{"source":"https://decisionbench.ai/model/jev-1.13","dataSource":"https://decisionbench.ai/viewer.json","generatedAt":"2026-09-24T17:36:03.640157+00:00","retrievedAt":"2026-09-24","sourceSha256":"d3b619d3a83756026fadf152d2c1155385da7277113b8aefc46707713ada8e57","corpusSha256":"3599baea0d9c7e4e3d86c8b06af96e6850edca037b334bbc6b4e1a0033021725","runId":"jev-1.13-bench-v4-c861f2a4","completedAt":"2026-09-23T13:50:29.093424+00:00","apiModel":"jev-1.13.0","summary":{"rows":1041,"correct":976,"accuracy":0.9375600384245918,"ci":[0.921192569576704,0.9507100452259665],"verdict":"Adequado"},"excluded":30,"latency":437.3780000023544,"cost1000":0.043822380403458254,"brier":0.09570331728192177,"ece":0.013542922015544445,"highConfidenceErrors":15,"categories":[{"id":"engineering","name":"Engenharia","best":"Jev 1.13","bestAccuracy":0.9733333333333334,"rows":150,"correct":146,"accuracy":0.9733333333333334,"ci":[0.9334461094878556,0.989582059177032],"verdict":"Adequado"},{"id":"agents","name":"Agentes e avaliações de IA","best":"Gemini Flash / DeepSeek Flash","bestAccuracy":0.9285714285714286,"rows":154,"correct":135,"accuracy":0.8766233766233766,"ci":[0.8153398649097212,0.9195747821461866],"verdict":"Arriscado"},{"id":"safety","name":"Confiança e segurança","best":"DeepSeek Flash","bestAccuracy":0.9833333333333333,"rows":60,"correct":58,"accuracy":0.9666666666666667,"ci":[0.886362257256914,0.9908106807438021],"verdict":"Adequado"},{"id":"support","name":"Suporte ao cliente","best":"Gemini Flash / GLM Flash / DeepSeek Flash","bestAccuracy":0.9850746268656716,"rows":67,"correct":65,"accuracy":0.9701492537313433,"ci":[0.8975344443664799,0.991775305161102],"verdict":"Adequado"},{"id":"commerce","name":"Vendas e comércio","best":"Flash Lite / Luna API","bestAccuracy":0.9666666666666667,"rows":90,"correct":84,"accuracy":0.9333333333333333,"ci":[0.8620990522567448,0.9690900722541721],"verdict":"Adequado"},{"id":"finance","name":"Finanças","best":"Luna API / Haiku API / Jev 1.13","bestAccuracy":0.9917355371900827,"rows":121,"correct":120,"accuracy":0.9917355371900827,"ci":[0.9546693563957512,0.9985396266145802],"verdict":"Adequado"},{"id":"legal","name":"Jurídico","best":"Jev 1.13","bestAccuracy":0.9603174603174603,"rows":126,"correct":121,"accuracy":0.9603174603174603,"ci":[0.9104643457790981,0.9829328869198303],"verdict":"Adequado"},{"id":"product","name":"Gestão de produtos","best":"Gemini Flash","bestAccuracy":0.9166666666666666,"rows":60,"correct":47,"accuracy":0.7833333333333333,"ci":[0.6637997242680521,0.868769559518097],"verdict":"Não adequado"},{"id":"data","name":"Dados e análises","best":"Sonnet API / GLM Flash","bestAccuracy":1,"rows":126,"correct":124,"accuracy":0.9841269841269841,"ci":[0.9439712362150748,0.9956361981751772],"verdict":"Adequado"},{"id":"documents","name":"Documentos e reuniões","best":"Sonnet API","bestAccuracy":0.9080459770114943,"rows":87,"correct":76,"accuracy":0.8735632183908046,"ci":[0.7876218511925265,0.9279104712055445],"verdict":"Arriscado"},{"id":"design","name":"Design","best":"Gemini Flash / Flash Lite / Luna API / Sonnet API","bestAccuracy":1,"rows":0,"correct":0,"accuracy":null,"ci":[0,0],"verdict":"Não avaliado"}],"tasks":[{"id":"ENG-1","title":"Localizar o arquivo a corrigir","category":"engineering","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"ENG-2","title":"Rotular uma alteração de