{"3dsrbench":{"n":20,"recent":8,"stars":2},"aa-briefcase":{"n":23,"recent":20,"stars":3},"aa-fdb-backchannel":{"n":37,"recent":18,"stars":4},"aa-fdb-interruption":{"n":37,"recent":18,"stars":4},"aa-fdb-pause-handling":{"n":37,"recent":18,"stars":4},"aa-fdb-turn-taking":{"n":37,"recent":18,"stars":4},"aa-index":{"n":11,"recent":6,"stars":2},"aa-lcr":{"n":209,"recent":77,"stars":5},"aa-omniscience":{"n":73,"recent":29,"stars":4},"aa-omniscience-accuracy":{"n":42,"recent":20,"stars":4},"aa-omniscience-decision-accuracy":{"n":28,"recent":27,"stars":3},"aa-omniscience-decision-non-hallucination":{"n":28,"recent":27,"stars":3},"aa-omniscience-non-hallucination":{"n":24,"recent":7,"stars":2},"aa-omniscience-public":{"n":10,"recent":6,"stars":2},"aa-omniscience-public-accuracy":{"n":3,"recent":3,"stars":1},"aa-s2s-ttfa":{"n":39,"recent":17,"stars":4},"aa-speech-agent-arena":{"n":29,"recent":13,"stars":3},"aa-speech-agent-task-success":{"n":29,"recent":13,"stars":3},"acebench":{"n":17,"recent":0,"stars":1},"acebench-zh":{"n":5,"recent":0,"stars":0},"acos-decision":{"n":38,"recent":37,"stars":4},"acp-bench-bool":{"n":23,"recent":0,"stars":1},"acp-bench-mcq":{"n":23,"recent":0,"stars":1},"activitynet-qa":{"n":10,"recent":0,"stars":1},"acva":{"n":5,"recent":0,"stars":0},"advancedif":{"n":12,"recent":6,"stars":2},"aethercode":{"n":17,"recent":2,"stars":1},"afrimed-qa":{"n":4,"recent":0,"stars":0},"ag-news":{"n":7,"recent":6,"stars":1},"agentbench":{"n":7,"recent":0,"stars":0},"agentcompany":{"n":7,"recent":0,"stars":0},"agentdojo":{"n":21,"recent":0,"stars":1},"agentharm":{"n":1,"recent":0,"stars":0},"agentic-coding":{"n":22,"recent":0,"stars":1},"agentif":{"n":4,"recent":4,"stars":1},"agentif-oneday":{"n":3,"recent":1,"stars":0},"agents-last-exam":{"n":114,"recent":97,"stars":5},"agents-last-exam-score":{"n":76,"recent":61,"stars":4},"agentworldbench-android":{"n":14,"recent":3,"stars":2},"agentworldbench-mcp":{"n":14,"recent":3,"stars":2},"agentworldbench-os":{"n":14,"recent":3,"stars":2},"agentworldbench-search":{"n":14,"recent":3,"stars":2},"agentworldbench-swe":{"n":14,"recent":3,"stars":2},"agentworldbench-terminal":{"n":14,"recent":3,"stars":2},"agentworldbench-web":{"n":14,"recent":3,"stars":2},"agieval":{"n":228,"recent":16,"stars":5},"agieval-lsat-ar":{"n":6,"recent":0,"stars":0},"ai2d":{"n":258,"recent":8,"stars":4},"aicodeking-non-agentic":{"n":20,"recent":0,"stars":1},"aider-code-editing":{"n":51,"recent":0,"stars":2},"aider-polyglot":{"n":133,"recent":2,"stars":3},"aider-polyglot-diff":{"n":65,"recent":0,"stars":2},"aime-2024":{"n":266,"recent":10,"stars":5},"aime-2024-ko":{"n":4,"recent":0,"stars":0},"aime-2025":{"n":498,"recent":57,"stars":5},"aime-2026-i":{"n":170,"recent":67,"stars":5},"aime-2026-i-with-tools":{"n":4,"recent":1,"stars":0},"ainstein-swe-bench":{"n":5,"recent":0,"stars":0},"alignbench":{"n":98,"recent":0,"stars":2},"all-angles-bench":{"n":17,"recent":1,"stars":1},"almieyar":{"n":4,"recent":0,"stars":0},"alpacaeval":{"n":51,"recent":3,"stars":3},"alpacaeval-1.0":{"n":45,"recent":0,"stars":2},"alpacaeval-2.0":{"n":121,"recent":6,"stars":4},"am-2k-mad":{"n":2,"recent":2,"stars":0},"amazon-esci":{"n":38,"recent":37,"stars":4},"amc-23":{"n":64,"recent":0,"stars":2},"amobench":{"n":25,"recent":2,"stars":1},"amobench-zh":{"n":9,"recent":0,"stars":0},"android-daily":{"n":4,"recent":1,"stars":0},"androidbench":{"n":5,"recent":5,"stars":1},"androidworld":{"n":70,"recent":15,"stars":4},"anli":{"n":38,"recent":37,"stars":4},"apex-agents":{"n":76,"recent":41,"stars":4},"apex-agents-v1.1":{"n":54,"recent":43,"stars":4},"apex-swe":{"n":3,"recent":3,"stars":1},"api-bank":{"n":5,"recent":0,"stars":0},"api-bank-decision":{"n":36,"recent":35,"stars":4},"arabicmmlu":{"n":17,"recent":0,"stars":1},"arc-agi-1":{"n":325,"recent":138,"stars":5},"arc-agi-2":{"n":340,"recent":146,"stars":5},"arc-agi-3":{"n":9,"recent":7,"stars":1},"arc-average":{"n":11,"recent":0,"stars":1},"arc-cf":{"n":1,"recent":0,"stars":0},"arc-challenge":{"n":378,"recent":60,"stars":5},"arc-challenge-chat":{"n":1,"recent":0,"stars":0},"arc-challenge-de":{"n":2,"recent":0,"stars":0},"arc-challenge-multilingual":{"n":1,"recent":0,"stars":0},"arc-easy":{"n":172,"recent":47,"stars":5},"arc-easy-de":{"n":2,"recent":0,"stars":0},"arena-hard":{"n":89,"recent":3,"stars":3},"arena-hard-v2":{"n":104,"recent":4,"stars":4},"arena-hard-v2-creative-writing":{"n":18,"recent":0,"stars":1},"arena-hard-v2-hard-prompt":{"n":19,"recent":0,"stars":1},"arkitscenes":{"n":11,"recent":0,"stars":1},"art-agent-red-teaming":{"n":38,"recent":0,"stars":2},"artifactsbench":{"n":55,"recent":10,"stars":4},"arxivmath":{"n":18,"recent":12,"stars":3},"asr-ami":{"n":4,"recent":0,"stars":0},"asr-commonvoice-8-ja":{"n":14,"recent":1,"stars":1},"asr-earnings22":{"n":4,"recent":0,"stars":0},"asr-gigaspeech":{"n":4,"recent":0,"stars":0},"asr-jsut-basic5000":{"n":14,"recent":1,"stars":1},"asr-librispeech-clean":{"n":15,"recent":0,"stars":1},"asr-librispeech-other":{"n":17,"recent":0,"stars":1},"asr-reazonspeech":{"n":14,"recent":1,"stars":1},"asr-spgispeech":{"n":4,"recent":0,"stars":0},"asr-ted-lium":{"n":4,"recent":0,"stars":0},"asr-voxpopuli":{"n":4,"recent":0,"stars":0},"astabench":{"n":27,"recent":0,"stars":1},"attaq":{"n":18,"recent":3,"stars":2},"audio-multichallenge":{"n":31,"recent":11,"stars":4},"autocodebench":{"n":45,"recent":0,"stars":2},"autocodebench-lite":{"n":46,"recent":0,"stars":2},"autologi":{"n":7,"recent":0,"stars":0},"automationbench":{"n":70,"recent":60,"stars":4},"automationbench-aa":{"n":16,"recent":15,"stars":3},"automationbench-partial":{"n":10,"recent":9,"stars":2},"babe":{"n":11,"recent":1,"stars":1},"babyvision":{"n":71,"recent":24,"stars":4},"babyvision-with-tools":{"n":20,"recent":14,"stars":3},"balrog":{"n":27,"recent":0,"stars":1},"bankertoolbench":{"n":14,"recent":10,"stars":3},"banking77":{"n":36,"recent":35,"stars":4},"bbh":{"n":457,"recent":27,"stars":5},"bbh-decision":{"n":39,"recent":38,"stars":4},"bbh-zh":{"n":14,"recent":2,"stars":1},"bbl-hard":{"n":1,"recent":0,"stars":0},"bbq":{"n":12,"recent":0,"stars":1},"beam-128k":{"n":3,"recent":1,"stars":0},"beavertails":{"n":4,"recent":0,"stars":0},"belebele":{"n":34,"recent":15,"stars":4},"benchcad":{"n":14,"recent":12,"stars":3},"benchcad-python-tool":{"n":12,"recent":10,"stars":3},"beyondaime":{"n":35,"recent":5,"stars":3},"bfcl":{"n":24,"recent":0,"stars":1},"bfcl-decision":{"n":38,"recent":37,"stars":4},"bfcl-live-v2":{"n":9,"recent":0,"stars":0},"bfcl-v2":{"n":9,"recent":0,"stars":0},"bfcl-v3":{"n":129,"recent":14,"stars":5},"bfcl-v3-ja":{"n":12,"recent":1,"stars":1},"bfcl-v3-live":{"n":19,"recent":2,"stars":1},"bfcl-v3-multi-turn":{"n":37,"recent":5,"stars":3},"bfcl-v4":{"n":161,"recent":62,"stars":5},"bfcl-v4-multi-turn":{"n":3,"recent":1,"stars":0},"bharatmath":{"n":4,"recent":1,"stars":0},"big-bench":{"n":2,"recent":0,"stars":0},"big-bench-audio":{"n":70,"recent":20,"stars":4},"big-bench-extra-hard":{"n":47,"recent":9,"stars":3},"big-finance-bench":{"n":5,"recent":4,"stars":1},"bigcodebench":{"n":233,"recent":8,"stars":4},"bigcodebench-hard":{"n":212,"recent":0,"stars":3},"biobench":{"n":5,"recent":0,"stars":0},"biology-instruction":{"n":23,"recent":7,"stars":2},"biolp-bench":{"n":3,"recent":0,"stars":0},"biomysterybench":{"n":30,"recent":23,"stars":4},"biomysterybench-hard":{"n":21,"recent":16,"stars":3},"bioreason-coding":{"n":7,"recent":7,"stars":1},"bioreason-non-snv":{"n":7,"recent":7,"stars":1},"bird-sql":{"n":34,"recent":4,"stars":3},"bixbench":{"n":2,"recent":0,"stars":0},"blend":{"n":12,"recent":0,"stars":1},"blink":{"n":169,"recent":26,"stars":5},"blueprint-bench-2":{"n":8,"recent":3,"stars":1},"bob-hvr":{"n":14,"recent":0,"stars":1},"bold":{"n":2,"recent":0,"stars":0},"boolq":{"n":154,"recent":13,"stars":5},"borda-count-multilingual":{"n":8,"recent":0,"stars":0},"bpomp-decision":{"n":38,"recent":37,"stars":4},"bridgebench":{"n":4,"recent":0,"stars":0},"bright-decision":{"n":38,"recent":37,"stars":4},"brokenarxiv":{"n":7,"recent":7,"stars":1},"browsecomp":{"n":212,"recent":81,"stars":5},"browsecomp-agent-swarm":{"n":2,"recent":0,"stars":0},"browsecomp-plus":{"n":34,"recent":15,"stars":4},"browsecomp-vl":{"n":11,"recent":1,"stars":1},"browsecomp-with-content-manager":{"n":35,"recent":8,"stars":3},"browsecomp-zh":{"n":101,"recent":21,"stars