<?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/multi-input-ciphertext-multiplication-hardware_complexity-l-k-24-n-2-16-w-64</loc><lastmod>2026-02-26T05:52:36.939Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/2d-localization-on-indoor-lab-environment-5m-x-5m-5-locations-v1-test</loc><lastmod>2026-02-26T05:48:40.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/jailbreak-attack-evaluation-on-harmbench-400-random-samples</loc><lastmod>2026-02-26T05:23:53.265Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mobile-gui-automation-on-privscreen</loc><lastmod>2026-02-26T05:31:15.287Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-test-em-and-f1</loc><lastmod>2026-02-26T05:41:40.171Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-nlu-on-boolq-arc-e-arc-c-and-hellaswag</loc><lastmod>2026-02-26T05:37:53.672Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-research-on-xbench-deepsearch</loc><lastmod>2026-02-26T05:57:28.110Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-fineweb-edu-500m-token-val</loc><lastmod>2026-02-26T06:08:06.117Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-toolbench-goodput</loc><lastmod>2026-02-26T05:46:01.443Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/llm-inference-on-merge</loc><lastmod>2026-02-26T05:46:01.427Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/authorship-segmentation-on-mas-entire-corpus</loc><lastmod>2026-02-26T06:02:47.253Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/attribution-faithfulness-on-agnews</loc><lastmod>2026-02-26T05:45:11.266Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/attribution-faithfulness-on-sent140</loc><lastmod>2026-02-26T05:45:11.070Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-and-question-answering-on-short-context-task-suite-wikitext-lambada-triviaqa-piqa-hellaswag-winogrande-arc-easy-gpqa-social-iqa-openbookqa-sciq-test</loc><lastmod>2026-02-26T06:08:50.084Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/argumentative-fallacy-classification-on-afc</loc><lastmod>2026-02-26T05:51:28.108Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/decision-correctness-on-hmda-test</loc><lastmod>2026-02-26T05:43:33.796Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/process-verification-on-processbench-without-standard-answers</loc><lastmod>2026-02-26T05:58:11.586Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/process-verification-on-processbench-with-standard-answers</loc><lastmod>2026-02-26T05:58:11.414Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/summarization-on-ragtruth-summarization-test</loc><lastmod>2026-02-26T06:00:37.207Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/zero-shot-nlp-evaluation-on-aggregate</loc><lastmod>2026-02-26T05:35:15.726Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/commonsense-reasoning-on-comm</loc><lastmod>2026-02-26T05:31:10.451Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-modeling-on-nlp-standard-suite</loc><lastmod>2026-02-26T05:38:13.544Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-diamond-accuracy-avg-at-32</loc><lastmod>2026-02-26T05:34:31.024Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-accuracy-avg-at-32</loc><lastmod>2026-02-26T05:34:09.603Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-accuracy-avg-at-32</loc><lastmod>2026-02-26T05:34:31.001Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-bamboogle-em-f1aware</loc><lastmod>2026-02-26T05:41:39.011Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-musique-em-f1aware</loc><lastmod>2026-02-26T05:41:38.993Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-em-f1aware</loc><lastmod>2026-02-26T05:41:38.834Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-question-answering-on-triviaqa-em-f1aware</loc><lastmod>2026-02-26T05:41:38.818Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/early-rumor-detection-on-twitter-covid-19-test</loc><lastmod>2026-02-26T05:51:28.030Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/data-science-task-automation-on-xbench-ds</loc><lastmod>2026-02-26T06:03:53.569Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/web-based-question-answering-on-webwalkerqa</loc><lastmod>2026-02-26T06:05:10.885Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-pubmed-high-label</loc><lastmod>2026-02-26T05:31:08.493Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-pubmed-low-label</loc><lastmod>2026-02-26T05:31:08.