código","category":"engineering","rows":30,"correct":28,"accuracy":0.9333333333333333,"ci":[0.7867654163738308,0.9815229762087295],"verdict":"Arriscado"},{"id":"ENG-3","title":"Classificar uma vulnerabilidade","category":"engineering","rows":30,"correct":29,"accuracy":0.9666666666666667,"ci":[0.8332960900859082,0.9940914096183874],"verdict":"Arriscado"},{"id":"ENG-4","title":"Triar alertas de segredos","category":"engineering","rows":30,"correct":29,"accuracy":0.9666666666666667,"ci":[0.8332960900859082,0.9940914096183874],"verdict":"Arriscado"},{"id":"ENG-5","title":"Associar uma diferença ao commit","category":"engineering","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"AGT-1","title":"Escolher a ferramenta certa","category":"agents","rows":36,"correct":35,"accuracy":0.9722222222222222,"ci":[0.8583028134672614,0.9950795928601897],"verdict":"Adequado"},{"id":"AGT-2","title":"Identificar um agente sequestrado","category":"agents","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"AGT-3","title":"Verificar se o agente concluiu o trabalho","category":"agents","rows":30,"correct":23,"accuracy":0.7666666666666667,"ci":[0.5907167384187784,0.8820761185551049],"verdict":"Não adequado"},{"id":"AGT-4","title":"Conferir uma resposta com suas fontes","category":"agents","rows":30,"correct":21,"accuracy":0.7,"ci":[0.5212421254128504,0.8333525173175619],"verdict":"Não adequado"},{"id":"AGT-5","title":"Escolher a melhor resposta","category":"agents","rows":28,"correct":26,"accuracy":0.9285714285714286,"ci":[0.7735463743160095,0.9801879358846942],"verdict":"Arriscado"},{"id":"SAF-1","title":"Detectar ataques de prompt","category":"safety","rows":30,"correct":29,"accuracy":0.9666666666666667,"ci":[0.8332960900859082,0.9940914096183874],"verdict":"Arriscado"},{"id":"SAF-2","title":"Identificar comentários tóxicos","category":"safety","rows":30,"correct":29,"accuracy":0.9666666666666667,"ci":[0.8332960900859082,0.9940914096183874],"verdict":"Arriscado"},{"id":"SUP-1","title":"Encaminhar uma reclamação","category":"support","rows":35,"correct":35,"accuracy":1,"ci":[0.9010990076755959,0.9999999999999999],"verdict":"Adequado"},{"id":"SUP-2","title":"Identificar o assunto de uma reclamação","category":"support","rows":32,"correct":30,"accuracy":0.9375,"ci":[0.7985287685584542,0.982689432968359],"verdict":"Arriscado"},{"id":"COM-1","title":"Avaliar relevância de busca","category":"commerce","rows":30,"correct":24,"accuracy":0.8,"ci":[0.6269430358685175,0.9049489282271013],"verdict":"Arriscado"},{"id":"COM-2","title":"Classificar um produto","category":"commerce","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"COM-3","title":"Classificar o setor de uma empresa","category":"commerce","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"FIN-1","title":"Classificar uma passagem de 10-K","category":"finance","rows":30,"correct":29,"accuracy":0.9666666666666667,"ci":[0.8332960900859082,0.9940914096183874],"verdict":"Arriscado"},{"id":"FIN-2","title":"Classificar um formulário 8-K","category":"finance","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"FIN-3","title":"Encontrar o total de um recibo","category":"finance","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"FIN-4","title":"Identificar um número reportado","category":"finance","rows":31,"correct":31,"accuracy":1,"ci":[0.889744604539564,1],"verdict":"Adequado"},{"id":"LEG-1","title":"Verificar