{"results":[{"rank":1,"model":"gpt-6-sol","reasoning":"xhigh","modelId":"openai/gpt-6-sol","score":40.90706288844849,"recall":35.775862068965516,"precision":95.95959595959596,"issuesFound":83,"issuesTotal":232,"falsePositives":4,"cost":12.7626561,"totalTimeSeconds":4148.965,"totalTokens":1716842,"tokens":"1.7M","harness":"codex"},{"rank":2,"model":"gpt-6-astra","reasoning":"xhigh","modelId":"openai/gpt-6-astra","score":37.78838504375497,"recall":32.758620689655174,"precision":97.9381443298969,"issuesFound":76,"issuesTotal":232,"falsePositives":2,"cost":63.70032,"totalTimeSeconds":2986.861,"totalTokens":1683939,"tokens":"1.7M","harness":"codex"},{"rank":3,"model":"gpt-5.6-sol","reasoning":"xhigh","modelId":"openai/gpt-5.6-sol","score":35.4374092511927,"recall":30.603448275862068,"precision":96.25,"issuesFound":71,"issuesTotal":232,"falsePositives":3,"cost":55.977321,"totalTimeSeconds":13142.174,"totalTokens":2274882,"tokens":"2.3M","harness":"codex"},{"rank":4,"model":"claude-opus-5","reasoning":"max","modelId":"anthropic/claude-opus-5","score":32.43823404749859,"recall":28.01724137931034,"precision":87.95180722891565,"issuesFound":65,"issuesTotal":232,"falsePositives":10,"cost":127.92943925,"totalTimeSeconds":9259.06,"totalTokens":4453699,"tokens":"4.5M","harness":"claude"},{"rank":5,"model":"gpt-6-astra","reasoning":"medium","modelId":"openai/gpt-6-astra","score":29.330889092575617,"recall":25,"precision":95.52238805970148,"issuesFound":58,"issuesTotal":232,"falsePositives":3,"cost":35.2024904,"totalTimeSeconds":1309.273,"totalTokens":972966,"tokens":"973.0K","harness":"codex"},{"rank":6,"model":"gpt-6-sol","reasoning":"medium","modelId":"openai/gpt-6-sol","score":29.305680793507666,"recall":25,"precision":94.20289855072464,"issuesFound":58,"issuesTotal":232,"falsePositives":4,"cost":12.0458051,"totalTimeSeconds":1688.28,"totalTokens":932113,"tokens":"932.1K","harness":"codex"},{"rank":7,"model":"claude-opus-5","reasoning":"medium","modelId":"anthropic/claude-opus-5","score":28.24849725028776,"recall":24.568965517241377,"precision":70.45454545454545,"issuesFound":57,"issuesTotal":232,"falsePositives":26,"cost":31.9572995,"totalTimeSeconds":2821.091,"totalTokens":999742,"tokens":"999.7K","harness":"claude"},{"rank":8,"model":"gpt-5.6-luna","reasoning":"xhigh","modelId":"openai/gpt-5.6-luna","score":26.67865168539326,"recall":22.844827586206897,"precision":81.15942028985508,"issuesFound":53,"issuesTotal":232,"falsePositives":13,"cost":24.58934445,"totalTimeSeconds":10899.621,"totalTokens":3343404,"tokens":"3.3M","harness":"codex"},{"rank":9,"model":"claude-opus-5.5","reasoning":"max","modelId":"anthropic/claude-opus-5.5","score":26.675474606395195,"recall":22.844827586206897,"precision":81.0126582278481,"issuesFound":53,"issuesTotal":232,"falsePositives":15,"cost":40.3115366,"totalTimeSeconds":13867.504,"totalTokens":1175065,"tokens":"1.2M","harness":"claude"},{"rank":10,"model":"gpt-5.6-sol","reasoning":"medium","modelId":"openai/gpt-5.6-sol","score":25.00153070596159,"recall":21.120689655172413,"precision":94.33962264150944,"issuesFound":49,"issuesTotal":232,"falsePositives":3,"cost":17.9499475,"totalTimeSeconds":1851.869,"totalTokens":703048,"tokens":"703.0K","harness":"codex"},{"rank":11,"model":"glm-5.3","reasoning":"high","modelId":"zai/glm-5.3","score":21.910099913600217,"recall":18.53448275862069,"precision":80.7017543859649,"issuesFound":43,"issuesTotal":232,"falsePositives":11,"cost":16.21793418,"totalTimeSeconds":7537.177,"totalTokens":1232142,"tokens":"1.2M","harness":"pi"},{"rank":12,"model":"gpt-5.5","reasoning":"xhigh","modelId":"openai/gpt-5.5","score":21.113290828837663,"recall":17.67241379310345,"precision":95.45454545454545,"issuesFound":41,"issuesTotal":232,"falsePositives":2,"cost":43.422859,"totalTimeSeconds":8577.362,"totalTokens":2158830,"tokens":"2.2M","harness":"codex"},{"rank":13,"model":"gpt-6-luna","reasoning":"xhigh","modelId":"openai/gpt-6-luna","score":21.052254489873903,"recall":17.67241379310345,"precision":89.58333333333334,"issuesFound":41,"issuesTotal":232,"falsePositives":5,"cost":0.508593415,"totalTimeSeconds":3636.329,"totalTokens":1423488,"tokens":"1.4M","harness":"codex"},{"rank":14,"model":"glm-5.3","reasoning":"max","modelId":"zai/glm-5.3","score":20.39395145244728,"recall":17.24137931034483,"precision":75.92592592592592,"issuesFound":40,"issuesTotal":232,"falsePositives":13,"cost":14.60052385,"totalTimeSeconds":5374.419,"totalTokens":1241823,"tokens":"1.2M","harness":"pi"},{"rank":15,"model":"gpt-5.6-terra","reasoning":"xhigh","modelId":"openai/gpt-5.6-terra","score":19.135195136103334,"recall":15.948275862068966,"precision":95.34883720930233,"issuesFound":37,"issuesTotal":232,"falsePositives":2,"cost":27.80705975,"totalTimeSeconds":6332.109,"totalTokens":2108744,"tokens":"2.1M","harness":"codex"},{"rank":16,"model":"kimi-k3","reasoning":"xhigh","modelId":"moonshotai/kimi-k3","score":17.48776690391459,"recall":14.655172413793101,"precision":77.08333333333334,"issuesFound":34,"issuesTotal":232,"falsePositives":11,"cost":12.37509965,"totalTimeSeconds":7178.909,"totalTokens":731913,"tokens":"731.9K","harness":"pi"},{"rank":17,"model":"claude-sonnet-5","reasoning":"max","modelId":"anthropic/claude-sonnet-5","score":16.98629331137126,"recall":14.224137931034484,"precision":76.08695652173914,"issuesFound":33,"issuesTotal":232,"falsePositives":11,"cost":45.1699711,"totalTimeSeconds":11300.283,"totalTokens":4601814,"tokens":"4.6M","harness":"claude"},{"rank":18,"model":"deepseek-v4-flash","reasoning":"xhigh","modelId":"deepseek/deepseek-v4-flash","score":16.47373107747106,"recall":13.793103448275861,"precision":74,"issuesFound":32,"issuesTotal":232,"falsePositives":13,"cost":5.9404634588,"totalTimeSeconds":4688.823,"totalTokens":1480960,"tokens":"1.5M","harness":"pi"},{"rank":19,"model":"qwen3.8-max","reasoning":"xhigh","modelId":"alibaba/qwen3.8-max","score":16.472868217054263,"recall":13.793103448275861,"precision":73.91304347826086,"issuesFound":32,"issuesTotal":232,"falsePositives":12,"cost":6.330858,"totalTimeSeconds":6739.89,"totalTokens":342592,"tokens":"342.6K","harness":"pi"},{"rank":20,"model":"grok-4.5","reasoning":"medium","modelId":"xai/grok-4.5","score":16.46706586826347,"recall":13.793103448275861,"precision":73.33333333333333,"issuesFound":32,"issuesTotal":232,"falsePositives":12,"cost":11.0445542,"totalTimeSeconds":5853.412,"totalTokens":909637,"tokens":"909.6K","harness":"pi"},{"rank":21,"model":"grok-4.6","reasoning":"xhigh","modelId":"xai/grok-4.6","score":16.162669447340978,"recall":13.36206896551724,"precision":100,"issuesFound":31,"issuesTotal":232,"falsePositives":0,"cost":22.291042,"totalTimeSeconds":14556.027,"totalTokens":3456369,"tokens":"3.5M","harness":"pi"},{"rank":22,"model":"qwen3.8-max","reasoning":"medium","modelId":"alibaba/qwen3.8-max","score":15.527950310559007,"recall":12.931034482758621,"precision":78.94736842105263,"issuesFound":30,"issuesTotal":232,"falsePositives":8,"cost":6.219504,"totalTimeSeconds":7412.953,"totalTokens":383408,"tokens":"383.4K","harness":"pi"},{"rank":23,"model":"grok-4.5","reasoning":"xhigh","modelId":"xai/grok-4.5","score":15.518770322199233,"recall":12.931034482758621,"precision":77.77777777777779,"issuesFound":30,"issuesTotal":232,"falsePositives":10,"cost":5.6020852,"totalTimeSeconds":5057.093,"totalTokens":1010476,"tokens":"1.0M","harness":"pi"},{"rank":24,"model":"deepseek-v4-flash","