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-high-label</loc><lastmod>2026-02-26T05:31:08.460Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-cora-low-label</loc><lastmod>2026-02-26T05:31:08.441Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/coreference-resolution-on-xwinograd-french</loc><lastmod>2026-04-23T10:55:27.466Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/natural-language-inference-on-xnli-french</loc><lastmod>2026-04-23T10:55:26.904Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-reasoning-on-livecodebench-1-0-test</loc><lastmod>2026-02-26T05:31:07.738Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-reasoning-on-gpqa-1-0-test</loc><lastmod>2026-02-26T05:31:07.720Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-knowledge-on-mmmlu</loc><lastmod>2026-02-26T05:32:35.958Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-squad-roc-rac-f1-at-b-ra-at-50</loc><lastmod>2026-02-26T06:00:19.613Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-pass-at-1-sharp-tokens</loc><lastmod>2026-04-06T07:22:26.288Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-calibration-on-gpqa-diamond</loc><lastmod>2026-02-26T05:26:07.155Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-calibration-on-gpqa-main</loc><lastmod>2026-02-26T05:26:07.128Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-calibration-on-scibench</loc><lastmod>2026-02-26T05:26:07.103Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/uncertainty-calibration-on-math-500</loc><lastmod>2026-02-26T05:26:07.085Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-on-imo-answerbench-score</loc><lastmod>2026-07-02T08:11:11.356Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-retrieval-augmented-generation-on-mkqa-1-0-test</loc><lastmod>2026-02-26T05:34:05.730Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-reward-modeling-on-bespoke-meta-ood</loc><lastmod>2026-02-26T05:37:49.074Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/personalized-generation-on-bespoke</loc><lastmod>2026-02-26T05:59:13.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-tool-use-on-xbench</loc><lastmod>2026-02-26T05:57:25.379Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-tool-use-on-browsecomp-zh</loc><lastmod>2026-02-26T05:57:25.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-tool-use-on-browsecomp</loc><lastmod>2026-02-26T05:57:25.349Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-turn-tool-use-on-gaia</loc><lastmod>2026-02-26T05:57:25.332Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/ai-peer-review-on-paperaudit-dataset-icml-branch</loc><lastmod>2026-02-26T05:53:58.324Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/gui-agent-navigation-and-action-on-aitz</loc><lastmod>2026-03-24T12:31:07.329Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-tool-use-domain-aggregate</loc><lastmod>2026-02-26T05:36:33.629Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-tool-use-domain-subset-3</loc><lastmod>2026-02-26T05:45:37.145Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-tool-use-domain-subset-2</loc><lastmod>2026-02-26T05:45:36.388Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-tool-use-domain-subset-1</loc><lastmod>2026-02-26T05:45:36.166Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/tool-use-on-tool-use-domain-subset-0</loc><lastmod>2026-02-26T05:45:36.186Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/evidence-grounding-on-biomedical-qa-test</loc><lastmod>2026-02-26T06:01:18.913Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/language-model-evaluation-across-subsets-on-elephant</loc><lastmod>2026-02-26T05:54:04.688Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-sage-eval</loc><lastmod>2026-02-26T06:03:37.479Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/presupposition-correction-on-cancer-myth</loc><lastmod>2026-02-26T05:54:58.472Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/retrieval-on-mmeb-v2</loc><lastmod>2026-02-26T05:47:00.364Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/scientific-coding-on-scicode</loc><lastmod>2026-06-23T08:22:15.330Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-term-dialogue-memory-on-longmemeval-test</loc><lastmod>2026-03-05T07:21:08.477Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/general-knowledge-on-knowledge-benchmarks-arc-c-arc-e-mmlu-gpqa-test</loc><lastmod>2026-02-27T10:52:01.256Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-evaluation-on-harmbench-and-safechain-safety-tuned</loc><lastmod>2026-02-27T10:52:02.905Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/view-change-prediction-on-view-change-prediction-dataset</loc><lastmod>2026-02-26T05:43:32.729Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-diagnosis-on-medeinst-robust-1-0</loc><lastmod>2026-02-26T06:02:22.131Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-diagnosis-on-medeinst-baseline-1-0</loc><lastmod>2026-02-26T05:37:40.825Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/fact-checking-on-infi-check-fg-1-0-test</loc><lastmod>2026-02-26T05:58:53.338Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hallucination-detection-on-frank</loc><lastmod>2026-02-26T05:37:30.465Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-simpleqa-verified-ood</loc><lastmod>2026-02-26T05:31:02.706Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-acc-ece-brier-auroc</loc><lastmod>2026-02-26T05:31:02.691Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-id-accuracy-ece-brier-auroc</loc><lastmod>2026-02-26T05:31:02.676Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-ethics-evaluation-on-medes-1-0-test</loc><lastmod>2026-02-26T05:41:30.624Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-25-pass-at-1-pass-at-8-sharp-invoc</loc><lastmod>2026-02-26T05:57:25.