":5},"browsecomp-zh-with-content-manager":{"n":1,"recent":0,"stars":0},"brumo25":{"n":28,"recent":2,"stars":1},"business-arena":{"n":10,"recent":9,"stars":2},"buzzbench":{"n":28,"recent":0,"stars":1},"c-eval":{"n":330,"recent":10,"stars":5},"c3":{"n":60,"recent":0,"stars":2},"c3-bench":{"n":3,"recent":0,"stars":0},"caselaw":{"n":1,"recent":0,"stars":0},"caselaw-v2":{"n":78,"recent":2,"stars":2},"casereportbench":{"n":8,"recent":1,"stars":0},"cc-bench-v2-backend":{"n":4,"recent":0,"stars":0},"cc-bench-v2-frontend":{"n":4,"recent":0,"stars":0},"cc-bench-v2-repo-exploration":{"n":4,"recent":0,"stars":0},"cc-ocr":{"n":43,"recent":2,"stars":2},"cc-ocr-kie":{"n":9,"recent":3,"stars":1},"cc-ocr-multilingual":{"n":3,"recent":0,"stars":0},"ccbench":{"n":11,"recent":0,"stars":1},"ccpm":{"n":13,"recent":0,"stars":1},"cfcolor-decision":{"n":38,"recent":37,"stars":4},"cfeval":{"n":5,"recent":0,"stars":0},"cgbench":{"n":12,"recent":1,"stars":1},"charades-sta":{"n":25,"recent":1,"stars":1},"chartbench":{"n":3,"recent":0,"stars":0},"chartmuseum":{"n":50,"recent":3,"stars":3},"chartography":{"n":11,"recent":10,"stars":3},"chartography-with-tools":{"n":16,"recent":16,"stars":3},"chartqa":{"n":223,"recent":5,"stars":4},"chartqa-pro":{"n":46,"recent":12,"stars":4},"chartqa-pro-with-tools":{"n":2,"recent":1,"stars":0},"charxiv-dq":{"n":171,"recent":5,"stars":4},"charxiv-rq":{"n":274,"recent":49,"stars":5},"charxiv-rq-with-tools":{"n":33,"recent":23,"stars":4},"chessbench-decision":{"n":38,"recent":37,"stars":4},"chexpert":{"n":4,"recent":0,"stars":0},"chid":{"n":28,"recent":0,"stars":1},"chinese-simpleqa":{"n":28,"recent":4,"stars":2},"cibench":{"n":13,"recent":0,"stars":1},"circa":{"n":2,"recent":2,"stars":0},"civil-comments":{"n":4,"recent":4,"stars":1},"cl-bench":{"n":36,"recent":11,"stars":4},"cl-bench-life":{"n":15,"recent":5,"stars":2},"cladder":{"n":38,"recent":37,"stars":4},"claw-eval":{"n":59,"recent":28,"stars":4},"claw-eval-multimodal":{"n":6,"recent":1,"stars":0},"claw-gym":{"n":5,"recent":2,"stars":0},"claweval-pass-at-3":{"n":7,"recent":0,"stars":0},"claweval-pass3":{"n":70,"recent":31,"stars":4},"click":{"n":23,"recent":5,"stars":2},"clinc150-oos":{"n":36,"recent":35,"stars":4},"cloc-count":{"n":5,"recent":3,"stars":1},"clockbench":{"n":1,"recent":0,"stars":0},"cloningscenarios":{"n":2,"recent":0,"stars":0},"cluewsc":{"n":49,"recent":0,"stars":2},"cmath":{"n":93,"recent":2,"stars":2},"cmmlu":{"n":281,"recent":9,"stars":4},"cmmmu":{"n":9,"recent":0,"stars":0},"cmrc2018":{"n":16,"recent":0,"stars":1},"cmt-benchmark":{"n":17,"recent":11,"stars":3},"cnmo-2024":{"n":18,"recent":0,"stars":1},"coco-caption":{"n":3,"recent":0,"stars":0},"coco-det-f1":{"n":7,"recent":3,"stars":1},"coco-pointing":{"n":5,"recent":3,"stars":1},"codeforces":{"n":78,"recent":9,"stars":3},"codeforces-percentile":{"n":27,"recent":0,"stars":1},"codeif-bench":{"n":5,"recent":0,"stars":0},"collegemath":{"n":24,"recent":0,"stars":1},"collie":{"n":24,"recent":1,"stars":1},"collie-hard":{"n":5,"recent":0,"stars":0},"commerceagentbench":{"n":10,"recent":9,"stars":2},"commonsenseqa":{"n":114,"recent":9,"stars":4},"complex-workflow":{"n":5,"recent":0,"stars":0},"complexfuncbench":{"n":9,"recent":0,"stars":0},"complexfuncbench-audio":{"n":9,"recent":0,"stars":0},"cona":{"n":1,"recent":0,"stars":0},"contphy":{"n":10,"recent":4,"stars":2},"contract-scrub":{"n":5,"recent":2,"stars":0},"contractnli":{"n":39,"recent":38,"stars":4},"convfinqa":{"n":10,"recent":0,"stars":1},"copa":{"n":41,"recent":0,"stars":2},"coqa":{"n":10,"recent":0,"stars":1},"core":{"n":2,"recent":0,"stars":0},"corpfin":{"n":7,"recent":5,"stars":1},"corpusqa":{"n":19,"recent":0,"stars":1},"cosmos-reason-bench":{"n":13,"recent":7,"stars":2},"countbench":{"n":96,"recent":4,"stars":3},"countbenchqa":{"n":50,"recent":3,"stars":3},"countdown":{"n":5,"recent":0,"stars":0},"countix":{"n":4,"recent":0,"stars":0},"countqa":{"n":41,"recent":15,"stars":4},"covost":{"n":2,"recent":0,"stars":0},"crag":{"n":4,"recent":0,"stars":0},"creative-story-writing-v3":{"n":18,"recent":0,"stars":1},"creative-writing-longform":{"n":145,"recent":26,"stars":5},"creative-writing-v3":{"n":190,"recent":34,"stars":5},"critpt":{"n":95,"recent":40,"stars":4},"crosstabbench-relation-f1":{"n":6,"recent":5,"stars":1},"crosstabbench-teds":{"n":6,"recent":5,"stars":1},"crossvid":{"n":10,"recent":4,"stars":2},"crpe":{"n":18,"recent":0,"stars":1},"crux-i":{"n":132,"recent":0,"stars":3},"crux-o":{"n":166,"recent":3,"stars":4},"cruxeval":{"n":56,"recent":3,"stars":3},"cruxeval-decision":{"n":38,"recent":37,"stars":4},"csatqa":{"n":1,"recent":0,"stars":0},"csimpleqa":{"n":36,"recent":4,"stars":3},"cultcat":{"n":5,"recent":1,"stars":0},"cultural-bench":{"n":1,"recent":0,"stars":0},"cursorbench-3.0":{"n":10,"recent":0,"stars":1},"cursorbench-3.2":{"n":6,"recent":6,"stars":1},"cursorbench-4.0":{"n":9,"recent":9,"stars":1},"customer-support-qa":{"n":5,"recent":0,"stars":0},"cute":{"n":5,"recent":0,"stars":0},"cv-bench":{"n":72,"recent":13,"stars":4},"cvtg-2k-clipscore":{"n":9,"recent":0,"stars":0},"cvtg-2k-ned":{"n":9,"recent":0,"stars":0},"cvtg-2k-word-accuracy":{"n":9,"recent":0,"stars":0},"cwe-bench":{"n":11,"recent":11,"stars":3},"cxr14":{"n":4,"recent":0,"stars":0},"cybench":{"n":24,"recent":0,"stars":1},"cyberattack-assistance":{"n":1,"recent":0,"stars":0},"cybergym":{"n":47,"recent":33,"stars":4},"cybersecurity-capture-the-flag-challenges":{"n":8,"recent":3,"stars":1},"cybersecurity-ctf":{"n":3,"recent":0,"stars":0},"d4la":{"n":5,"recent":1,"stars":0},"da-2k":{"n":13,"recent":1,"stars":1},"daily-omni":{"n":6,"recent":1,"stars":0},"deep-planning":{"n":27,"recent":1,"stars":1},"deepcodebench":{"n":4,"recent":4,"stars":1},"deepconsult":{"n":5,"recent":0,"stars":0},"deepform":{"n":1,"recent":0,"stars":0},"deepmind-math":{"n":18,"recent":3,"stars":2},"deepresearch-bench-ii":{"n":14,"recent":10,"stars":3},"deepresearchbench":{"n":16,"recent":0,"stars":1},"deepsearchqa":{"n":75,"recent":36,"stars":4},"deepsearchqa-f1":{"n":22,"recent":6,"stars":2},"deepshop":{"n":5,"recent":0,"stars":0},"deepswe":{"n":41,"recent":31,"stars":4},"deepswe-v1.0":{"n":26,"recent":12,"stars":3},"deepswe-v1.1":{"n":80,"recent":67,"stars":4},"defects4j":{"n":10,"recent":0,"stars":1},"dense200-det-f1":{"n":7,"recent":3,"stars":1},"dense200-pointing":{"n":5,"recent":3,"stars":1},"der2-bench":{"n":9,"recent":0,"stars":0},"design2code":{"n":14,"recent":0,"stars":1},"designarena":{"n":199,"recent":57,"stars":5},"detailbench":{"n":6,"recent":0,"stars":0},"dialogue-safety":{"n":1,"recent":0,"stars":0},"dices350":{"n":1,"recent":0,"stars":0},"discox":{"n":12,"recent":0,"stars":1},"do-anything-now":{"n":5,"recent":0,"stars":0},"do-not-answer":{"n":12,"recent":0,"stars":1},"doc2dial":{"n":10,"recent":0,"stars":1},"docfigcapbench-caption":{"n":5,"recent":4,"stars":1},"docfigcapbench-loc-f1":{"n":7,"recent":6,"stars":1},"doclaynet":{"n":5,"recent":1,"stars":0},"docmath":{"n":48,"recent":2,"stars":2},"docmatix":{"n":8,"recent":0,"stars":0},"docvqa":{"n":245,"recent":9,"stars":4},"dolphin-page":{"n":2,"recent":0,"stars":0},"doqa":{"n":10,"recent":0,"stars":1},"dpg-bench":{"n":14,"recent":0,"stars":1},"draco":{"n":20,"recent":15,"stars":3},"dream-1k":{"n":5,"recent":5,"stars":1},"drop":{"n":151,"recent":10,"stars":5},"ds-1000":{"n":8,"recent":0,"stars":0},"dsbench-fullstack":{"n":8,"recent":6,"stars":1},"dsbench-hard":{"n":9,"recent":7,"stars":1},"dude":{"n":11,"recent":2,"stars":1},"dynamath":{"n":68,"recent":4,"stars":3},"eclektic":{"n":1,"recent":0,"stars":0},"economically-important-tasks":{"n":2,"recent":0,"stars":0},"edubench-english":{"n":5,"recent":1,"stars":0},"edubench-history":{"n":5,"recent":1,"stars":0},"edubench-literature":{"n":5,"recent":1,"stars":0},"edubench-math":{"n":5,"recent":1,"stars":0},"edubench-math-university":{"n":5,"recent":1,"stars":0},"edubench-russian":{"n":5,"recent":1,"stars":0},"education-bench":{"n":5,"recent":0,"stars":0},"eebench":{"n":26,"recent":22,"stars":3},"ege":{"n":5,"recent":1,"stars":0},"ego3d-bench":{"n":9,"recent":2,"stars":0},"egoplan-bench2":{"n":13,"recent":7,"stars":2},"egoschema":{"n":70,"recent":3,"stars":3},"egotempo":{"n":9,"recent":1,"stars":0},"ehrnoteqa":{"n":4,"recent":0,"stars":0},"eifbench":{"n":5,"recent":0,"stars":0},"emb-v1.1":{"n":1,"recent":1,"stars":0},"embspatialbench":{"n":71,"recent":13,"stars":4},"emma":{"n":11,"recent":2,"stars":1},"enamel":{"n":10,"recent":0,"stars":1},"enconda-bench":{"n":4,"recent":0,"stars":0},"encyclo-k":{"n":9,"recent":0,"stars":0},"enigmaval":{"n":15,"recent":0,"stars":1},"enterprise-rag":{"n":5,"recent":0,"stars":0},"enterpriseops-gym":{"n":6,"recent":3,"stars":1},"eqbench":{"n":186,"recent":1,"stars":3},"eqbench-3":{"n":83,"recent":4,"stars":3},"erqa":{"n":114,"recent":27,"stars":5},"erqa-plus":{"n":13,"recent":7,"stars":2},"et-bench":{"n":3,"recent":3,"stars":1},"evalperf":{"n":34,"recent":0,"stars":2},"evalplus":{"n":173,"recent":2,"stars":3},"evg":{"n":2,"recent":0,"stars":0},"execute":{"n":5,"recent":0,"stars":0},"expertfactsqa-law":{"n":5,"recent":1,"stars":0},"expertfactsqa-medicine":{"n":5,"recent":1,"stars":0},"exploitbench":{"n":19,"recent":17,"stars":3},"exploitbench-2026-jun-aug":{"n":2,"recent":2,"stars":0},"exploitgym":{"n":17,"recent":16,"stars":3},"exploitgym-honeypot":{"n":2,"recent":2,"stars":0},"facts-benchmark-suite":{"n":14,"recent":0,"stars":1},"facts-grounding":{"n":81,"recent":15,"stars":4},"facts-parametric":{"n":3,"recent":0,"stars":0},"factscore":{"n":11,"recent":0,"stars":1},"fairpoliticsqa":{"n":2,"recent":1,"stars":0},"faitheval-inconsistent":{"n":3,"recent":2,"stars":0},"faithjudge-1-hallu":{"n":8,"recent":0,"stars":0},"faix-agent":{"n":76,"recent":0,"stars":2},"faix-code":{"n":163,"recent":0,"stars":3},"faix-math":{"n":175,"recent":0,"stars":3},"faix-ocr":{"n":82,"recent":0,"stars":2},"faix-overall":{"n":303,"recent":35,"stars":5},"faix-safety":{"n":53,"recent":0,"stars":2},"faix-stem":{"n":226,"recent":0,"stars":3},"faix-text":{"n":197,"recent":0,"stars":3},"faix-visual":{"n":103,"recent":0,"stars":3},"faix-writing":{"n":22,"recent":0,"stars":1},"fate-h":{"n":4,"recent":1,"stars":0},"fate-x":{"n":4,"recent":1,"stars":0},"fd-bench-v1-latency":{"n":13,"recent":8,"stars":2},"fd-bench-v1.5":{"n":10,"recent":6,"stars":2},"fd-bench-v3":{"n":10,"recent":6,"stars":2},"fd-bench-v3-pass1":{"n":13,"recent":7,"stars":2},"featbench":{"n":4,"recent":4,"stars":1},"fetaqa":{"n":6,"recent":0,"stars":0},"few-shot-attack":{"n":1,"recent":0,"stars":0},"figqa":{"n":5,"recent":2,"stars":0},"finance-reasoning":{"n":5,"recent":0,"stars":0},"financeagent":{"n":10,"recent":0,"stars":1},"financeagent-v1.1":{"n":30,"recent":12,"stars":4},"financeagent-v2":{"n":32,"recent":27,"stars":4},"financebench-fulldoc":{"n":4,"recent":0,"stars":0},"financialphrasebank":{"n":2,"recent":2,"stars":0},"finentity-decision":{"n":38,"recent":37,"stars":4},"finqa-128k":{"n":5,"recent":1,"stars":0},"finsearchcomp":{"n":32,"recent":1,"stars":2},"finsearchcomp-cn":{"n":12,"recent":0,"stars":1},"finsearchcomp-t2t3":{"n":5,"recent":0,"stars":0},"flame-react-eval":{"n":10,"recent":0,"stars":1},"fleurs":{"n":2,"recent":0,"stars":0},"flickr30k":{"n":9,"recent":0,"stars":0},"flores":{"n":17,"recent":0,"stars":1},"flteval":{"n":5,"recent":1,"stars":0},"forecastbench-decision":{"n":7,"recent":6,"stars":1},"forte":{"n":6,"recent":2,"stars":0},"fortress-adversarial":{"n":17,"recent":9,"stars":2},"fortress-benign":{"n":17,"recent":9,"stars":2},"fox-page-cn":{"n":2,"recent":0,"stars":0},"fox-page-en":{"n":2,"recent":0,"stars":0},"fr-bench-pdf2md":{"n":9,"recent":6,"stars":1},"frames":{"n":55,"recent":2,"stars":2},"freshqa":{"n":5,"recent":0,"stars":0},"frontier-cs":{"n":12,"recent":6,"stars":2},"frontierbench":{"n":13,"recent":11,"stars":3},"frontiercode":{"n":4,"recent":4,"stars":1},"frontiercode-diamond":{"n":3,"recent":2,"stars":0},"frontiercode-extended":{"n":46,"recent":39,"stars":4},"frontiercode-main":{"n":46,"recent":39,"stars":4},"frontierfinance":{"n":18,"recent":17,"stars":3},"frontiermath":{"n":3,"recent":1,"stars":0},"frontierscience":{"n":10,"recent":1,"stars":1},"frontierscience-olympiad":{"n":49,"recent":17,"stars":4},"frontierscience-research":{"n":55,"recent":19,"stars":4},"frontierswe":{"n":19,"recent":15,"stars":3},"frontiervep":{"n":7,"recent":7,"stars":1},"frontierxrd":{"n":1,"recent":1,"stars":0},"fsc-147":{"n":13,"recent":5,"stars":2},"fullstackbench":{"n":56,"recent":3,"stars":3},"fullstackbench-zh":{"n":6,"recent":0,"stars":0},"futureomni":{"n":6,"recent":0,"stars":0},"gaia":{"n":93,"recent":16,"stars":4},"gaia-no-file":{"n":7,"recent":0,"stars":0},"gaia-text-only":{"n":66,"recent":15,"stars":4},"gaia2":{"n":17,"recent":1,"stars":1},"gandalf-ignore":{"n":1,"recent":0,"stars":0},"gaokao-2023-en":{"n":24,"recent":0,"stars":1},"gaokao-bench":{"n":93,"recent":0,"stars":2},"gaokao-math-2026":{"n":6,"recent":3,"stars":1},"gaokao-mathcloze":{"n":4,"recent":0,"stars":0},"gaokao-mathqa":{"n":4,"recent":0,"stars":0},"gdp-pdf":{"n":33,"recent":29,"stars":4},"gdpval":{"n":57,"recent":18,"stars":4},"gdpval-aa-elo":{"n":44,"recent":18,"stars":4},"gdpval-aa-v2-elo":{"n":100,"recent":76,"stars":5},"gdpval-rubrics":{"n":26,"recent":11,"stars":3},"genebench":{"n":4,"recent":0,"stars":0},"genebench-pro":{"n":8,"recent":6,"stars":1},"general-tool-use":{"n":18,"recent":0,"stars":1},"genomeqa":{"n":7,"recent":7,"stars":1},"geobench":{"n":1,"recent":0,"stars":0},"geobench1":{"n":5,"recent":0,"stars":0},"global-mgsm":{"n":4,"recent":0,"stars":0},"global-mmlu":{"n":46,"recent":12,"stars":4},"global-mmlu-lite":{"n":49,"recent":12,"stars":4},"global-piqa":{"n":55,"recent":2,"stars":2},"glue":{"n":76,"recent":0,"stars":2},"gmai-mmbench":{"n":1,"recent":0,"stars":0},"gorilla-api-bench":{"n":5,"recent":0,"stars":0},"gpqa":{"n":323,"recent":23,"stars":5},"gpqa-diamond":{"n":631,"recent":175,"stars":5},"gpqa-main":{"n":1,"recent":0,"stars":0},"gqa":{"n":4,"recent":0,"stars":0},"graphwalks-128k":{"n":1,"recent":0,"stars":0},"graphwalks-bfs":{"n":18,"recent":4,"stars":2},"graphwalks-bfs-1m":{"n":15,"recent":8,"stars":2},"graphwalks-bfs-256k":{"n":17,"recent":9,"stars":2},"graphwalks-bfs-256k-1m":{"n":7,"recent":4,"stars":1},"graphwalks-parents":{"n":13,"recent":0,"stars":1},"graphwalks-parents-1m":{"n":5,"recent":1,"stars":0},"graphwalks-parents-256k":{"n":8,"recent":3,"stars":1},"graphwalks-parents-256k-1m":{"n":1,"recent":0,"stars":0},"gre-math-maj16":{"n":6,"recent":0,"stars":0},"ground-ui-1k":{"n":22,"recent":0,"stars":1},"gsm-infinite-hard-128k":{"n":4,"recent":0,"stars":0},"gsm-infinite-hard-16k":{"n":4,"recent":0,"stars":0},"gsm-infinite-hard-32k":{"n":4,"recent":0,"stars":0},"gsm-infinite-hard-64k":{"n":4,"recent":0,"stars":0},"gsm-plus":{"n":47,"recent":10,"stars":4},"gsm-symbolic":{"n":7,"recent":3,"stars":1},"gsm8k":{"n":705,"recent":38,"stars":5},"gsm8k-de":{"n":2,"recent":0,"stars":0},"gsm8k-decision":{"n":38,"recent":37,"stars":4},"gsm8k-ja":{"n":13,"recent":1,"stars":1},"gsm8k-ko":{"n":6,"recent":0,"stars":0},"gsm8k-platinum":{"n":3,"recent":0,"stars":0},"gso-benchmark":{"n":31,"recent":6,"stars":3},"habermas-machine-decision":{"n":38,"recent":37,"stars":4},"hae-rae-bench":{"n":21,"recent":2,"stars":1},"hallusionbench":{"n":163,"recent":8,"stars":4},"harbor-index":{"n":10,"recent":10,"stars":3},"hardmultiqa":{"n":5,"recent":1,"stars":0},"harmbench":{"n":12,"recent":3,"stars":2},"harmfulq":{"n":3,"recent":0,"stars":0},"harvey-lab-aa":{"n":20,"recent":16,"stars":3},"healthbench":{"n":45,"recent":7,"stars":3},"healthbench-hard":{"n":24,"recent":0,"stars":1},"healthbench-hard-hallucinations":{"n":3,"recent":0,"stars":0},"healthbench-professional":{"n":28,"recent":24,"stars":3},"hellaswag":{"n":415,"recent":53,"stars":5},"hellaswag-de":{"n":2,"recent":0,"stars":0},"hellaswag-multilingual":{"n":1,"recent":0,"stars":0},"helmet-longqa":{"n":4,"recent":0,"stars":0},"helpsteer2":{"n":3,"recent":3,"stars":1},"herobench":{"n":24,"recent":0,"stars":1},"hhem-v2.1":{"n":21,"recent":0,"stars":1},"hiddenmath":{"n":11,"recent":0,"stars":1},"hiertext-f1":{"n":6,"recent":3,"stars":1},"hipho":{"n":26,"recent":13,"stars":3},"hitab":{"n":6,"recent":0,"stars":0},"hlab-vals-1.1":{"n":1,"recent":1,"stars":0},"hle":{"n":258,"recent":64,"stars":5},"hle-diamond":{"n":6,"recent":6,"stars":1},"hle-multichoice":{"n":58,"recent":57,"stars":4},"hle-overconfidence":{"n":15,"recent":0,"stars":1},"hle-text-only":{"n":206,"recent":69,"stars":5},"hle-verified":{"n":17,"recent":9,"stars":2},"hle-vl":{"n":3,"recent":0,"stars":0},"hle-with-tools":{"n":153,"recent":72,"stars":5},"hmmt":{"n":2,"recent":0,"stars":0},"hmmt-2025":{"n":103,"recent":0,"stars":3},"