{"data":[{"model":"Anthropic Claude Opus 4.5","Pass":0.9780658026,"validation_score":97.8065802592,"multi_turn_resistance":88.8412017167,"multi_turn_success":11.1587982833,"multi_turn_attacks":466,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":93.323890988,"source_type":"closed_source"},{"model":"Anthropic Claude Sonnet 4.5","Pass":0.9740777667,"validation_score":97.40777667,"multi_turn_resistance":87.0292887029,"multi_turn_success":12.9707112971,"multi_turn_attacks":478,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":92.2185326865,"source_type":"closed_source"},{"model":"Anthropic Claude Sonnet 4.6","Pass":0.9695912263,"validation_score":96.9591226321,"multi_turn_resistance":86.6379310345,"multi_turn_success":13.3620689655,"multi_turn_attacks":464,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":91.7985268333,"source_type":"closed_source"},{"model":"Anthropic Claude Haiku 4.5","Pass":0.9646061815,"validation_score":96.4606181456,"multi_turn_resistance":86.4693446089,"multi_turn_success":13.5306553911,"multi_turn_attacks":473,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":91.4649813772,"source_type":"closed_source"},{"model":"Anthropic Claude 3 Sonnet","Pass":0.9217347956,"validation_score":92.1734795613,"multi_turn_resistance":88.1355932203,"multi_turn_success":11.8644067797,"multi_turn_attacks":472,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":90.1545363908,"source_type":"closed_source"},{"model":"Anthropic Claude Opus 4.6","Pass":0.9636091725,"validation_score":96.3609172483,"multi_turn_resistance":83.7953091684,"multi_turn_success":16.2046908316,"multi_turn_attacks":469,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":90.0781132083,"source_type":"closed_source"},{"model":"Anthropic Claude Opus 4.7","Pass":0.9735792622,"validation_score":97.3579262213,"multi_turn_resistance":80.9725158562,"multi_turn_success":19.0274841438,"multi_turn_attacks":473,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":89.1652210388,"source_type":"closed_source"},{"model":"Openai Gpt 5.4 Mini","Pass":0.9042871386,"validation_score":90.4287138584,"multi_turn_resistance":87.8205128205,"multi_turn_success":12.1794871795,"multi_turn_attacks":468,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":89.1246133395,"source_type":"closed_source"},{"model":"Openai Gpt 5.4 Nano","Pass":0.9047856431,"validation_score":90.4785643071,"multi_turn_resistance":87.3931623932,"multi_turn_success":12.6068376068,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":88.9358633501,"source_type":"closed_source"},{"model":"Minimax Minimax M2.5","Pass":0.9047856431,"validation_score":90.4785643071,"multi_turn_resistance":84.7639484979,"multi_turn_success":15.2360515021,"multi_turn_attacks":466,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":87.6212564025,"source_type":"open_source"},{"model":"Openai Gpt 5.4","Pass":0.9725822532,"validation_score":97.258225324,"multi_turn_resistance":75.321888412,"multi_turn_success":24.678111588,"multi_turn_attacks":466,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":86.290056868,"source_type":"closed_source"},{"model":"Anthropic Claude Sonnet 5","Pass":0.9775672981,"validation_score":97.7567298106,"multi_turn_resistance":74.358974359,"multi_turn_success":25.641025641,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":86.0578520848,"source_type":"closed_source"},{"model":"Anthropic Claude 3.5 Sonnet","Pass":0.9670987039,"validation_score":96.7098703888,"multi_turn_resistance":75.161987041,"multi_turn_success":24.838012959,"multi_turn_attacks":463,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":85.9359287149,"source_type":"closed_source"},{"model":"Openai Gpt 5.2","Pass":0.9526420738,"validation_score":95.2642073779,"multi_turn_resistance":76.4957264957,"multi_turn_success":23.5042735043,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":85.8799669368,"source_type":"closed_source"},{"model":"Anthropic Claude Opus 4.1","Pass":0.9775672981,"validation_score":97.7567298106,"multi_turn_resistance":73.8853503185,"multi_turn_success":26.1146496815,"multi_turn_attacks":471,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":85.8210400645,"source_type":"closed_source"},{"model":"Openai Gpt 5 Nano","Pass":0.9247258225,"validation_score":92.4725822532,"multi_turn_resistance":78.2795698925,"multi_turn_success":21.7204301075,"multi_turn_attacks":465,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":85.3760760729,"source_type":"closed_source"},{"model":"Anthropic Claude 3 Haiku","Pass":0.7886340977,"validation_score":78.8634097707,"multi_turn_resistance":91.0256410256,"multi_turn_success":8.9743589744,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":84.9445253982,"source_type":"closed_source"},{"model":"Openai