uma afirmação sobre um NDA","category":"legal","rows":33,"correct":28,"accuracy":0.8484848484848485,"ci":[0.6908012411955788,0.9334954271839244],"verdict":"Arriscado"},{"id":"LEG-2","title":"Classificar uma cláusula contratual","category":"legal","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"LEG-3","title":"Identificar termos de serviço abusivos","category":"legal","rows":33,"correct":33,"accuracy":1,"ci":[0.895730002457548,1],"verdict":"Adequado"},{"id":"LEG-4","title":"Encontrar uma cláusula no contrato","category":"legal","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"PRD-1","title":"Prever a manchete vencedora","category":"product","rows":30,"correct":17,"accuracy":0.5666666666666667,"ci":[0.3919730700081361,0.7262251442353347],"verdict":"Não adequado"},{"id":"PRD-2","title":"Classificar uma atualização de versão","category":"product","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"DAT-1","title":"Escolher a consulta SQL correta","category":"data","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"DAT-2","title":"Responder a partir de uma tabela","category":"data","rows":30,"correct":29,"accuracy":0.9666666666666667,"ci":[0.8332960900859082,0.9940914096183874],"verdict":"Arriscado"},{"id":"DAT-3","title":"Conferir uma afirmação sobre um gráfico","category":"data","rows":32,"correct":32,"accuracy":1,"ci":[0.8928208017449293,1],"verdict":"Adequado"},{"id":"DAT-4","title":"Identificar o conteúdo de uma coluna","category":"data","rows":34,"correct":33,"accuracy":0.9705882352941176,"ci":[0.8508442670731406,0.9947890937237309],"verdict":"Adequado"},{"id":"DOC-1","title":"Identificar o tipo de documento","category":"documents","rows":30,"correct":30,"accuracy":1,"ci":[0.8864866068260312,0.9999999999999999],"verdict":"Adequado"},{"id":"DOC-2","title":"Identificar decisões e itens de ação","category":"documents","rows":30,"correct":21,"accuracy":0.7,"ci":[0.5212421254128504,0.8333525173175619],"verdict":"Não adequado"},{"id":"DOC-3","title":"Associar uma reunião ao resumo","category":"documents","rows":27,"correct":25,"accuracy":0.9259259259259259,"ci":[0.7663040731697686,0.9794453459390113],"verdict":"Arriscado"},{"id":"DSN-1","title":"Nomear um ícone","category":"design","rows":0,"correct":0,"accuracy":null,"ci":[0,0],"verdict":"Não avaliado"}],"failures":[{"title":"Questão de raciocínio MT-Bench · direção da sombra da manhã","url":"https://decisionbench.ai/row/agt-5-mtbench-q109-gpt-3.5-turbo-vs-vicuna-13b-v1.2","task":"Escolha a melhor resposta.","gold":"A: A resposta A é melhor.","prediction":"B","others":"10/12​​"},{"title":"Teste Upworthy · uma hashtag do Twitter após um massacre","url":"https://decisionbench.ai/row/prd-1-53860d3c92398a9dda00001b","task":"Preveja a manchete vencedora.","gold":"B: O pacote B teve uma taxa de cliques mais alta…","prediction":"UM","others":"10/12​​"},{"title":"Chamada de ferramenta · painéis de monitoramento","url":"https://decisionbench.ai/row/agt-1-live-multiple-1031-259-0","task":"Escolha a ferramenta certa","gold":"Obtenha um painel de controle personalizado","prediction":"nenhum","others":"9/12​​"},{"title":"Suporte ao cliente · varejo · devolução de purificador de ar","url":"https://decisionbench.ai/row/agt-3-retail-48-0","task":"Verifique se o agente concluiu o trabalho.","gold":"não