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-pass-at-1-pass-at-8-sharp-invoc</loc><lastmod>2026-02-26T05:57:25.215Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-modal-instruction-following-on-mm-mtbench</loc><lastmod>2026-04-07T11:09:01.270Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/node-classification-on-products-accuracy-avg-rank</loc><lastmod>2026-02-26T05:31:01.594Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/spreadsheet-understanding-on-spreadsheetllm-benchmark</loc><lastmod>2026-02-26T05:34:56.318Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-locomo-single</loc><lastmod>2026-06-05T09:25:27.486Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-question-answering-on-locomo-locomo_open</loc><lastmod>2026-06-05T09:25:27.453Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-v6-humaneval-plus-mbpp-plus-and-scicode</loc><lastmod>2026-02-26T05:57:25.144Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/interruption-handling-on-full-duplex-bench</loc><lastmod>2026-04-15T10:05:50.986Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-ambigqa-cover-exact-match</loc><lastmod>2026-02-26T05:40:00.180Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-nq-cover-exact-match</loc><lastmod>2026-02-26T05:40:00.164Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-bamboogle-cover-exact-match</loc><lastmod>2026-02-26T05:40:00.199Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-musique-cover-exact-match</loc><lastmod>2026-02-26T05:40:00.149Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-hotpotqa-cover-exact-match</loc><lastmod>2026-02-26T05:40:00.134Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/toxicity-evaluation-on-bold-23679-prompts-test</loc><lastmod>2026-02-26T05:36:27.096Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-relevance-on-minor-language-family-qwen2-5-series-benchmark-test</loc><lastmod>2026-02-26T05:53:04.008Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-relevance-on-romance-language-family-qwen2-5-series-benchmark-test</loc><lastmod>2026-02-26T05:53:03.990Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/search-relevance-on-germanic-language-family-qwen2-5-series-benchmark-test</loc><lastmod>2026-02-26T05:53:03.974Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/survey-generation-on-scientific-survey-generation-test</loc><lastmod>2026-02-26T05:58:33.251Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-machine-translation-on-sand-glass-zh-es-test</loc><lastmod>2026-02-26T05:39:34.620Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-machine-translation-on-sand-glass-zh-de-test</loc><lastmod>2026-02-26T05:38:42.938Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/constrained-machine-translation-on-sand-glass-zh-en-test</loc><lastmod>2026-02-26T05:39:34.598Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-am24-am25-2024-2025</loc><lastmod>2026-02-26T05:22:27.797Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/topic-modeling-on-ec-news</loc><lastmod>2026-05-06T07:41:26.734Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medical-tf-qa-test</loc><lastmod>2026-02-26T05:30:59.445Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sql-execution-performance-on-spider-n-1034</loc><lastmod>2026-02-26T05:41:42.456Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/conditional-generation-on-pile</loc><lastmod>2026-02-26T05:57:55.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-quality-estimation-completeness-on-wmt-da-2022-test</loc><lastmod>2026-02-26T05:39:38.323Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/machine-translation-quality-estimation-coherence-on-wmt-da-2022-test</loc><lastmod>2026-02-26T05:59:06.812Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-livecodebench-pass-at-1-v5</loc><lastmod>2026-02-26T06:11:14.848Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/length-extrapolation-on-ruler-8k-256k-contexts</loc><lastmod>2026-02-26T05:57:49.971Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-downstream-tasks-on-longbench-e-test</loc><lastmod>2026-02-26T06:02:41.022Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-completion-on-indoculture-native-prompts-test</loc><lastmod>2026-02-26T05:36:24.272Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-completion-on-arabculture-native-prompts-test</loc><lastmod>2026-02-26T05:36:24.254Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-completion-on-arabculture</loc><lastmod>2026-02-26T06:04:16.652Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sentence-completion-on-indoculture</loc><lastmod>2026-02-26T06:04:16.633Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/hierarchical-text-classification-on-amazon</loc><lastmod>2026-05-21T11:19:00.326Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-reading-comprehension-on-belebele</loc><lastmod>2026-05-12T15:37:16.583Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-pass-at-1-sharp-tk</loc><lastmod>2026-02-26T05:57:24.850Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-pass-at-1-sharp-tk</loc><lastmod>2026-02-26T05:57:34.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multitask-language-understanding-on-mmlu-f_con-o-5</loc><lastmod>2026-02-26T05:34:15.625Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-f_con-o-5</loc><lastmod>2026-02-26T05:26:50.617Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-avg-at-32</loc><lastmod>2026-02-26T06:09:07.699Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multilingual-long-document-retrieval-on-mldr-13-test</loc><lastmod>2026-02-26T05:53:05.967Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt-24-pass-at-1</loc><lastmod>2026-02-26T05:57:24.611Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-unseen-average</loc><lastmod>2026-02-26T06:03:51.327Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-seen-average</loc><lastmod>2026-02-26T06:03:51.312Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-unseen-fold-3</loc><lastmod>2026-02-26T06:03:51.297Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-fold-3-seen</loc><lastmod>2026-02-26T06:03:51.283Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-unseen-fold-2</loc><lastmod>2026-02-26T06:03:51.267Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-fold-2-seen</loc><lastmod>2026-02-26T06:03:51.248Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-unseen-fold-1</loc><lastmod>2026-02-26T06:03:51.230Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-fold-1-seen</loc><lastmod>2026-02-26T06:03:51.212Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/compositional-generalization-on-evaluation-dataset-full</loc><lastmod>2026-02-26T06:03:51.192Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/question-answering-on-pubmedqa-em-f1</loc><lastmod>2026-02-26T05:41:40.060Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/instruction-following-on-alpacaeval-arena-hard-10-percent-selection</loc><lastmod>2026-02-26T05:34:52.978Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/math-problem-solving-on-aggregated-benchmarks-aime24-math-oai-minerva-olympiad-acm23</loc><lastmod>2026-02-26T05:22:28.348Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-humaneval-humaneval-plus-mbpp-mbpp-plus-bigcode-test</loc><lastmod>2026-02-26T05:46:43.533Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-captioning-on-molreasoner-original-test</loc><lastmod>2026-02-26T05:37:16.673Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/speech-reconstruction-on-salmon-sentiment-consistency-emotional-2025b-ood</loc><lastmod>2026-02-26T06:08:29.261Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/video-preference-evaluation-on-sharegpt-video</loc><lastmod>2026-02-26T05:30:54.877Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-throughput-and-latency</loc><lastmod>2026-02-26T06:06:26.109Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/code-generation-on-mbpp-tokens-s-speedup</loc><lastmod>2026-02-26T06:06:34.910Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/reward-modeling-on-ppe-ifeval</loc><lastmod>2026-02-26T05:30:54.075Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/prompt-classification-on-sea-safeguardbench-english</loc><lastmod>2026-02-26T05:25:40.853Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-hop-question-answering-on-hotpotqa-test-val</loc><lastmod>2026-07-08T07:00:52.125Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/factual-knowledge-evaluation-on-wikidata-knowledge-infusion</loc><lastmod>2026-02-26T05:30:53.957Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-accuracy-length</loc><lastmod>2026-02-26T05:30:53.941Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-amc23-accuracy-length</loc><lastmod>2026-02-26T05:30:53.925Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-accuracy-length</loc><lastmod>2026-02-26T05:30:53.907Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/medical-question-answering-on-medical-benchmarks-medqa-medmcqa-bullet-test</loc><lastmod>2026-02-26T05:52:28.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-memory-retrieval-on-locomo-test</loc><lastmod>2026-02-26T05:52:58.781Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/agent-memory-question-answering-on-perltqa-test</loc><lastmod>2026-02-26T05:37:01.009Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-lrls-bengali-swahili-telugu</loc><lastmod>2026-02-26T05:37:23.680Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/logical-reasoning-on-hrls-high-resource-languages</loc><lastmod>2026-02-26T05:37:23.