hmmt-feb-2025":{"n":96,"recent":12,"stars":4},"hmmt-feb-2026":{"n":120,"recent":55,"stars":5},"hmmt-nov-2025":{"n":81,"recent":5,"stars":3},"home-appliance-simulator-decision":{"n":38,"recent":37,"stars":4},"hotpotqa":{"n":7,"recent":0,"stars":0},"hover":{"n":38,"recent":37,"stars":4},"hrbench4k":{"n":35,"recent":2,"stars":2},"hrbench8k":{"n":32,"recent":1,"stars":2},"hrm8k":{"n":11,"recent":2,"stars":1},"hss":{"n":5,"recent":5,"stars":1},"humaneval":{"n":627,"recent":28,"stars":5},"humaneval-fim":{"n":3,"recent":0,"stars":0},"humaneval-plus":{"n":439,"recent":25,"stars":5},"humaneval-v":{"n":5,"recent":0,"stars":0},"humaneval-x":{"n":58,"recent":0,"stars":2},"humanref":{"n":6,"recent":3,"stars":1},"humicroedit-decision":{"n":38,"recent":37,"stars":4},"hungarian-math-exam":{"n":12,"recent":0,"stars":1},"hybridial":{"n":10,"recent":0,"stars":1},"hypersim":{"n":22,"recent":0,"stars":1},"icdar2015-f1":{"n":6,"recent":3,"stars":1},"ifbench":{"n":372,"recent":107,"stars":5},"ifeval":{"n":482,"recent":78,"stars":5},"ifeval-code":{"n":6,"recent":0,"stars":0},"ifeval-strict-prompt":{"n":53,"recent":1,"stars":2},"ifstruct":{"n":5,"recent":1,"stars":0},"imagemining":{"n":2,"recent":0,"stars":0},"img-qa-avg":{"n":22,"recent":0,"stars":1},"imo-2025":{"n":4,"recent":1,"stars":0},"imo-answerbench":{"n":150,"recent":33,"stars":5},"implicitmembench":{"n":2,"recent":2,"stars":0},"impossible-exploitgym":{"n":1,"recent":1,"stars":0},"include":{"n":67,"recent":5,"stars":3},"include-v2":{"n":1,"recent":0,"stars":0},"indicifeval-ground":{"n":5,"recent":1,"stars":0},"indicifeval-trans":{"n":5,"recent":1,"stars":0},"indicmmlu-pro":{"n":3,"recent":1,"stars":0},"indicsafe5":{"n":4,"recent":1,"stars":0},"indommlu":{"n":12,"recent":0,"stars":1},"infoqa":{"n":49,"recent":0,"stars":2},"information-extraction":{"n":5,"recent":0,"stars":0},"information-processing":{"n":5,"recent":0,"stars":0},"infotabs":{"n":6,"recent":0,"stars":0},"infovqa":{"n":166,"recent":7,"stars":4},"inscit":{"n":10,"recent":0,"stars":1},"intention-recognition":{"n":5,"recent":0,"stars":0},"intphys-2":{"n":18,"recent":3,"stars":2},"inverse-ifeval":{"n":12,"recent":0,"stars":1},"ioi":{"n":1,"recent":0,"stars":0},"ioi-2025":{"n":8,"recent":2,"stars":0},"ipho-2025-theory":{"n":3,"recent":0,"stars":0},"isarcasmeval":{"n":35,"recent":35,"stars":4},"isl-osl-8k-16k":{"n":3,"recent":0,"stars":0},"jamc-qa":{"n":31,"recent":0,"stars":2},"jculture":{"n":10,"recent":1,"stars":1},"jec-qa":{"n":16,"recent":0,"stars":1},"jevbench":{"n":25,"recent":25,"stars":3},"jevbench-public":{"n":7,"recent":7,"stars":1},"jevbench-public-easy":{"n":10,"recent":9,"stars":2},"jevbench-public-hard":{"n":11,"recent":10,"stars":3},"jevbench-public-original":{"n":10,"recent":9,"stars":2},"jfbench":{"n":10,"recent":1,"stars":1},"jgpqa":{"n":41,"recent":1,"stars":2},"jhumaneval":{"n":31,"recent":0,"stars":2},"jhumaneval-plus":{"n":10,"recent":1,"stars":1},"jmmlu":{"n":25,"recent":1,"stars":1},"jobbench":{"n":47,"recent":39,"stars":4},"jobbench-easy":{"n":13,"recent":8,"stars":2},"judgebench":{"n":2,"recent":2,"stars":0},"judgemark-v2-1":{"n":49,"recent":0,"stars":2},"kernelbench-hard":{"n":5,"recent":1,"stars":0},"kernelgen-1p":{"n":4,"recent":3,"stars":1},"kgc-safety":{"n":9,"recent":1,"stars":0},"kimi-claw-24-7-bench":{"n":4,"recent":2,"stars":0},"kimi-code-bench-v2":{"n":8,"recent":6,"stars":1},"kimi-code-bench-v3-long-horizon":{"n":7,"recent":7,"stars":1},"kimi-hallu-bench":{"n":6,"recent":6,"stars":1},"kimi-hallu-bench-hard-with-tools":{"n":7,"recent":7,"stars":1},"kina":{"n":5,"recent":2,"stars":0},"kk-4-people":{"n":5,"recent":0,"stars":0},"kk-8-people":{"n":5,"recent":0,"stars":0},"kmmlu":{"n":29,"recent":2,"stars":1},"kmmlu-pro":{"n":84,"recent":6,"stars":3},"kmmlu-redux":{"n":53,"recent":0,"stars":2},"ko-longbench":{"n":9,"recent":1,"stars":0},"kobest":{"n":1,"recent":0,"stars":0},"kobolt":{"n":26,"recent":2,"stars":1},"komt-bench":{"n":9,"recent":2,"stars":0},"konet":{"n":6,"recent":0,"stars":0},"kor-bench":{"n":26,"recent":3,"stars":2},"korbench":{"n":9,"recent":0,"stars":0},"kosimpleqa":{"n":13,"recent":4,"stars":2},"ksm":{"n":5,"recent":0,"stars":0},"kubricount-testb":{"n":5,"recent":3,"stars":1},"l-eval":{"n":21,"recent":0,"stars":1},"labbench2":{"n":11,"recent":11,"stars":3},"lambada":{"n":60,"recent":3,"stars":3},"latent-jailbreak":{"n":4,"recent":0,"stars":0},"lbv1-qa":{"n":11,"recent":0,"stars":1},"lbv2":{"n":11,"recent":0,"stars":1},"leetcode-contest":{"n":15,"recent":0,"stars":1},"legal-agent-benchmark":{"n":5,"recent":3,"stars":1},"legal-agent-benchmark-aa":{"n":5,"recent":5,"stars":1},"legal-agent-benchmark-held-out":{"n":19,"recent":16,"stars":3},"legal-research-bench":{"n":7,"recent":6,"stars":1},"legalbench":{"n":6,"recent":2,"stars":0},"lexam":{"n":3,"recent":1,"stars":0},"lexam-hard":{"n":5,"recent":3,"stars":1},"lexam-mcq4-en":{"n":5,"recent":2,"stars":0},"lifebench":{"n":21,"recent":6,"stars":2},"lifescibench":{"n":6,"recent":5,"stars":1},"lingoqa":{"n":38,"recent":8,"stars":3},"livebench":{"n":164,"recent":0,"stars":3},"livebrowsecomp":{"n":10,"recent":6,"stars":2},"liveclaw":{"n":4,"recent":2,"stars":0},"livecodebench":{"n":663,"recent":91,"stars":5},"livecodebench-ko":{"n":4,"recent":0,"stars":0},"livecodebench-pro":{"n":46,"recent":0,"stars":2},"livecodebench-pro-25q2-easy":{"n":39,"recent":5,"stars":3},"livecodebench-pro-25q2-med":{"n":39,"recent":4,"stars":3},"livecodebench-v3":{"n":45,"recent":0,"stars":2},"livecodebench-v5":{"n":147,"recent":3,"stars":4},"livemathematicianbench":{"n":5,"recent":2,"stars":0},"livemcp-101":{"n":18,"recent":0,"stars":1},"livesports-3k":{"n":13,"recent":4,"stars":2},"livesqlbench":{"n":5,"recent":1,"stars":0},"llava-bench-in-the-wild":{"n":38,"recent":0,"stars":2},"lmarena-text":{"n":429,"recent":62,"stars":5},"lmarena-vision":{"n":165,"recent":42,"stars":5},"loca-bench":{"n":2,"recent":1,"stars":0},"local-agent-bench":{"n":21,"recent":0,"stars":1},"locomo":{"n":2,"recent":2,"stars":0},"logicvista":{"n":65,"recent":8,"stars":3},"logiqa":{"n":8,"recent":0,"stars":0},"longbench":{"n":37,"recent":5,"stars":3},"longbench-v2":{"n":136,"recent":27,"stars":5},"longcodebench":{"n":7,"recent":0,"stars":0},"longfact-concepts":{"n":11,"recent":0,"stars":1},"longfact-objects":{"n":11,"recent":0,"stars":1},"longmemeval":{"n":11,"recent":3,"stars":2},"longtext-bench-en":{"n":9,"recent":0,"stars":0},"longtext-bench-zh":{"n":9,"recent":0,"stars":0},"longvideobench":{"n":87,"recent":14,"stars":4},"lpfqa":{"n":12,"recent":0,"stars":1},"lvbench":{"n":101,"recent":23,"stars":5},"lvis-det-f1":{"n":7,"recent":3,"stars":1},"lvis-pointing":{"n":5,"recent":3,"stars":1},"m-ifeval-ja":{"n":15,"recent":1,"stars":1},"m3gia-cn":{"n":4,"recent":0,"stars":0},"machiavelli":{"n":15,"recent":0,"stars":1},"makemesay":{"n":2,"recent":0,"stars":0},"mantis":{"n":42,"recent":0,"stars":2},"marena-hard":{"n":4,"recent":0,"stars":0},"mars-bench":{"n":12,"recent":0,"stars":1},"mask":{"n":79,"recent":0,"stars":2},"massive-intent":{"n":4,"recent":4,"stars":1},"matbench":{"n":5,"recent":0,"stars":0},"math":{"n":526,"recent":16,"stars":5},"math-100-ja":{"n":31,"recent":0,"stars":2},"math-ko":{"n":4,"recent":0,"stars":0},"math-lvl5":{"n":51,"recent":0,"stars":2},"math500":{"n":266,"recent":31,"stars":5},"math500-es":{"n":5,"recent":0,"stars":0},"math500-ja":{"n":10,"recent":1,"stars":1},"matharena-apex":{"n":51,"recent":23,"stars":4},"matharena-apex-shortlist":{"n":27,"recent":10,"stars":3},"mathbench-a":{"n":14,"recent":0,"stars":1},"mathbench-zh":{"n":11,"recent":0,"stars":1},"matholympiadbench":{"n":10,"recent":0,"stars":1},"mathqa":{"n":1,"recent":0,"stars":0},"mathverse":{"n":19,"recent":1,"stars":1},"mathverse-mini":{"n":69,"recent":5,"stars":3},"mathverse-vision":{"n":21,"recent":2,"stars":1},"mathvision":{"n":246,"recent":30,"stars":5},"mathvision-with-tools":{"n":12,"recent":4,"stars":2},"mathvista":{"n":111,"recent":9,"stars":4},"mathvista-mini":{"n":212,"recent":4,"stars":4},"mattools":{"n":10,"recent":3,"stars":2},"maverix":{"n":2,"recent":0,"stars":0},"maxife":{"n":29,"recent":2,"stars":1},"mbe-bar-exam":{"n":5,"recent":2,"stars":0},"mbpp":{"n":522,"recent":20,"stars":5},"mbpp-ko":{"n":9,"recent":2,"stars":0},"mbpp-plus":{"n":379,"recent":24,"stars":5},"mcp-atlas":{"n":130,"recent":65,"stars":5},"mcp-universe":{"n":39,"recent":