{"schema":"xor.bench.manifest/1","generatedAt":"2026-08-25","generator":"bin/gen-bench-manifest.mjs","corpus":{"version":"cve-bench-136","recordDate":"2026-02-22","scoredRecords":1864,"samples":128,"models":15,"weaknessClasses":10,"samplesWithoutWeaknessClass":44},"stages":{"published":["patch"],"declaredNotPublished":["finding","exploit"]},"oracle":{"reachableSamples":103,"totalSamples":128,"reachableShare":80.5,"unreachableSamples":25,"greedyCover":[{"model":"cursor-opus-4.6","newlyCovered":80,"cumulativeCovered":80,"cumulativeShare":62.5},{"model":"codex-gpt-5.2","newlyCovered":16,"cumulativeCovered":96,"cumulativeShare":75},{"model":"codex-gpt-5.2-codex","newlyCovered":3,"cumulativeCovered":99,"cumulativeShare":77.3},{"model":"opencode-gemini-gemini-3.1-pro-preview","newlyCovered":2,"cumulativeCovered":101,"cumulativeShare":78.9},{"model":"claude-claude-opus-4-5","newlyCovered":1,"cumulativeCovered":102,"cumulativeShare":79.7},{"model":"opencode-gpt-5.2-codex","newlyCovered":1,"cumulativeCovered":103,"cumulativeShare":80.5}]},"byModel":{"claude-claude-opus-4-5":{"n":127,"pass":58,"fail":43,"build":26,"rate":45.7,"ci":{"low":33.1,"high":55.5},"clusterCount":39,"costPerPassUsd":2.46,"costPerEvalUsd":1.1252,"costMeasuredShare":0.9,"costCoverage":1},"claude-claude-opus-4-6":{"n":125,"pass":77,"fail":28,"build":20,"rate":61.6,"ci":{"low":48.9,"high":71.3},"clusterCount":39,"costPerPassUsd":2.69,"costPerEvalUsd":1.6571,"costMeasuredShare":0.98,"costCoverage":1},"codex-gpt-5.2":{"n":126,"pass":79,"fail":12,"build":35,"rate":62.7,"ci":{"low":51.9,"high":71.5},"clusterCount":38,"costPerPassUsd":4.91,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"codex-gpt-5.2-codex":{"n":128,"pass":63,"fail":27,"build":38,"rate":49.2,"ci":{"low":35.9,"high":59.8},"clusterCount":39,"costPerPassUsd":6.26,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"cursor-composer-1.5":{"n":126,"pass":57,"fail":39,"build":30,"rate":45.2,"ci":{"low":32.5,"high":58},"clusterCount":39,"costPerPassUsd":3.87,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"cursor-gpt-5.2":{"n":122,"pass":63,"fail":34,"build":25,"rate":51.6,"ci":{"low":38.1,"high":63.6},"clusterCount":37,"costPerPassUsd":5.96,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"cursor-gpt-5.3-codex":{"n":127,"pass":64,"fail":40,"build":23,"rate":50.4,"ci":{"low":36.2,"high":61.2},"clusterCount":39,"costPerPassUsd":6.11,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"cursor-opus-4.6":{"n":128,"pass":80,"fail":24,"build":24,"rate":62.5,"ci":{"low":50.7,"high":71.9},"clusterCount":39,"costPerPassUsd":35.4,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"gemini-gemini-3-pro-preview":{"n":128,"pass":55,"fail":36,"build":37,"rate":43,"ci":{"low":32.8,"high":52.1},"clusterCount":39,"costPerPassUsd":4.56,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"gemini31-gemini-3.1-pro-preview":{"n":109,"pass":64,"fail":18,"build":27,"rate":58.7,"ci":{"low":44,"high":71.2},"clusterCount":35,"costPerPassUsd":3.34,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"opencode-claude-opus-4-5":{"n":125