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/deep-research-on-browsecomp-zh</loc><lastmod>2026-02-26T05:30:53.330Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/omnimodal-question-answering-on-omnivideobench-1-0-test</loc><lastmod>2026-02-26T05:39:36.912Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-audio-video-question-answering-on-worldsense</loc><lastmod>2026-02-26T05:35:16.088Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-pass-at-1-tps-latency</loc><lastmod>2026-03-19T09:09:37.044Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-theoremqa-pass-at-1</loc><lastmod>2026-02-26T05:57:24.305Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-math-pass-at-1</loc><lastmod>2026-02-26T05:57:24.290Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-val</loc><lastmod>2026-04-14T10:05:17.717Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/long-context-understanding-on-longbench-specific-qa-retrieval-metrics</loc><lastmod>2026-02-26T05:49:50.017Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-detection-on-polyguard-social-media</loc><lastmod>2026-02-26T05:26:05.385Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-detection-on-polyguard-hr</loc><lastmod>2026-02-26T05:26:05.365Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-detection-on-polyguard-education</loc><lastmod>2026-02-26T05:26:05.344Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-detection-on-polyguard-cyber</loc><lastmod>2026-02-26T05:26:05.321Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/safety-detection-on-polyguard-code</loc><lastmod>2026-02-26T05:26:05.297Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/overrefusal-detection-on-or-bench</loc><lastmod>2026-02-26T05:26:05.259Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-visual-question-answering-on-video-salmonn-2-test</loc><lastmod>2026-02-26T05:52:53.714Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-visual-question-answering-on-omnivideobench</loc><lastmod>2026-02-26T05:30:51.809Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/audio-visual-question-answering-on-worldsense</loc><lastmod>2026-02-26T05:30:51.789Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-accuracy</loc><lastmod>2026-02-26T05:30:51.647Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-aime24-acc-at-16-tokens</loc><lastmod>2026-03-24T13:59:27.740Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/relation-extraction-on-cail-2022</loc><lastmod>2026-02-26T05:58:30.905Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/entity-extraction-on-cail-2022</loc><lastmod>2026-02-26T05:58:30.855Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/creative-writing-on-arena-hard</loc><lastmod>2026-04-10T08:14:18.599Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multi-task-reasoning-on-mmlu-pro</loc><lastmod>2026-05-12T13:56:45.810Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-verification-on-mmmu-mathvision-mathverse-vo-dynamath-wemath-overall</loc><lastmod>2026-02-27T10:42:23.083Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-verification-on-wemath</loc><lastmod>2026-02-27T10:42:23.050Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-verification-on-dynamath</loc><lastmod>2026-02-27T10:42:23.016Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-verification-on-mathverse-vo</loc><lastmod>2026-02-27T10:42:22.988Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-verification-on-mathvision</loc><lastmod>2026-02-27T10:42:22.958Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/step-wise-verification-on-mmmu</loc><lastmod>2026-02-27T10:42:22.929Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/maze-navigation-on-maze-hard</loc><lastmod>2026-05-20T09:25:50.094Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-knowledge-editing-on-mmqake-rephrased-image</loc><lastmod>2026-02-27T10:41:52.072Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/multimodal-knowledge-editing-on-mmqake-original-image</loc><lastmod>2026-02-27T10:41:52.037Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/partial-maxsat-on-pms-2021</loc><lastmod>2026-02-26T06:03:50.031Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/sparse-autoencoder-concept-alignment-on-cub</loc><lastmod>2026-02-26T06:04:31.763Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-gsm8k-score-sharp-strategy</loc><lastmod>2026-02-26T06:03:49.976Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/mathematical-reasoning-on-math-score-and-strategy-count</loc><lastmod>2026-02-26T06:03:49.961Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-docking-on-jak2</loc><lastmod>2026-02-26T05:52:00.767Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-docking-on-5ht1b</loc><lastmod>2026-02-26T05:52:00.731Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-docking-on-fa7</loc><lastmod>2026-02-26T05:52:00.714Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/molecular-docking-on-parp1</loc><lastmod>2026-02-26T05:52:00.697Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lossless-genomics-data-compression-on-genomics-dataset-suite-aggregate</loc><lastmod>2026-02-26T05:36:07.674Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lossless-genomics-data-compression-on-tagu</loc><lastmod>2026-02-26T05:39:41.948Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lossless-genomics-data-compression-on-acsc</loc><lastmod>2026-02-26T05:39:41.930Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lossless-genomics-data-compression-on-arth</loc><lastmod>2026-02-26T05:39:41.914Z</lastmod></url><url><loc>https://www.sota2.com/research/sota/lossless-genomics-data-compression-on-mogu</loc><lastmod>2026-02-26T05:39:41.896Z</lastmod></url></urlset>