concluído","prediction":"concluído","others":"9/12​​"},{"title":"Comentário de notícias · a relevância da mídia tradicional","url":"https://decisionbench.ai/row/saf-2-civil-360007","task":"Denunciar comentários tóxicos","gold":"não tóxico","prediction":"tóxico","others":"9/12​​"},{"title":"Teste Upworthy · professores americanizam o nome de uma criança mexicana","url":"https://decisionbench.ai/row/prd-1-53169523a16f78f2a000003e","task":"Preveja a manchete vencedora.","gold":"A: O pacote A teve uma taxa de cliques mais alta…","prediction":"B","others":"9/12​​"},{"title":"Coluna CSV · FiveThirtyEight college-majors/recent-grads.csv · coluna 4 de 21","url":"https://decisionbench.ai/row/dat-4-college-3","task":"Adivinhe o que cabe em uma coluna.","gold":"contagem ou medição","prediction":"dinheiro","others":"9/12​​"},{"title":"Conversa de suporte · varejo · cancelamento de um pedido não enviado","url":"https://decisionbench.ai/row/agt-3-retail-57-2","task":"Verifique se o agente concluiu o trabalho.","gold":"não concluído","prediction":"concluído","others":"8/12​​"},{"title":"Resposta da Wikipédia · Qual o teor alcoólico da sidra?","url":"https://decisionbench.ai/row/agt-4-hagrid-dev-1480-1","task":"Verifique uma resposta comparando-a com suas fontes.","gold":"não suportado","prediction":"apoiado","others":"8/12​​"},{"title":"Mensagem de bate-papo · um marcador de FIM e uma solicitação de verificação ortográfica","url":"https://decisionbench.ai/row/saf-1-deepset-test-3","task":"Capturar ataques rápidos","gold":"injeção","prediction":"benigno","others":"8/12​​"},{"title":"Resultado da pesquisa · “campo de golfe flutuante para lago”","url":"https://decisionbench.ai/row/com-1-esci-827519","task":"Relevância da pesquisa de notas","gold":"complemento","prediction":"irrelevante","others":"8/12​​"},{"title":"Teste Upworthy · a história do estigma das doenças mentais","url":"https://decisionbench.ai/row/prd-1-53da9dc4c8d9d17311000012","task":"Preveja a manchete vencedora.","gold":"A: O pacote A teve uma taxa de cliques mais alta…","prediction":"B","others":"8/12​​"},{"title":"Teste Upworthy · um mapa do consumo de energia por país","url":"https://decisionbench.ai/row/prd-1-541c816b7bc1ef895600002b","task":"Preveja a manchete vencedora.","gold":"B: O pacote B teve uma taxa de cliques mais alta…","prediction":"UM","others":"8/12​​"},{"title":"Teste Upworthy · um curta de animação sobre trabalhadores americanos","url":"https://decisionbench.ai/row/prd-1-545395482693bbcdc6000046","task":"Preveja a manchete vencedora.","gold":"A: O pacote A teve uma taxa de cliques mais alta…","prediction":"B","others":"8/12​​"}],"bins":[{"lo":0.3,"hi":0.4,"count":1,"confidence":0.38,"accuracy":1},{"lo":0.4,"hi":0.5,"count":6,"confidence":0.45666666666666667,"accuracy":0.5},{"lo":0.5,"hi":0.6,"count":31,"confidence":0.55,"accuracy":0.5806451612903226},{"lo":0.6,"hi":0.7,"count":38,"confidence":0.6507894736842106,"accuracy":0.7368421052631579},{"lo":0.7,"hi":0.8,"count":57,"confidence":0.7452631578947368,"accuracy":0.7368421052631579},{"lo":0.8,"hi":0.9,"count":72,"confidence":0.8505555555555555,"accuracy":0.875},{"lo":0.9,"hi":1,"count":836,"confidence":0.9901413658112223,"accuracy":0.9820574162679426}],"scores":[[1,1],[1,1],[0.85,1],[1,1],[1,1],[0.89,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.97,1],[0.97,1],[1,1],[1,1],[1,1],[0.9393939393939393,