-06-16T08:49:11.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/runtime-agent-memory-on-hotpotqa</loc><lastmod>2026-02-26T05:43:30.690Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/runtime-agent-memory-on-longmemeval</loc><lastmod>2026-02-26T05:43:30.668Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/runtime-agent-memory-on-locomo</loc><lastmod>2026-02-26T05:43:30.652Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-performance-on-aggregate-across-math-code-chat</loc><lastmod>2026-06-26T08:17:10.399Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-throughput-and-speedup</loc><lastmod>2026-02-26T06:06:25.694Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-rewardbench-2</loc><lastmod>2026-03-05T06:56:22.529Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-acc-tps-speedup</loc><lastmod>2026-02-26T05:30:50.816Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-accuracy-tps-and-speedup</loc><lastmod>2026-02-26T05:30:50.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-llama-13b-2</loc><lastmod>2026-02-26T05:57:57.719Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gaokao-en</loc><lastmod>2026-02-26T05:57:19.322Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-pass-rate</loc><lastmod>2026-02-26T05:57:19.304Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc23-pass-rate-avg-at-8</loc><lastmod>2026-02-26T05:57:20.168Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-pass-rate-avg-at-8</loc><lastmod>2026-02-26T05:57:20.150Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-based-agent-qa-on-webwalkerqa</loc><lastmod>2026-04-30T06:59:08.362Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-performance-estimation-on-winogrande-test</loc><lastmod>2026-02-26T05:49:09.892Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-performance-estimation-on-truthfulqa-test</loc><lastmod>2026-02-26T05:49:25.474Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-performance-estimation-on-mmlu-test</loc><lastmod>2026-06-17T07:20:51.445Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-performance-estimation-on-hellaswag-test</loc><lastmod>2026-02-26T05:49:25.438Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-performance-estimation-on-gsm8k-test</loc><lastmod>2026-02-26T05:49:25.424Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-performance-estimation-on-arc-test</loc><lastmod>2026-02-26T05:49:25.407Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-tabmwp</loc><lastmod>2026-02-26T05:41:37.471Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-em</loc><lastmod>2026-02-26T05:42:28.053Z</lastmod></url></urlset>