0,"stars":2},"mcpmark":{"n":93,"recent":22,"stars":4},"mcpmark-verified":{"n":8,"recent":5,"stars":1},"mdolly":{"n":4,"recent":0,"stars":0},"mdpbench":{"n":9,"recent":7,"stars":1},"measurebench":{"n":5,"recent":2,"stars":0},"medbullets-op4":{"n":7,"recent":0,"stars":0},"medbullets-op5":{"n":7,"recent":0,"stars":0},"medchembench-internal":{"n":5,"recent":4,"stars":1},"medmcqa":{"n":27,"recent":0,"stars":1},"medqa":{"n":40,"recent":1,"stars":2},"medqa-mcmle":{"n":16,"recent":0,"stars":1},"medxpertqa-mm":{"n":58,"recent":8,"stars":3},"medxpertqa-text":{"n":17,"recent":1,"stars":1},"meeseeks-zh":{"n":1,"recent":0,"stars":0},"membench":{"n":2,"recent":2,"stars":0},"memoryagentbench":{"n":2,"recent":2,"stars":0},"memorybench":{"n":5,"recent":5,"stars":1},"metr":{"n":33,"recent":0,"stars":2},"mewc":{"n":6,"recent":0,"stars":0},"mgsm":{"n":154,"recent":7,"stars":4},"mhpp":{"n":10,"recent":0,"stars":1},"miabench":{"n":23,"recent":0,"stars":1},"microvqa":{"n":18,"recent":5,"stars":2},"milu":{"n":5,"recent":1,"stars":0},"mimic-cxr":{"n":4,"recent":0,"stars":0},"mimo-niah-multi-128k":{"n":4,"recent":0,"stars":0},"mimo-niah-multi-256k":{"n":1,"recent":0,"stars":0},"mimo-niah-multi-32k":{"n":4,"recent":0,"stars":0},"mimo-niah-multi-64k":{"n":4,"recent":0,"stars":0},"mindcube":{"n":51,"recent":8,"stars":3},"mindcube-tiny":{"n":7,"recent":1,"stars":0},"minerva-math":{"n":67,"recent":9,"stars":3},"minerva-video":{"n":10,"recent":4,"stars":2},"minif2f-pass1":{"n":3,"recent":0,"stars":0},"minif2f-pass32":{"n":16,"recent":0,"stars":1},"minif2f-test":{"n":26,"recent":1,"stars":1},"mirb":{"n":19,"recent":0,"stars":1},"mixcount":{"n":5,"recent":3,"stars":1},"mixeval":{"n":33,"recent":4,"stars":3},"mixeval-hard":{"n":9,"recent":2,"stars":0},"mle-bench":{"n":8,"recent":6,"stars":1},"mle-bench-30":{"n":6,"recent":6,"stars":1},"mle-bench-lite":{"n":40,"recent":23,"stars":4},"mlogiqa":{"n":1,"recent":0,"stars":0},"mls-bench-lite":{"n":10,"recent":8,"stars":2},"mlvu":{"n":105,"recent":7,"stars":4},"mm-browsecomp":{"n":7,"recent":0,"stars":0},"mm-clawbench":{"n":6,"recent":0,"stars":0},"mm-ifeval":{"n":42,"recent":4,"stars":3},"mm-mt-bench":{"n":26,"recent":0,"stars":1},"mmar":{"n":9,"recent":4,"stars":1},"mmau-pro":{"n":8,"recent":3,"stars":1},"mmbench":{"n":100,"recent":0,"stars":3},"mmbench-cn":{"n":78,"recent":0,"stars":2},"mmbench-gui-l2":{"n":21,"recent":0,"stars":1},"mmbench-v1.1-cn":{"n":345,"recent":3,"stars":4},"mmbench-v1.1-en":{"n":367,"recent":4,"stars":4},"mmbench-v1.1-en-dev":{"n":80,"recent":3,"stars":3},"mmbench-video":{"n":24,"recent":0,"stars":1},"mmc-benchmark":{"n":14,"recent":0,"stars":1},"mmdu":{"n":2,"recent":0,"stars":0},"mme-cc":{"n":5,"recent":0,"stars":0},"mme-elo":{"n":86,"recent":0,"stars":2},"mme-realworld-cn":{"n":25,"recent":0,"stars":1},"mme-realworld-en":{"n":48,"recent":0,"stars":2},"mmhal-bench":{"n":36,"recent":4,"stars":3},"mmhal-bench-hallucination-rate":{"n":18,"recent":4,"stars":2},"mmiu":{"n":40,"recent":0,"stars":2},"mmlb-niah-128k":{"n":4,"recent":0,"stars":0},"mmlb-vrag-128k":{"n":4,"recent":0,"stars":0},"mmlongbench-128k":{"n":5,"recent":2,"stars":0},"mmlongbench-doc":{"n":52,"recent":10,"stars":4},"mmlu":{"n":760,"recent":90,"stars":5},"mmlu-arabic":{"n":9,"recent":0,"stars":0},"mmlu-cf":{"n":1,"recent":0,"stars":0},"mmlu-cloze":{"n":3,"recent":0,"stars":0},"mmlu-fulltext":{"n":2,"recent":0,"stars":0},"mmlu-med":{"n":11,"recent":0,"stars":1},"mmlu-pro":{"n":779,"recent":107,"stars":5},"mmlu-pro-cf":{"n":1,"recent":0,"stars":0},"mmlu-pro-mcf":{"n":9,"recent":0,"stars":0},"mmlu-prox":{"n":58,"recent":9,"stars":3},"mmlu-prox-ja":{"n":41,"recent":1,"stars":2},"mmlu-redux":{"n":272,"recent":26,"stars":5},"mmlu-stem":{"n":106,"recent":0,"stars":3},"mmmb":{"n":20,"recent":2,"stars":1},"mmmlu":{"n":114,"recent":10,"stars":5},"mmmlu-es":{"n":5,"recent":0,"stars":0},"mmmlu-german":{"n":1,"recent":0,"stars":0},"mmmu":{"n":317,"recent":13,"stars":5},"mmmu-med":{"n":7,"recent":0,"stars":0},"mmmu-pro":{"n":226,"recent":49,"stars":5},"mmmu-pro-vision":{"n":49,"recent":2,"stars":2},"mmmu-pro-with-tools":{"n":19,"recent":6,"stars":2},"mmmu-test":{"n":30,"recent":0,"stars":2},"mmsearch":{"n":24,"recent":3,"stars":2},"mmsearch-plus":{"n":3,"recent":0,"stars":0},"mmsi-bench":{"n":20,"recent":8,"stars":2},"mmsibench-circular":{"n":10,"recent":2,"stars":1},"mmstar":{"n":211,"recent":18,"stars":5},"mmt-bench":{"n":63,"recent":4,"stars":3},"mmvet":{"n":107,"recent":1,"stars":3},"mmvet-v2":{"n":21,"recent":0,"stars":1},"mmvp":{"n":10,"recent":1,"stars":1},"mmvu":{"n":69,"recent":17,"stars":4},"mobile-actions":{"n":4,"recent":0,"stars":0},"mobileworld":{"n":28,"recent":10,"stars":3},"mol-instructions":{"n":23,"recent":7,"stars":2},"molbench-bind":{"n":8,"recent":2,"stars":0},"molecular-iq":{"n":19,"recent":7,"stars":2},"mortgagetax":{"n":1,"recent":0,"stars":0},"motionbench":{"n":55,"recent":10,"stars":4},"mpdocbench-truncated-table-teds":{"n":6,"recent":5,"stars":1},"mrcr-128k":{"n":44,"recent":4,"stars":3},"mrcr-128k-2n":{"n":5,"recent":0,"stars":0},"mrcr-128k-4n":{"n":5,"recent":0,"stars":0},"mrcr-128k-8n":{"n":44,"recent":12,"stars":4},"mrcr-16k-8n":{"n":3,"recent":0,"stars":0},"mrcr-1m":{"n":21,"recent":3,"stars":2},"mrcr-1m-8n":{"n":9,"recent":6,"stars":1},"mrcr-256k-8n":{"n":11,"recent":4,"stars":2},"mrcr-32k-8n":{"n":3,"recent":0,"stars":0},"mrcr-512k-8n":{"n":8,"recent":6,"stars":1},"mrcr-64k-2n":{"n":5,"recent":0,"stars":0},"mrcr-64k-4n":{"n":5,"recent":0,"stars":0},"mrcr-64k-8n":{"n":8,"recent":0,"stars":0},"mrcr-8k-8n":{"n":3,"recent":0,"stars":0},"mrcr-v2":{"n":22,"recent":6,"stars":2},"ms-cxr-t":{"n":4,"recent":0,"stars":0},"msearth-mcq":{"n":5,"recent":0,"stars":0},"msvd-qa":{"n":7,"recent":0,"stars":0},"mt-bench":{"n":149,"recent":11,"stars":5},"mt-bench-ja":{"n":18,"recent":6,"stars":2},"mtalk-bench":{"n":4,"recent":1,"stars":0},"mteb-code-v1":{"n":1,"recent":0,"stars":0},"mteb-english-v2":{"n":1,"recent":0,"stars":0},"mteb-multilingual-v2":{"n":1,"recent":0,"stars":0},"mtob-full-book":{"n":4,"recent":0,"stars":0},"mtob-half-book":{"n":4,"recent":0,"stars":0},"mtvqa":{"n":24,"recent":0,"stars":1},"muirbench":{"n":80,"recent":3,"stars":3},"multi-if":{"n":129,"recent":19,"stars":5},"multi-ifeval":{"n":15,"recent":0,"stars":1},"multi-swe-bench":{"n":32,"recent":0,"stars":2},"multi-swe-bench-flash":{"n":1,"recent":0,"stars":0},"multi-swe-bench-mini":{"n":1,"recent":0,"stars":0},"multichallenge":{"n":129,"recent":25,"stars":5},"multiimg-qa-avg":{"n":19,"recent":0,"stars":1},"multilingual-jailbreak":{"n":1,"recent":0,"stars":0},"multilingual-mmbench":{"n":12,"recent":1,"stars":1},"multilingual-mmlu":{"n":34,"recent":0,"stars":2},"multiloko":{"n":4,"recent":1,"stars":0},"multipl-e":{"n":130,"recent":9,"stars":4},"multipl-e-humaneval":{"n":22,"recent":0,"stars":1},"multipl-e-mbpp":{"n":22,"recent":0,"stars":1},"musr":{"n":94,"recent":42,"stars":4},"mvbench":{"n":128,"recent":8,"stars":4},"nanochat-autoresearch":{"n":1,"recent":1,"stars":0},"nanogpt":{"n":4,"recent":3,"stars":1},"nanogpt-speedrun":{"n":1,"recent":1,"stars":0},"nanonets-kie":{"n":4,"recent":0,"stars":0},"natural2code":{"n":8,"recent":0,"stars":0},"naturalcodebench":{"n":15,"recent":0,"stars":1},"naturalquestions":{"n":124,"recent":3,"stars":4},"navsim":{"n":5,"recent":3,"stars":1},"new-yorker-caption-matching":{"n":38,"recent":37,"stars":4},"nextbase":{"n":7,"recent":7,"stars":1},"nextqa":{"n":22,"recent":0,"stars":1},"nexus":{"n":15,"recent":0,"stars":1},"nih":{"n":3,"recent":0,"stars":0},"nl2repo":{"n":73,"recent":42,"stars":4},"nli4ct":{"n":38,"recent":37,"stars":4},"nocaps":{"n":4,"recent":0,"stars":0},"noharm":{"n":1,"recent":1,"stars":0},"nolima-128k":{"n":5,"recent":0,"stars":0},"nolima-32k":{"n":5,"recent":0,"stars":0},"nolima-64k":{"n":5,"recent":0,"stars":0},"nova-63":{"n":29,"recent":2,"stars":1},"nuscenes":{"n":12,"recent":0,"stars":1},"objectron":{"n":3,"recent":0,"stars":0},"obqa":{"n":5,"recent":0,"stars":0},"ocnli":{"n":37,"recent":0,"stars":2},"ocrbench":{"n":239,"recent":15,"stars":5},"ocrbench-elo":{"n":17,"recent":0,"stars":1},"ocrbench-kie":{"n":9,"recent":3,"stars":1},"ocrbenchv2-cn":{"n":61,"recent":19,"stars":4},"ocrbenchv2-en":{"n":78,"recent":25,"stars":4},"ocrbenchv2-kie":{"n":5,"recent":3,"stars":1},"ocrbenchv2-kie-en":{"n":4,"recent":0,"stars":0},"ocrbenchv2-kie-zh":{"n":