Gpt Oss 120b","Pass":0.9275506813,"validation_score":92.7550681289,"multi_turn_resistance":76.9230769231,"multi_turn_success":23.0769230769,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":84.839072526,"source_type":"open_source"},{"model":"Anthropic Claude Opus 4.8","Pass":0.9770687936,"validation_score":97.7068793619,"multi_turn_resistance":69.7624190065,"multi_turn_success":30.2375809935,"multi_turn_attacks":463,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":83.7346491842,"source_type":"closed_source"},{"model":"Anthropic Claude 3.5 Haiku","Pass":0.7926221336,"validation_score":79.2622133599,"multi_turn_resistance":87.8723404255,"multi_turn_success":12.1276595745,"multi_turn_attacks":470,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":83.5672768927,"source_type":"closed_source"},{"model":"Openai Gpt 5.5","Pass":0.9765702891,"validation_score":97.6570289133,"multi_turn_resistance":68.4665226782,"multi_turn_success":31.5334773218,"multi_turn_attacks":463,"multi_turn_conversations":96,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":83.0617757957,"source_type":"closed_source"},{"model":"Minimax Minimax M2.1","Pass":0.8140578265,"validation_score":81.405782652,"multi_turn_resistance":81.25,"multi_turn_success":18.75,"multi_turn_attacks":464,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":81.327891326,"source_type":"open_source"},{"model":"Openai Gpt 5.3 Chat","Pass":0.9566301097,"validation_score":95.6630109671,"multi_turn_resistance":65.1709401709,"multi_turn_success":34.8290598291,"multi_turn_attacks":468,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":80.416975569,"source_type":"closed_source"},{"model":"Openai Gpt 5.1 Chat","Pass":0.9636091725,"validation_score":96.3609172483,"multi_turn_resistance":63.9658848614,"multi_turn_success":36.0341151386,"multi_turn_attacks":469,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":80.1634010548,"source_type":"closed_source"},{"model":"Amazon Nova 2 Lite","Pass":0.6595214357,"validation_score":65.9521435693,"multi_turn_resistance":92.1108742004,"multi_turn_success":7.8891257996,"multi_turn_attacks":469,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":79.0315088849,"source_type":"closed_source"},{"model":"Anthropic Claude 3 Opus","Pass":0.9416749751,"validation_score":94.1674975075,"multi_turn_resistance":62.1276595745,"multi_turn_success":37.8723404255,"multi_turn_attacks":470,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":78.147578541,"source_type":"closed_source"},{"model":"Minimax Minimax M2","Pass":0.8195413759,"validation_score":81.9541375872,"multi_turn_resistance":69.1489361702,"multi_turn_success":30.8510638298,"multi_turn_attacks":470,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":75.5515368787,"source_type":"open_source"},{"model":"Openai Gpt 5","Pass":0.9192422732,"validation_score":91.924227318,"multi_turn_resistance":58.7606837607,"multi_turn_success":41.2393162393,"multi_turn_attacks":468,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":75.3424555394,"source_type":"closed_source"},{"model":"Openai Gpt Oss 20b","Pass":0.8582585577,"validation_score":85.825855766,"multi_turn_resistance":61.5384615385,"multi_turn_success":38.4615384615,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":73.6821586522,"source_type":"open_source"},{"model":"Openai Gpt Oss Safeguard 120b","Pass":0.8767032237,"validation_score":87.6703223662,"multi_turn_resistance":59.3617021277,"multi_turn_success":40.6382978723,"multi_turn_attacks":470,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":73.5160122469,"source_type":"open_source"},{"model":"Openai Gpt 5 Mini","Pass":0.9491525424,"validation_score":94.9152542373,"multi_turn_resistance":49.7890295359,"multi_turn_success":50.2109704641,"multi_turn_attacks":474,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":72.3521418866,"source_type":"closed_source"},{"model":"Anthropic Claude Sonnet 4","Pass":0.9690927218,"validation_score":96.9092721834,"multi_turn_resistance":42.2746781116,"multi_turn_success":57.7253218884,"multi_turn_attacks":466,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":69.5919751475,"source_type":"closed_source"},{"model":"Xai Grok 4.5","Pass":0.7701894317,"validation_score":77.0189431705,"multi_turn_resistance":62.0985010707,"multi_turn_success":37.9014989293,"multi_turn_attacks":467,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":69.5587221206,"source_type":"closed_source"},{"model":"Openai O4 Mini","Pass":0.8768693918,"validation_score":87.6869391825,"multi_turn_resistance":47.965738758,"multi_turn_success":52.034261242,"multi_turn_attacks":467,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":67.8263389702,"source_type":"closed_source"},{"model":"Xai