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.56,1],[1,1],[1,1],[0.86,1],[1,1],[0.92,1],[0.77,1],[1,1],[0.88,1],[0.91,1],[1,1],[0.51,1],[0.87,1],[0.44,0],[0.99,1],[1,1],[0.67,1],[1,1],[0.99,1],[0.99,1],[0.99,1],[1,1],[1,1],[0.95,1],[0.99,1],[1,1],[0.98,1],[0.71,1],[0.94,1],[0.9,1],[0.85,1],[0.92,1],[0.73,0],[0.97,1],[1,1],[0.87,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.98,1],[0.89,1],[1,1],[0.98,0],[1,1],[0.6,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[0.95,1],[0.81,1],[1,1],[1,1],[0.85,1],[1,1],[1,1],[0.81,1],[0.76,1],[0.48,1],[0.67,1],[0.73,1],[0.8,1],[0.79,1],[0.56,1],[0.99,1],[0.83,1],[0.96,1],[0.98,1],[1,1],[0.79,1],[1,1],[0.94,1],[0.76,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.93,0],[0.82,1],[0.6,1],[0.79,1],[0.92,1],[0.97,1],[0.81,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.78,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.98,1],[0.98,1],[1,1],[1,1],[1,1],[0.97,1],[0.9,0],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.99,1],[0.99,1],[1,1],[0.97,1],[0.99,1],[0.99,1],[1,1],[1,1],[0.99,1],[0.75,1],[1,1],[0.99,1],[1,1],[1,1],[0.85,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[0.99,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.72,1],[1,1],[0.99,1],[0.98,1],[0.99,1],[1,1],[0.52,1],[0.96,1],[0.92,1],[0.98,1],[0.98,1],[0.64,1],[0.99,1],[0.72,1],[0.93,1],[0.77,1],[0.72,0],[0.68,0],[0.71,1],[0.56,0],[0.7,1],[0.88,1],[0.96,1],[0.97,1],[0.75,1],[0.82,0],[0.71,0],[0.96,1],[0.6,0],[0.8,1],[0.63,1],[0.75,1],[0.67,1],[0.97,1],[0.75,0],[0.89,1],[1,1],[0.89,1],[0.88,1],[0.67,1],[0.99,1],[0.95,1],[0.94,1],[0.99,1],[0.98,1],[0.99,1],[0.98,1],[0.86,1],[0.76,1],[0.98,1],[1,1],[0.87,0],[0.9,1],[0.92,0],[0.56,1],[0.56,0],[1,1],[0.82,0],[0.9,0],[0.6,1],[0.92,1],[0.67,0],[0.73,0],[0.99,1],[0.6,0],[0.81,0],[0.58,1],[1,1],[0.65,0],[0.98,1],[0.96,1],[0.99,1],[1,1],[1,1],[0.98,1],[0.71,0],[0.86,1],[0.99,1],[0.99,1],[0.99,1],[1,1],[0.95,1],[0.53,1],[0.99,1],[0.98,1],[1,1],[1,1],[0.95,1],[0.99,1],[1,1],[0.88,1],[1,1],[0.97,1],[1,1],[0.93,1],[0.99,1],[0.73,1],[0.9,1],[0.98,1],[0.52,0],[0.99,1],[1,1],[1,1],[0.74,1],[0.95,1],[1,1],[0.99,1],[0.99,1],[0.98,1],[0.99,1],[0.99,1],[0.98,1],[0.8,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.46,1],[0.74,1],[1,1],[1,1],[0.81,1],[0.98,1],[1,1],[0.91,1],[0.71,1],[0.99,1],[0.99,1],[1,1],[0.93,1],[0.99,1],[0.98,1],[0.96,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.94,1],[1,1],[0.72,1],[0.87,1],[0.99,1],[0.58,0],[1,1],[1,1],[1,1],[1,1],[0.95,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.92,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[0.94,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.97,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.89,1],[1,1],[1,1],[0.94,1],[0.59,1],[0.98,1],[0.83,1],[1,1],[1,1],[0.97,1],[1,1],[0.98,1],[0.92,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.91,1],[1,1],[1,1],[1,1],[0.97,0],[0.73,0],[1,1],[1,1],[1,1],[1,1],[1,1],[0.84,1],[0.98,1],[0.68,1],[0.95,1],[0.99,1],[0.55,1],[0.74,0],[0.98,1],[0.76,1],[0.74,1],[0.67,0],[0.76,1],[0.87,1],[0.83,0],[0.9393939393939393,1],[0.84,1],[0.92,1],[1,1],[0.53,1],[0.86,1],[1,1],[0.9400000000000001,1],[0.85,1],[0.91,1],[0.88,0],[0.45,0],[0.66,1],[0.53,0],[0.68,1],[0.47,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.98,1],[1,1],[1,1],[0.97,1],[1,1],[0.76,1],[1,1],[0.91,1],[1,1],[1,1],[1,1],[1,1],[0.97,1],[0.99,1],[1,1],[0