4,"recent":0,"stars":0},"ocrreasoning":{"n":16,"recent":9,"stars":2},"ocrvqa":{"n":8,"recent":0,"stars":0},"octocodingbench":{"n":6,"recent":0,"stars":0},"ocw-courses":{"n":7,"recent":0,"stars":0},"odinw-13":{"n":33,"recent":2,"stars":2},"odvbench":{"n":4,"recent":2,"stars":0},"odyssey-math":{"n":14,"recent":0,"stars":1},"officeqa":{"n":5,"recent":0,"stars":0},"officeqa-pro":{"n":34,"recent":25,"stars":4},"officeqa-pro-v2":{"n":6,"recent":6,"stars":1},"oibench-en":{"n":7,"recent":0,"stars":0},"ojbench":{"n":71,"recent":9,"stars":3},"okvqa":{"n":17,"recent":0,"stars":1},"olmocr-bench":{"n":61,"recent":12,"stars":4},"olympiadbench":{"n":80,"recent":6,"stars":3},"olympic-arena":{"n":4,"recent":0,"stars":0},"omega":{"n":38,"recent":0,"stars":2},"omni-math":{"n":36,"recent":5,"stars":3},"omni-math-hard":{"n":20,"recent":0,"stars":1},"omni3d":{"n":4,"recent":1,"stars":0},"omnidocbench":{"n":57,"recent":10,"stars":4},"omnidocbench-1.5":{"n":61,"recent":8,"stars":3},"omnidocbench-cn":{"n":25,"recent":0,"stars":1},"omnidocbench-edit":{"n":25,"recent":0,"stars":1},"omnidocbench-v1.6":{"n":42,"recent":14,"stars":4},"omnigaia":{"n":5,"recent":0,"stars":0},"omnimedvqa":{"n":7,"recent":0,"stars":0},"omnimmi":{"n":2,"recent":0,"stars":0},"omnispatial":{"n":9,"recent":0,"stars":0},"one-sided-statement":{"n":1,"recent":0,"stars":0},"oneig-bench-en":{"n":14,"recent":0,"stars":1},"oneig-bench-zh":{"n":11,"recent":0,"stars":1},"onemillionbench":{"n":13,"recent":10,"stars":3},"online-mind2web":{"n":18,"recent":5,"stars":2},"open-rewrite":{"n":2,"recent":0,"stars":0},"openai-internal-advanced-cyber-completion-rate":{"n":3,"recent":3,"stars":1},"openai-internal-broken-search-nondisclosure":{"n":6,"recent":6,"stars":1},"openai-internal-circumvention":{"n":2,"recent":2,"stars":0},"openai-internal-coding-deception":{"n":5,"recent":5,"stars":1},"openai-internal-cua-safety":{"n":8,"recent":8,"stars":1},"openai-internal-cua-safety-autoreview":{"n":2,"recent":2,"stars":0},"openai-internal-data-science-tasks":{"n":3,"recent":3,"stars":1},"openai-internal-db-migration-tasks":{"n":4,"recent":4,"stars":1},"openai-internal-design-tasks":{"n":3,"recent":3,"stars":1},"openai-internal-expert-swe":{"n":2,"recent":0,"stars":0},"openai-internal-factual-error-rate":{"n":6,"recent":6,"stars":1},"openai-internal-hallucination":{"n":2,"recent":2,"stars":0},"openai-internal-investment-banking-modeling":{"n":7,"recent":0,"stars":0},"openai-internal-management-consulting":{"n":7,"recent":5,"stars":1},"openai-internal-research-debugging":{"n":4,"recent":3,"stars":1},"openai-internal-reviewer-bypass":{"n":6,"recent":6,"stars":1},"openai-internal-unauthorized-agent-interaction":{"n":4,"recent":4,"stars":1},"openai-internal-vuln-discovery-report-writing":{"n":3,"recent":3,"stars":1},"openai-internal-warning-circumvention":{"n":6,"recent":6,"stars":1},"openai-internal-zero-day-discovery":{"n":3,"recent":3,"stars":1},"openbookqa":{"n":108,"recent":7,"stars":4},"openeqa":{"n":12,"recent":1,"stars":1},"openrewrite-eval":{"n":3,"recent":0,"stars":0},"openscore-string-quartets":{"n":2,"recent":2,"stars":0},"optmath":{"n":5,"recent":0,"stars":0},"order-15-items":{"n":5,"recent":0,"stars":0},"order-30-items":{"n":5,"recent":0,"stars":0},"osworld":{"n":26,"recent":1,"stars":1},"osworld-2.0":{"n":35,"recent":30,"stars":4},"osworld-2.0-offline":{"n":8,"recent":8,"stars":1},"osworld-2.0-strict":{"n":15,"recent":14,"stars":3},"osworld-2.1":{"n":10,"recent":10,"stars":3},"osworld-2.1-offline":{"n":4,"recent":3,"stars":1},"osworld-2.1-strict":{"n":7,"recent":7,"stars":1},"osworld-g":{"n":86,"recent":10,"stars":4},"osworld-verified":{"n":87,"recent":38,"stars":4},"osworld2":{"n":4,"recent":0,"stars":0},"ovbench":{"n":17,"recent":6,"stars":2},"ovisocr-kie-inhouse":{"n":5,"recent":3,"stars":1},"ovobench":{"n":25,"recent":8,"stars":2},"p3m-500-np-mad":{"n":2,"recent":2,"stars":0},"pagentbench":{"n":6,"recent":3,"stars":1},"paper-bench-code-dev":{"n":11,"recent":5,"stars":2},"paperbench":{"n":32,"recent":17,"stars":4},"parsebench":{"n":15,"recent":7,"stars":2},"part-affordance":{"n":13,"recent":7,"stars":2},"pathvqa":{"n":7,"recent":0,"stars":0},"paws-x":{"n":4,"recent":4,"stars":1},"penguinscrolls":{"n":3,"recent":0,"stars":0},"perceptionbench":{"n":11,"recent":9,"stars":2},"perceptiontest":{"n":37,"recent":3,"stars":3},"permemsafe":{"n":2,"recent":2,"stars":0},"persona-modulation":{"n":1,"recent":0,"stars":0},"personal-info-leak-fs":{"n":1,"recent":0,"stars":0},"personamem":{"n":2,"recent":2,"stars":0},"perspective-bench":{"n":2,"recent":1,"stars":0},"phishnchips":{"n":38,"recent":37,"stars":4},"phybench":{"n":33,"recent":5,"stars":3},"physical-safety":{"n":1,"recent":0,"stars":0},"phyx":{"n":11,"recent":5,"stars":2},"pinchbench":{"n":47,"recent":23,"stars":4},"pinchbench-avg":{"n":37,"recent":13,"stars":4},"pinchbench-best":{"n":10,"recent":0,"stars":1},"piobench":{"n":13,"recent":7,"stars":2},"piqa":{"n":207,"recent":15,"stars":5},"pixmo-points":{"n":17,"recent":10,"stars":3},"pixmocount":{"n":71,"recent":8,"stars":3},"plawbench":{"n":5,"recent":5,"stars":1},"pmc-vqa":{"n":35,"recent":5,"stars":3},"point-bench":{"n":49,"recent":11,"stars":4},"pointarena":{"n":6,"recent":5,"stars":1},"polymath":{"n":69,"recent":3,"stars":3},"pop909-cl-decision":{"n":36,"recent":35,"stars":4},"pope":{"n":58,"recent":2,"stars":2},"popqa":{"n":66,"recent":0,"stars":2},"posttrainbench":{"n":32,"recent":21,"stars":4},"posttrainbench-lite":{"n":4,"recent":3,"stars":1},"ppm-100-mad":{"n":2,"recent":2,"stars":0},"prbench-finance":{"n":5,"recent":5,"stars":1},"prbench-legal":{"n":10,"recent":7,"stars":2},"prdbench":{"n":2,"recent":0,"stars":0},"presentbench":{"n":5,"recent":2,"stars":0},"procbench":{"n":9,"recent":0,"stars":0},"programbench":{"n":28,"recent":23,"stars":3},"programbench-almost-solved":{"n":11,"recent":11,"stars":3},"prompt-extraction-robustness":{"n":1,"recent":0,"stars":0},"prompt-injection":{"n":1,"recent":0,"stars":0},"prontoqa":{"n":10,"recent":0,"stars":1},"proofbench-advanced":{"n":28,"recent":1,"stars":1},"proofbench-basic":{"n":9,"recent":0,"stars":0},"proofnet-test":{"n":13,"recent":0,"stars":1},"protocolqa":{"n":2,"recent":0,"stars":0},"proverbench":{"n":12,"recent":0,"stars":1},"pubmedqa":{"n":15,"recent":4,"stars":2},"pubtabnet":{"n":6,"recent":1,"stars":0},"puredocbench":{"n":9,"recent":7,"stars":1},"putnam-2025":{"n":2,"recent":0,"stars":0},"putnambench":{"n":17,"recent":2,"stars":1},"q-bench":{"n":10,"recent":0,"stars":1},"q-spatial-bench":{"n":13,"recent":7,"stars":2},"qivd":{"n":12,"recent":6,"stars":2},"qrecc":{"n":10,"recent":0,"stars":1},"quac":{"n":23,"recent":0,"stars":1},"quality":{"n":2,"recent":0,"stars":0},"query-sufficiency":{"n":5,"recent":2,"stars":0},"qvhighlights":{"n":9,"recent":0,"stars":0},"qwenclawbench":{"n":37,"recent":15,"stars":4},"r-bench":{"n":19,"recent":0,"stars":1},"race":{"n":67,"recent":2,"stars":2},"race-high":{"n":21,"recent":0,"stars":1},"race-middle":{"n":36,"recent":0,"stars":2},"ragtruth":{"n":39,"recent":38,"stars":4},"random-complex-tasks":{"n":8,"recent":0,"stars":0},"real5-omnidocbench":{"n":30,"recent":8,"stars":3},"realbench":{"n":5,"recent":0,"stars":0},"realkie-fcc-verified":{"n":14,"recent":0,"stars":1},"realworldqa":{"n":228,"recent":17,"stars":5},"reasonseg-val":{"n":5,"recent":2,"stars":0},"recruit-bench":{"n":5,"recent":2,"stars":0},"ref-l4-rod-f1":{"n":6,"recent":3,"stars":1},"ref-l4-test":{"n":2,"recent":0,"stars":0},"ref-zom-ciou":{"n":5,"recent":2,"stars":0},"ref-zom-rejection":{"n":5,"recent":2,"stars":0},"refcoco":{"n":97,"recent":8,"stars":3},"refcoco-m":{"n":1,"recent":0,"stars":0},"refcoco-testa-ciou":{"n":6,"recent":2,"stars":0},"refcocog":{"n":35,"recent":0,"stars":2},"refcocog-rod-f1":{"n":6,"recent":3,"stars":1},"refcocog-rod-rejection":{"n":6,"recent":3,"stars":1},"refcocog-test-ciou":{"n":6,"recent":2,"stars":0},"refcocoplus":{"n":33,"recent":0,"stars":2},"refcocoplus-testa-ciou":{"n":6,"recent":2,"stars":0},"refspatialbench":{"n":71,"recent":13,"stars":4},"refusal-suppression":{"n":1,"recent":0,"stars":0},"refusalbench":{"n":4,"recent":0,"stars":0},"remi":{"n":5,"recent":0,"stars":0},"repobench":{"n":16,"recent":0,"stars":1},"researchrubrics":{"n":27,"recent":8,"stars":2},"rewardbench":{"n":175,"recent":0,"stars":3},"riemannbench":{"n":7,"recent":6,"stars":1},"