Grok 4.1 Fast Reasoning","Pass":0.760219342,"validation_score":76.0219341974,"multi_turn_resistance":56.5315315315,"multi_turn_success":43.4684684685,"multi_turn_attacks":444,"multi_turn_conversations":100,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":66.2767328645,"source_type":"closed_source"},{"model":"Amazon Nova Premier","Pass":0.5967098704,"validation_score":59.6709870389,"multi_turn_resistance":69.8072805139,"multi_turn_success":30.1927194861,"multi_turn_attacks":467,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":64.7391337764,"source_type":"closed_source"},{"model":"Openai Gpt Oss Safeguard 20b","Pass":0.8245264207,"validation_score":82.4526420738,"multi_turn_resistance":46.3983050847,"multi_turn_success":53.6016949153,"multi_turn_attacks":472,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":64.4254735793,"source_type":"open_source"},{"model":"Xai Grok 4.3","Pass":0.6704885344,"validation_score":67.0488534397,"multi_turn_resistance":60.5995717345,"multi_turn_success":39.4004282655,"multi_turn_attacks":467,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":63.8242125871,"source_type":"closed_source"},{"model":"Anthropic Claude Opus 4","Pass":0.9526420738,"validation_score":95.2642073779,"multi_turn_resistance":32.1276595745,"multi_turn_success":67.8723404255,"multi_turn_attacks":470,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":63.6959334762,"source_type":"closed_source"},{"model":"Moonshot Kimi K2 Thinking","Pass":0.7941176471,"validation_score":79.4117647059,"multi_turn_resistance":46.4668094218,"multi_turn_success":53.5331905782,"multi_turn_attacks":467,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":62.9392870639,"source_type":"open_source"},{"model":"Moonshot Kimi K2.5","Pass":0.7587238285,"validation_score":75.8723828514,"multi_turn_resistance":47.2103004292,"multi_turn_success":52.7896995708,"multi_turn_attacks":466,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":61.5413416403,"source_type":"open_source"},{"model":"Amazon Nova Pro","Pass":0.4666001994,"validation_score":46.6600199402,"multi_turn_resistance":76.1802575107,"multi_turn_success":23.8197424893,"multi_turn_attacks":466,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":61.4201387255,"source_type":"closed_source"},{"model":"Meta Llama3 2 1B Instruct","Pass":0.7861415753,"validation_score":78.6141575274,"multi_turn_resistance":41.9491525424,"multi_turn_success":58.0508474576,"multi_turn_attacks":472,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":60.2816550349,"source_type":"open_source"},{"model":"Xai Grok 4","Pass":0.7821535394,"validation_score":78.2153539382,"multi_turn_resistance":34.6793349169,"multi_turn_success":65.3206650831,"multi_turn_attacks":421,"multi_turn_conversations":97,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":56.4473444275,"source_type":"closed_source"},{"model":"Google Gemini 3 Pro","Pass":0.8190428714,"validation_score":81.9042871386,"multi_turn_resistance":26.6524520256,"multi_turn_success":73.3475479744,"multi_turn_attacks":469,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":54.2783695821,"source_type":"closed_source"},{"model":"Amazon Nova Lite","Pass":0.3639082752,"validation_score":36.3908275174,"multi_turn_resistance":71.129707113,"multi_turn_success":28.870292887,"multi_turn_attacks":478,"multi_turn_conversations":99,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":53.7602673152,"source_type":"closed_source"},{"model":"Anthropic Claude 3.7 Sonnet","Pass":0.887337986,"validation_score":88.7337986042,"multi_turn_resistance":17.6220806794,"multi_turn_success":82.3779193206,"multi_turn_attacks":471,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":53.1779396418,"source_type":"closed_source"},{"model":"Amazon Nova Micro","Pass":0.3509471585,"validation_score":35.0947158524,"multi_turn_resistance":69.1489361702,"multi_turn_success":30.8510638298,"multi_turn_attacks":470,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":52.1218260113,"source_type":"closed_source"},{"model":"Xai Grok 4 Fast Reasoning","Pass":0.7632103689,"validation_score":76.3210368893,"multi_turn_resistance":25.5863539446,"multi_turn_success":74.4136460554,"multi_turn_attacks":469,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":50.9536954169,"source_type":"closed_source"},{"model":"Xai Grok 4.20 Non Reasoning","Pass":0.8025922233,"validation_score":80.259222333,"multi_turn_resistance":21.3675213675,"multi_turn_success":78.6324786325,"multi_turn_attacks":468,"multi_turn_conversations":98,"has_validation_data":true,"has_multi_turn_data":true,"combined_score":50.8133718503,"source_type":"closed_source"}],"pagination":{"total":107,"limit":50,"offset":0,"has_more":true}}