.9,1],[0.98,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.99,1],[0.97,1],[1,1],[1,1],[0.99,1],[0.99,1],[1,1],[0.97,1],[1,1],[1,1],[1,1],[0.64,1],[1,1],[1,1],[1,1],[0.79,1],[1,1],[1,1],[1,1],[0.98,0],[1,1],[0.99,1],[0.76,1],[1,1],[1,1],[0.86,1],[0.85,1],[1,1],[1,1],[0.95,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.99,1],[1,1],[0.85,1],[1,1],[0.95,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.91,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.91,1],[1,1],[1,1],[0.96,1],[0.9400000000000001,1],[0.97,1],[0.66,1],[1,1],[1,1],[0.98,0],[0.89,1],[0.87,0],[0.83,1],[1,1],[0.73,1],[1,1],[1,1],[0.77,1],[0.98,1],[1,1],[0.75,1],[1,1],[0.81,0],[0.8,1],[1,1],[0.89,1],[0.75,1],[0.75,1],[0.91,0],[0.95,1],[0.83,0],[0.99,1],[0.71,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.98,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.97,1],[0.87,1],[1,1],[0.95,1],[0.96,1],[0.88,1],[0.92,1],[1,1],[0.92,1],[0.92,1],[0.96,1],[0.38,1],[1,1],[0.69,1],[1,1],[1,1],[1,1],[0.97,1],[1,1],[1,1],[1,1],[0.88,1],[0.88,1],[0.91,1],[1,1],[1,1],[0.99,1],[1,1],[0.97,1],[0.89,1],[0.84,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.88,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.91,1],[1,1],[1,1],[0.99,1],[0.99,1],[1,1],[1,1],[0.99,1],[0.56,1],[0.99,1],[1,1],[0.53,1],[0.58,0],[0.76,1],[0.52,0],[0.64,1],[0.69,0],[0.69,1],[0.54,0],[0.58,0],[0.53,1],[0.53,0],[0.59,0],[0.57,1],[0.74,0],[0.83,1],[0.66,1],[0.57,0],[0.54,0],[0.77,1],[0.64,0],[0.65,1],[0.65,1],[0.8,1],[0.64,0],[0.63,1],[0.54,1],[0.73,1],[0.65,1],[0.61,0],[0.81,1],[1,1],[0.93,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[0.95,1],[1,1],[0.99,1],[0.99,1],[0.95,1],[0.69,1],[1,1],[0.8,1],[0.96,1],[0.98,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.98,1],[0.92,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.91,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.63,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.97,1],[1,1],[1,1],[1,1],[1,1],[0.98,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.71,0],[1,1],[0.99,1],[1,1],[1,1],[1,1],[0.97,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.97,1],[1,1],[0.97,1],[0.91,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.99,1],[0.44,0],[1,1],[0.96,1],[1,1],[0.97,1],[0.62,1],[1,1],[0.91,1],[1,1],[1,1],[1,1],[0.98,1],[1,1],[1,1],[0.68,1],[1,1],[1,1],[1,1],[0.93,1],[1,1],[1,1],[0.86,1],[1,1],[0.95,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[1,1],[0.92,1],[0.9,1],[0.96,1],[0.86,1],[1,1],[1,1],[1,1],[0.98,1],[0.93,1],[1,1],[0.99,1],[0.99,1],[0.96,0],[0.71,0],[0.87,1],[0.88,1],[0.99,1],[0.78,0],[0.78,1],[0.72,0],[0.99,1],[1,1],[0.9393939393939393,1],[0.98,0],[0.99,0],[0.57,1],[0.99,0],[0.74,0],[0.95,1],[0.98,0],[0.79,1],[0.92,1],[0.87,1],[0.87,1],[0.95,1],[0.98,1],[0.5,1],[0.79,1],[1,1],[1,1],[0.94,1],[0.9,1],[0.98,1],[0.99,1],[0.72,0],[0.86,1],[0.97,1],[0.95,1],[0.87,1],[0.82,1],[0.6900000000000001,1],[0.64,1],[0.56,1],[0.84,1],[0.74,1],[0.93,0],[0.83,1]],"files":{"metadata":"results/bench-v4/jev-1.13/metadata.json","predictions":"results/bench-v4/jev-1.13/predictions.jsonl","scores":"results/bench-v4/jev-1.13/scores.json","readme":"results/bench-v4/jev-1.13/README.md"},"request":{},"pricing":{"input_per_mtok":0.042,"output_per_mtok":0,"source_url":"https://docs.typesafe.ai/models","as_of":"2026-09","note":"Published input rate; output tokens are not billed."}}