reasoning":"medium","modelId":"deepseek/deepseek-v4-flash","score":15.416238437821173,"recall":12.931034482758621,"precision":66.66666666666666,"issuesFound":30,"issuesTotal":232,"falsePositives":16,"cost":5.0621898232,"totalTimeSeconds":4875.954,"totalTokens":1422508,"tokens":"1.4M","harness":"pi"},{"rank":25,"model":"gpt-6-luna","reasoning":"medium","modelId":"openai/gpt-6-luna","score":13.584117032392895,"recall":11.206896551724139,"precision":89.65517241379311,"issuesFound":26,"issuesTotal":232,"falsePositives":3,"cost":1.753570525,"totalTimeSeconds":1495.953,"totalTokens":873505,"tokens":"873.5K","harness":"codex"},{"rank":26,"model":"glm-5.3-flash","reasoning":"high","modelId":"zai/glm-5.3-flash","score":12.981767828294483,"recall":10.822510822510822,"precision":64.28571428571429,"issuesFound":25,"issuesTotal":231,"falsePositives":15,"cost":0.3543498,"totalTimeSeconds":1281.431,"totalTokens":1264649,"tokens":"1.3M","harness":"pi"},{"rank":27,"model":"gpt-5.5","reasoning":"medium","modelId":"openai/gpt-5.5","score":12.578616352201257,"recall":10.344827586206897,"precision":92.3076923076923,"issuesFound":24,"issuesTotal":232,"falsePositives":2,"cost":14.941307,"totalTimeSeconds":1445.28,"totalTokens":751439,"tokens":"751.4K","harness":"codex"},{"rank":28,"model":"gpt-5.6-terra","reasoning":"medium","modelId":"openai/gpt-5.6-terra","score":12.067156348373558,"recall":9.913793103448276,"precision":92,"issuesFound":23,"issuesTotal":232,"falsePositives":2,"cost":5.14664175,"totalTimeSeconds":795.22,"totalTokens":617655,"tokens":"617.7K","harness":"codex"},{"rank":29,"model":"gpt-5.6-luna","reasoning":"medium","modelId":"openai/gpt-5.6-luna","score":12.03191071973495,"recall":9.913793103448276,"precision":82.75862068965517,"issuesFound":23,"issuesTotal":232,"falsePositives":5,"cost":5.2303598,"totalTimeSeconds":719.251,"totalTokens":572011,"tokens":"572.0K","harness":"codex"},{"rank":30,"model":"gemini-3.6-flash","reasoning":"medium","modelId":"google/gemini-3.6-flash","score":11.512297226582941,"recall":9.482758620689655,"precision":80,"issuesFound":22,"issuesTotal":232,"falsePositives":6,"cost":10.74136315,"totalTimeSeconds":1580.574,"totalTokens":2730747,"tokens":"2.7M","harness":"pi"},{"rank":31,"model":"kimi-k3","reasoning":"medium","modelId":"moonshotai/kimi-k3","score":11.430709119627569,"recall":9.482758620689655,"precision":64.1025641025641,"issuesFound":22,"issuesTotal":232,"falsePositives":14,"cost":10.84387065,"totalTimeSeconds":5355.958,"totalTokens":676615,"tokens":"676.6K","harness":"pi"},{"rank":32,"model":"glm-5.3-flash","reasoning":"max","modelId":"zai/glm-5.3-flash","score":10.964912280701755,"recall":9.090909090909092,"precision":62.5,"issuesFound":21,"issuesTotal":231,"falsePositives":15,"cost":1.82886845,"totalTimeSeconds":2464.336,"totalTokens":1598368,"tokens":"1.6M","harness":"pi"},{"rank":33,"model":"grok-4.7","reasoning":"xhigh","modelId":"spacexai/grok-4.7","score":10.932323710364411,"recall":9.051724137931034,"precision":64.70588235294117,"issuesFound":21,"issuesTotal":232,"falsePositives":12,"cost":13.2787114,"totalTimeSeconds":2543.235,"totalTokens":1703425,"tokens":"1.7M","harness":"pi"},{"rank":34,"model":"glm-5.2","reasoning":"medium","modelId":"zai/glm-5.2","score":10.416666666666666,"recall":8.620689655172415,"precision":62.5,"issuesFound":20,"issuesTotal":232,"falsePositives":12,"cost":11.08801345,"totalTimeSeconds":3818.193,"totalTokens":1498943,"tokens":"1.5M","harness":"pi"},{"rank":35,"model":"claude-opus-5.5","reasoning":"medium","modelId":"anthropic/claude-opus-5.5","score":9.989484752891693,"recall":8.189655172413794,"precision":82.6086956521739,"issuesFound":19,"issuesTotal":232,"falsePositives":4,"cost":