rlhf":{"n":1,"recent":0,"stars":0},"roboafford":{"n":18,"recent":11,"stars":3},"roborefit":{"n":13,"recent":7,"stars":2},"robospatialhome":{"n":49,"recent":12,"stars":4},"robotgrounding-inhouse":{"n":6,"recent":5,"stars":1},"robovqa":{"n":13,"recent":7,"stars":2},"roo-code-evals":{"n":40,"recent":0,"stars":2},"routerbench-decision":{"n":38,"recent":37,"stars":4},"ruler-100-1m":{"n":2,"recent":0,"stars":0},"ruler-100-256k":{"n":2,"recent":0,"stars":0},"ruler-100-512k":{"n":2,"recent":0,"stars":0},"ruler-128k":{"n":44,"recent":4,"stars":3},"ruler-16k":{"n":28,"recent":1,"stars":1},"ruler-1m":{"n":21,"recent":4,"stars":2},"ruler-2048k":{"n":1,"recent":0,"stars":0},"ruler-256k":{"n":11,"recent":3,"stars":2},"ruler-32k":{"n":35,"recent":3,"stars":3},"ruler-4k":{"n":17,"recent":0,"stars":1},"ruler-512k":{"n":10,"recent":2,"stars":1},"ruler-64k":{"n":38,"recent":5,"stars":3},"ruler-8k":{"n":28,"recent":1,"stars":1},"rw-search":{"n":15,"recent":3,"stars":2},"saas-bench":{"n":4,"recent":3,"stars":1},"safetybench":{"n":5,"recent":0,"stars":0},"salad-bench":{"n":7,"recent":3,"stars":1},"sarena-icon":{"n":5,"recent":0,"stars":0},"sat":{"n":24,"recent":8,"stars":2},"sat-math":{"n":4,"recent":0,"stars":0},"sata-bench":{"n":38,"recent":37,"stars":4},"scale-ai-multi-challenge":{"n":9,"recent":1,"stars":0},"scicode":{"n":213,"recent":84,"stars":5},"scicode-main":{"n":31,"recent":5,"stars":3},"scienceqa":{"n":34,"recent":0,"stars":2},"sciq":{"n":30,"recent":1,"stars":2},"scireasoner":{"n":20,"recent":5,"stars":2},"scires-frontiermath-tier-1-3":{"n":17,"recent":5,"stars":2},"scires-frontiermath-tier-4":{"n":21,"recent":8,"stars":2},"screenqa-complex":{"n":12,"recent":0,"stars":1},"screenqa-short":{"n":12,"recent":0,"stars":1},"screenspot":{"n":40,"recent":3,"stars":3},"screenspot-pro":{"n":164,"recent":15,"stars":5},"screenspot-pro-with-tools":{"n":3,"recent":1,"stars":0},"screenspot-v2":{"n":88,"recent":4,"stars":3},"seal-0":{"n":44,"recent":3,"stars":3},"sec-bench-pro":{"n":12,"recent":11,"stars":3},"seccodebench":{"n":6,"recent":0,"stars":0},"seed-bench-2-plus":{"n":35,"recent":0,"stars":2},"seed-bench-img":{"n":75,"recent":1,"stars":2},"seedbench":{"n":24,"recent":1,"stars":1},"sfe":{"n":23,"recent":5,"stars":2},"sgd-x-decision":{"n":38,"recent":37,"stars":4},"sgi-bench":{"n":17,"recent":6,"stars":2},"sharerobot-affordance":{"n":6,"recent":5,"stars":1},"sharerobot-traj":{"n":13,"recent":7,"stars":2},"showdown":{"n":22,"recent":0,"stars":1},"sifo":{"n":6,"recent":0,"stars":0},"sifo-multiturn":{"n":6,"recent":0,"stars":0},"simple-safety-tests":{"n":1,"recent":0,"stars":0},"simpleqa":{"n":133,"recent":11,"stars":5},"simpleqa-search":{"n":13,"recent":0,"stars":1},"simpleqa-verified":{"n":82,"recent":24,"stars":4},"simplevqa":{"n":100,"recent":18,"stars":5},"simplevqa-ds":{"n":4,"recent":0,"stars":0},"simplevqa-with-tools":{"n":12,"recent":9,"stars":2},"siqa":{"n":58,"recent":3,"stars":3},"skatebench":{"n":1,"recent":0,"stars":0},"skillsbench":{"n":59,"recent":31,"stars":4},"skillsbench-v1.1":{"n":5,"recent":5,"stars":1},"slake":{"n":39,"recent":5,"stars":3},"smolinstruct":{"n":5,"recent":0,"stars":0},"sob":{"n":4,"recent":2,"stars":0},"socialiqa":{"n":21,"recent":1,"stars":1},"sol-execbench":{"n":1,"recent":1,"stars":0},"sparbench":{"n":7,"recent":1,"stars":0},"spatialsense-vqa":{"n":3,"recent":0,"stars":0},"spatialviz":{"n":15,"recent":0,"stars":1},"speechrole":{"n":3,"recent":0,"stars":0},"spider":{"n":25,"recent":0,"stars":1},"spider-2.0-lite":{"n":6,"recent":3,"stars":1},"spiral-bench":{"n":24,"recent":0,"stars":1},"spreadsheetbench-2":{"n":16,"recent":15,"stars":3},"spreadsheetbench-v1":{"n":24,"recent":10,"stars":3},"spreadsheetbench-verified":{"n":4,"recent":1,"stars":0},"sqa":{"n":10,"recent":0,"stars":1},"squad-v1.1":{"n":15,"recent":0,"stars":1},"squad-v2.0":{"n":35,"recent":6,"stars":3},"sre-bench":{"n":3,"recent":3,"stars":1},"sroie-f1":{"n":6,"recent":3,"stars":1},"streamingbench":{"n":14,"recent":4,"stars":2},"strongreject":{"n":17,"recent":9,"stars":2},"stvqa":{"n":1,"recent":0,"stars":0},"sunrgbd":{"n":19,"recent":0,"stars":1},"superchem":{"n":31,"recent":14,"stars":4},"superglue":{"n":29,"recent":0,"stars":1},"supergpqa":{"n":149,"recent":18,"stars":5},"surds":{"n":18,"recent":7,"stars":2},"svg-bench":{"n":9,"recent":1,"stars":0},"swe-atlas-qna":{"n":44,"recent":33,"stars":4},"swe-atlas-refactoring":{"n":20,"recent":14,"stars":3},"swe-atlas-test-writing":{"n":23,"recent":14,"stars":3},"swe-bench":{"n":43,"recent":2,"stars":2},"swe-bench-multilingual":{"n":167,"recent":72,"stars":5},"swe-bench-multimodal":{"n":19,"recent":15,"stars":3},"swe-bench-openhands":{"n":9,"recent":1,"stars":0},"swe-bench-pro":{"n":139,"recent":84,"stars":5},"swe-bench-pro-public":{"n":100,"recent":48,"stars":5},"swe-bench-pro-v2":{"n":8,"recent":5,"stars":1},"swe-bench-pro-v2-hard":{"n":4,"recent":4,"stars":1},"swe-bench-verified":{"n":340,"recent":101,"stars":5},"swe-dev":{"n":6,"recent":0,"stars":0},"swe-fficiency":{"n":5,"recent":1,"stars":0},"swe-interact":{"n":2,"recent":2,"stars":0},"swe-lancer":{"n":8,"recent":0,"stars":0},"swe-lancer-diamond":{"n":6,"recent":0,"stars":0},"swe-lancer-ic-diamond":{"n":3,"recent":0,"stars":0},"swe-marathon":{"n":22,"recent":18,"stars":3},"swe-marathon-v1.1":{"n":7,"recent":7,"stars":1},"swe-perf":{"n":7,"recent":0,"stars":0},"swe-review":{"n":5,"recent":0,"stars":0},"swebbench":{"n":6,"recent":3,"stars":1},"switzerland-qa":{"n":1,"recent":0,"stars":0},"swt-bench":{"n":7,"recent":0,"stars":0},"sysbench":{"n":17,"recent":7,"stars":2},"t-eval":{"n":13,"recent":0,"stars":1},"tabfact":{"n":9,"recent":2,"stars":0},"tabmwp":{"n":17,"recent":0,"stars":1},"tallyqa":{"n":3,"recent":0,"stars":0},"tat-qa":{"n":6,"recent":0,"stars":0},"tau-voice-airline":{"n":29,"recent":16,"stars":3},"tau-voice-retail":{"n":29,"recent":16,"stars":3},"tau-voice-telecom":{"n":29,"recent":16,"stars":3},"tau1-airline":{"n":13,"recent":0,"stars":1},"tau1-retail":{"n":13,"recent":0,"stars":1},"tau2-airline":{"n":101,"recent":19,"stars":5},"tau2-airline-verified":{"n":11,"recent":0,"stars":1},"tau2-bench":{"n":9,"recent":0,"stars":0},"tau2-retail":{"n":114,"recent":19,"stars":5},"tau2-retail-verified":{"n":11,"recent":0,"stars":1},"tau2-telecom":{"n":203,"recent":32,"stars":5},"tau3-airline":{"n":17,"recent":3,"stars":2},"tau3-banking":{"n":121,"recent":80,"stars":5},"tau3-banking-voice":{"n":5,"recent":4,"stars":1},"tau3-retail":{"n":17,"recent":3,"stars":2},"tau3-telecom":{"n":19,"recent":4,"stars":2},"tax-agent-bench":{"n":1,"recent":1,"stars":0},"taxeval":{"n":1,"recent":0,"stars":0},"tempcompass":{"n":31,"recent":3,"stars":3},"tense-change":{"n":1,"recent":0,"stars":0},"terminal-bench":{"n":90,"recent":1,"stars":2},"terminal-bench-2.0":{"n":144,"recent":22,"stars":5},"terminal-bench-2.1":{"n":194,"recent":141,"stars":5},"terminal-bench-3.0":{"n":19,"recent":19,"stars":3},"terminal-bench-4.0":{"n":47,"recent":45,"stars":4},"terminal-bench-4.0-aa":{"n":5,"recent":5,"stars":1},"terminal-bench-hard":{"n":78,"recent":7,"stars":3},"terminal-bench-lite":{"n":15,"recent":8,"stars":2},"terminal-bench-science":{"n":14,"recent":14,"stars":3},"terminal-bench-terminus":{"n":11,"recent":0,"stars":1},"textquests":{"n":18,"recent":0,"stars":1},"textquests-harm":{"n":15,"recent":0,"stars":1},"textvqa":{"n":194,"recent":8,"stars":4},"theoremqa":{"n":87,"recent":0,"stars":2},"tiif-bench-long":{"n":16,"recent":0,"stars":1},"tiif-bench-short":{"n":16,"recent":0,"stars":1},"timelens-activitynet":{"n":8,"recent":4,"stars":1},"timelens-charades":{"n":8,"recent":4,"stars":1},"timelens-qvhighlights":{"n":8,"recent":4,"stars":1},"tir-bench":{"n":16,"recent":0,"stars":1},"tldr9-plus":{"n":2,"recent":0,"stars":0},"tomato":{"n":42,"recent":12,"stars":4},"tomg-bench":{"n":9,"recent":5,"stars":1},"tool-decathlon":{"n":18,"recent":0,"stars":1},"toolace":{"n":7,"recent":6,"stars":1},"toolathlon":{"n":61,"recent":20,"stars":4},"toolathlon-verified":{"n":59,"recent":46,"stars":4},"toolhop":{"n":4,"recent":2,"stars":0},"toolret-decision":{"n":38,"recent":37,"stars":4},"toolsandbox":{"n":12,"recent":4,"stars":2},"topiocqa":{"n":10,"recent":0,"stars":1},"totaltext-f1":{"n":6,"recent":3,"stars":1},"toxigen":{"n":1,"recent":0,"stars":0},"treebench":{"n":17,"recent":2,"stars":1},"triqa":{"n":4,"recent":0,"stars":0},"triviaqa":{"n":169,"recent":9,"stars":4},"triviaqa-wiki":{"n":5,"recent":0,"stars":0},"trustllm":{"n":4,"recent":0,"stars":0},"truthfulqa":{"n":169,"recent":4,"stars":4},"truthfulqa-binary":{"n":2,"recent":2,"stars":0},"truthfulqa-de":{"n":2,"recent":0,"stars":0},"truthqa":{"n":1,"recent":0,"stars":0},"truthqa-multilingual":{"n":1,"recent":0,"stars":0},"turkishmmlu":{"n":12,"recent":0,"stars":1},"tvbench":{"n":25,"recent":11,"stars":3},"tydiqa":{"n":12,"recent":0,"stars":1},"typed-decision":{"n":7,"recent":6,"stars":1},"u-artifacts":{"n":5,"recent":0,"stars":0},"ugc-videocap":{"n":5,"recent":5,"stars":1},"ui-vision":{"n":20,"recent":0,"stars":1},"unimernet":{"n":6,"recent":1,"stars":0},"uro-bench-pro-oral":{"n":3,"recent":0,"stars":0},"uro-bench-pro-reasoning":{"n":3,"recent":0,"stars":0},"uro-bench-pro-understanding":{"n":3,"recent":0,"stars":0},"usaco":{"n":10,"recent":0,"stars":1},"usamo-2026":{"n":17,"recent":7,"stars":2},"v-star":{"n":72,"recent":9,"stars":3},"v-star-with-tools":{"n":8,"recent":1,"stars":0},"vabench-point":{"n":13,"recent":7,"stars":2},"vabench-visual-trace":{"n":13,"recent":7,"stars":2},"vals-index":{"n":50,"recent":47,"stars":4},"vast-stance":{"n":38,"recent":37,"stars":4},"vcr-en-easy":{"n":27,"recent":0,"stars":1},"vcrbench":{"n":9,"recent":3,"stars":1},"vct":{"n":13,"recent":0,"stars":1},"vending-bench-2":{"n":23,"recent":2,"stars":1},"vibe-android":{"n":5,"recent":0,"stars":0},"vibe-average":{"n":7,"recent":0,"stars":0},"vibe-backend":{"n":5,"recent":0,"stars":0},"vibe-code-bench":{"n":4,"recent":4,"stars":1},"vibe-code-bench-v1.1":{"n":3,"recent":2,"stars":0},"vibe-eval-reka":{"n":1,"recent":0,"stars":0},"vibe-ios":{"n":5,"recent":0,"stars":0},"vibe-simulation":{"n":5,"recent":0,"stars":0},"vibe-web":{"n":5,"recent":0,"stars":0},"vibeval":{"n":11,"recent":0,"stars":1},"video-mme":{"n":26,"recent":2,"stars":1},"videoevalpro":{"n":26,"recent":3,"stars":2},"videohallucer":{"n":4,"recent":0,"stars":0},"videoholmes":{"n":22,"recent":8,"stars":2},"videomathqa":{"n":5,"recent":3,"stars":1},"videomme":{"n":41,"recent":5,"stars":3},"videomme-nosub":{"n":122,"recent":9,"stars":4},"videomme-sub":{"n":94,"recent":11,"stars":4},"videomme-v2":{"n":27,"recent":19,"stars":3},"videommmu":{"n":93,"recent":16,"stars":4},"videoreasonbench":{"n":9,"recent":1,"stars":0},"videosimpleqa":{"n":13,"recent":4,"stars":2},"viewspatial-bench":{"n":20,"recent":8,"stars":2},"visdrone-det-f1":{"n":7,"recent":3,"stars":1},"visdrone-pointing":{"n":5,"recent":3,"stars":1},"visfactor":{"n":13,"recent":7,"stars":2},"vision2web":{"n":22,"recent":17,"stars":3},"vispeak":{"n":9,"recent":1,"stars":0},"visualmrc":{"n":1,"recent":0,"stars":0},"visualprobe":{"n":4,"recent":1,"stars":0},"visualpuzzle":{"n":6,"recent":0,"stars":0},"visualwebbench-avg":{"n":28,"recent":0,"stars":1},"visulogic":{"n":47,"recent":2,"stars":2},"vitabench":{"n":66,"recent":22,"stars":4},"vitabench-2.0":{"n":6,"recent":3,"stars":1},"vizwiz":{"n":7,"recent":0,"stars":0},"vl-rewardbench":{"n":14,"recent":1,"stars":1},"vlabench":{"n":13,"recent":7,"stars":2},"vlad":{"n":9,"recent":2,"stars":0},"vlms-are-biased":{"n":13,"recent":1,"stars":1},"vlms-are-blind":{"n":16,"recent":0,"stars":1},"vlmsarebiased":{"n":21,"recent":8,"stars":2},"vlmsareblind":{"n":26,"recent":0,"stars":1},"voicebench-advbench":{"n":18,"recent":1,"stars":1},"voicebench-alpacaeval":{"n":18,"recent":1,"stars":1},"voicebench-bbh":{"n":13,"recent":1,"stars":1},"voicebench-commoneval":{"n":22,"recent":1,"stars":1},"voicebench-ifeval":{"n":24,"recent":4,"stars":2},"voicebench-ja-elyza":{"n":4,"recent":1,"stars":0},"voicebench-ja-m-ifeval":{"n":4,"recent":1,"stars":0},"voicebench-ja-spoken-elyza":{"n":4,"recent":1,"stars":0},"voicebench-mau-v05-15-25":{"n":30,"recent":10,"stars":4},"voicebench-mmsu":{"n":18,"recent":1,"stars":1},"voicebench-mmsu-audio":{"n":26,"recent":6,"stars":2},"voicebench-openbookqa":{"n":13,"recent":1,"stars":1},"voicebench-sd-qa":{"n":18,"recent":1,"stars":1},"voicebench-wildvoice":{"n":14,"recent":1,"stars":1},"vpct":{"n":6,"recent":0,"stars":0},"vqa-rad":{"n":11,"recent":0,"stars":1},"vqav2":{"n":83,"recent":0,"stars":2},"vsi-bench":{"n":55,"recent":10,"stars":4},"waymoqa":{"n":9,"recent":2,"stars":0},"waymoqa-safety":{"n":9,"recent":2,"stars":0},"webarena":{"n":7,"recent":0,"stars":0},"webarena-verified":{"n":19,"recent":12,"stars":3},"webclick":{"n":22,"recent":0,"stars":1},"webdev-arena":{"n":57,"recent":5,"stars":3},"webquest-multiqa":{"n":7,"recent":0,"stars":0},"webquest-singleqa":{"n":7,"recent":0,"stars":0},"websrc":{"n":18,"recent":0,"stars":1},"webtailbench":{"n":8,"recent":3,"stars":1},"webtestbench":{"n":4,"recent":4,"stars":1},"webvoyager":{"n":36,"recent":13,"stars":4},"webvoyager2":{"n":3,"recent":0,"stars":0},"webwalker-qa":{"n":15,"recent":2,"stars":1},"wemath":{"n":49,"recent":3,"stars":3},"weref-f1":{"n":6,"recent":3,"stars":1},"weref-rejection":{"n":6,"recent":3,"stars":1},"werefmat-category-mad":{"n":2,"recent":2,"stars":0},"werefmat-referring-mad":{"n":2,"recent":2,"stars":0},"werewolf":{"n":1,"recent":0,"stars":0},"wgo-bench":{"n":5,"recent":5,"stars":1},"when2call":{"n":61,"recent":59,"stars":4},"where2place":{"n":29,"recent":12,"stars":3},"wide-search":{"n":90,"recent":43,"stars":4},"wikiwebfacts":{"n":5,"recent":1,"stars":0},"wild-jailbreak":{"n":12,"recent":6,"stars":2},"wildbench-v2":{"n":20,"recent":0,"stars":1},"wildclawbench":{"n":53,"recent":32,"stars":4},"wildguardtest":{"n":32,"recent":27,"stars":4},"wildspeech-bench":{"n":10,"recent":5,"stars":2},"wildvision":{"n":23,"recent":0,"stars":1},"windows-agent-arena":{"n":4,"recent":0,"stars":0},"winogender":{"n":3,"recent":0,"stars":0},"winogrande":{"n":325,"recent":53,"stars":5},"winogrande-de":{"n":2,"recent":0,"stars":0},"wmdp-bio":{"n":3,"recent":0,"stars":0},"wmdp-chem":{"n":3,"recent":0,"stars":0},"wmdp-cyber":{"n":3,"recent":0,"stars":0},"wmt16":{"n":2,"recent":0,"stars":0},"wmt16-instruct":{"n":2,"recent":0,"stars":0},"wmt20-en-ja":{"n":31,"recent":0,"stars":2},"wmt20-ja-en":{"n":31,"recent":0,"stars":2},"wmt23-ende":{"n":1,"recent":0,"stars":0},"wmt24-plus-plus":{"n":70,"recent":10,"stars":4},"wod-e2e":{"n":4,"recent":3,"stars":1},"workbench":{"n":4,"recent":2,"stars":0},"workbuddy-bench":{"n":12,"recent":9,"stars":2},"workspacebench":{"n":15,"recent":12,"stars":3},"workspacebench-lite":{"n":8,"recent":8,"stars":1},"worldbench":{"n":5,"recent":2,"stars":0},"worldtravel2-multimodal":{"n":5,"recent":0,"stars":0},"worldtravel2-text":{"n":5,"recent":0,"stars":0},"worldvqa":{"n":30,"recent":15,"stars":4},"worldvqa-with-tools":{"n":7,"recent":4,"stars":1},"writingbench":{"n":43,"recent":3,"stars":3},"wsc":{"n":54,"recent":0,"stars":2},"wtq":{"n":7,"recent":0,"stars":0},"xbench-deepsearch":{"n":42,"recent":7,"stars":3},"xbench-deepsearch-2025.05":{"n":31,"recent":1,"stars":2},"xbench-deepsearch-2025.10":{"n":37,"recent":6,"stars":3},"xcopa":{"n":22,"recent":3,"stars":2},"xdev-bench-hard":{"n":5,"recent":5,"stars":1},"xlrs-bench":{"n":18,"recent":5,"stars":2},"xnli":{"n":24,"recent":7,"stars":2},"xorqa-in":{"n":5,"recent":1,"stars":0},"xpertbench-edu":{"n":5,"recent":0,"stars":0},"xpertbench-fin":{"n":5,"recent":0,"stars":0},"xpertbench-humanities":{"n":5,"recent":0,"stars":0},"xpertbench-law":{"n":5,"recent":0,"stars":0},"xpertbench-research":{"n":5,"recent":0,"stars":0},"xquad":{"n":3,"recent":0,"stars":0},"xquad-in":{"n":5,"recent":1,"stars":0},"xstest":{"n":17,"recent":5,"stars":2},"xstorycloze":{"n":2,"recent":0,"stars":0},"xwinograd":{"n":2,"recent":0,"stars":0},"yc-bench":{"n":7,"recent":1,"stars":0},"zclawbench":{"n":4,"recent":0,"stars":0},"zebralogic":{"n":147,"recent":2,"stars":3},"zerobench":{"n":48,"recent":6,"stars":3},"zerobench-sub":{"n":52,"recent":7,"stars":3},"zerobench-with-tools":{"n":23,"recent":19,"stars":3},"zeroscrolls-booksumsort":{"n":7,"recent":0,"stars":0},"zeroscrolls-govreport":{"n":8,"recent":0,"stars":0},"zeroscrolls-musique":{"n":9,"recent":0,"stars":0},"zeroscrolls-narrativeqa":{"n":8,"recent":0,"stars":0},"zeroscrolls-qasper":{"n":8,"recent":0,"stars":0},"zeroscrolls-qmsum":{"n":8,"recent":0,"stars":0},"zeroscrolls-quality":{"n":8,"recent":0,"stars":0},"zeroscrolls-spacedigest":{"n":9,"recent":0,"stars":0},"zeroscrolls-squality":{"n":9,"recent":0,"stars":0},"zeroscrolls-summscreenfd":{"n":8,"recent":0,"stars":0}}