7.3206714,"totalTimeSeconds":421.351,"totalTokens":37979,"tokens":"38.0K","harness":"claude"},{"rank":36,"model":"glm-5.2","reasoning":"xhigh","modelId":"zai/glm-5.2","score":9.862079193237433,"recall":8.189655172413794,"precision":53.84615384615385,"issuesFound":19,"issuesTotal":232,"falsePositives":18,"cost":51.8419396,"totalTimeSeconds":9044.302,"totalTokens":4727558,"tokens":"4.7M","harness":"pi"},{"rank":37,"model":"gemini-3.6-flash","reasoning":"xhigh","modelId":"google/gemini-3.6-flash","score":8.947368421052632,"recall":7.327586206896551,"precision":77.27272727272727,"issuesFound":17,"issuesTotal":232,"falsePositives":5,"cost":5.3306856,"totalTimeSeconds":1338.207,"totalTokens":1822407,"tokens":"1.8M","harness":"pi"},{"rank":38,"model":"grok-4.7","reasoning":"medium","modelId":"spacexai/grok-4.7","score":7.8441626356386465,"recall":6.4655172413793105,"precision":53.333333333333336,"issuesFound":15,"issuesTotal":232,"falsePositives":14,"cost":3.967042,"totalTimeSeconds":1287.974,"totalTokens":904541,"tokens":"904.5K","harness":"pi"},{"rank":39,"model":"claude-opus-4.8","reasoning":"max","modelId":"anthropic/claude-opus-4.8","score":6.885593220338984,"recall":5.603448275862069,"precision":81.25,"issuesFound":13,"issuesTotal":232,"falsePositives":3,"cost":7.56051025,"totalTimeSeconds":1168.541,"totalTokens":80840,"tokens":"80.8K","harness":"claude"},{"rank":40,"model":"claude-opus-4.8","reasoning":"medium","modelId":"anthropic/claude-opus-4.8","score":6.849315068493151,"recall":5.603448275862069,"precision":61.904761904761905,"issuesFound":13,"issuesTotal":232,"falsePositives":8,"cost":10.80563125,"totalTimeSeconds":1096.478,"totalTokens":78060,"tokens":"78.1K","harness":"claude"},{"rank":41,"model":"inkling","reasoning":"xhigh","modelId":"thinkingmachines/inkling","score":6.295907660020987,"recall":5.172413793103448,"precision":48,"issuesFound":12,"issuesTotal":232,"falsePositives":13,"cost":1.92991144,"totalTimeSeconds":694.398,"totalTokens":300894,"tokens":"300.9K","harness":"pi"},{"rank":42,"model":"claude-sonnet-5","reasoning":"medium","modelId":"anthropic/claude-sonnet-5","score":5.813953488372093,"recall":4.741379310344827,"precision":61.111111111111114,"issuesFound":11,"issuesTotal":232,"falsePositives":7,"cost":6.65526365,"totalTimeSeconds":947.373,"totalTokens":442155,"tokens":"442.2K","harness":"claude"},{"rank":43,"model":"inkling","reasoning":"medium","modelId":"thinkingmachines/inkling","score":5.2356020942408374,"recall":4.310344827586207,"precision":37.03703703703704,"issuesFound":10,"issuesTotal":232,"falsePositives":17,"cost":2.1764797,"totalTimeSeconds":631.231,"totalTokens":508959,"tokens":"509.0K","harness":"pi"},{"rank":44,"model":"claude-haiku-4.5","reasoning":"default","modelId":"anthropic/claude-haiku-4.5","score":4.712041884816754,"recall":3.8793103448275863,"precision":33.33333333333333,"issuesFound":9,"issuesTotal":232,"falsePositives":18,"cost":5.91296485,"totalTimeSeconds":1780.469,"totalTokens":912363,"tokens":"912.4K","harness":"claude"},{"rank":45,"model":"gemini-3.5-flash-lite","reasoning":"medium","modelId":"google/gemini-3.5-flash-lite","score":2.134471718249733,"recall":1.7241379310344827,"precision":44.44444444444444,"issuesFound":4,"issuesTotal":232,"falsePositives":5,"cost":0.58244988,"totalTimeSeconds":105.902,"totalTokens":459925,"tokens":"459.9K","harness":"pi"},{"rank":46,"model":"gemini-3.5-flash-lite","reasoning":"xhigh","modelId":"google/gemini-3.5-flash-lite","score":1.0695187165775402,"recall":0.8620689655172413,"precision":28.57142857142857,"issuesFound":2,"issuesTotal":232,"falsePositives":5,"cost":0.17540406,"totalTimeSeconds":67.116,"totalTokens":406521,"tokens":"406.5K","harness":"pi"}]}