,"pass":46,"fail":29,"build":50,"rate":36.8,"ci":{"low":25,"high":48.5},"clusterCount":39,"costPerPassUsd":36.89,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"opencode-claude-opus-4-6":{"n":122,"pass":58,"fail":15,"build":49,"rate":47.5,"ci":{"low":32,"high":59.7},"clusterCount":39,"costPerPassUsd":46.54,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"opencode-gemini-gemini-3.1-pro-preview":{"n":122,"pass":67,"fail":25,"build":30,"rate":54.9,"ci":{"low":42.9,"high":66.7},"clusterCount":38,"costPerPassUsd":5.54,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"opencode-gpt-5.2":{"n":122,"pass":63,"fail":11,"build":48,"rate":51.6,"ci":{"low":39.5,"high":63.1},"clusterCount":37,"costPerPassUsd":5.96,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"opencode-gpt-5.2-codex":{"n":127,"pass":48,"fail":32,"build":47,"rate":37.8,"ci":{"low":25,"high":48.7},"clusterCount":39,"costPerPassUsd":8.15,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}},"byWeaknessClass":{"CWE-787":{"n":247,"pass":137,"fail":52,"build":58,"rate":55.5,"ci":{"low":40.3,"high":73},"clusterCount":14,"costPerPassUsd":10.53,"costPerEvalUsd":5.8402,"costMeasuredShare":0.13,"costCoverage":1},"CWE-125":{"n":1101,"pass":630,"fail":222,"build":249,"rate":57.2,"ci":{"low":43.9,"high":66.4},"clusterCount":32,"costPerPassUsd":10.3,"costPerEvalUsd":5.8966,"costMeasuredShare":0.13,"costCoverage":1},"CWE-1284":{"n":29,"pass":13,"fail":1,"build":15,"rate":44.8,"ci":{"low":0,"high":86.7},"clusterCount":2,"costPerPassUsd":13.1,"costPerEvalUsd":5.8741,"costMeasuredShare":0.14,"costCoverage":1},"CWE-843":{"n":29,"pass":10,"fail":0,"build":19,"rate":34.5,"ci":{"low":0,"high":66.7},"clusterCount":2,"costPerPassUsd":17.08,"costPerEvalUsd":5.8906,"costMeasuredShare":0.14,"costCoverage":1},"CWE-416":{"n":186,"pass":59,"fail":41,"build":86,"rate":31.7,"ci":{"low":13.2,"high":57.5},"clusterCount":8,"costPerPassUsd":18.19,"costPerEvalUsd":5.7714,"costMeasuredShare":0.11,"costCoverage":1},"CWE-475":{"n":15,"pass":6,"fail":1,"build":8,"rate":40,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":14.44,"costPerEvalUsd":5.7762,"costMeasuredShare":0.07,"costCoverage":1},"CWE-476":{"n":29,"pass":7,"fail":15,"build":7,"rate":24.1,"ci":{"low":14.3,"high":33.3},"clusterCount":2,"costPerPassUsd":23.64,"costPerEvalUsd":5.7051,"costMeasuredShare":0.1,"costCoverage":1},"CWE-908":{"n":126,"pass":28,"fail":72,"build":26,"rate":22.2,"ci":{"low":8,"high":50.6},"clusterCount":6,"costPerPassUsd":27.03,"costPerEvalUsd":6.0067,"costMeasuredShare":0.13,"costCoverage":1},"CWE-562":{"n":15,"pass":4,"fail":2,"build":9,"rate":26.7,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":22.25,"costPerEvalUsd":5.9343,"costMeasuredShare":0.13,"costCoverage":1},"CWE-415":{"n":43,"pass":23,"fail":4,"build":16,"rate":53.5,"ci":{"low":0,"high":80},"clusterCount":3,"costPerPassUsd":11.3,"costPerEvalUsd":6.0467,"costMeasuredShare":0.12,"costCoverage":1}},"byModelWeaknessClass":{"claude-claude-opus-4-5":{"CWE-787":{"n":17,"pass":8,"fail":7,"build":2,"rate":47.1,"ci":{"low":25,"high":73.3},"clusterCount":14,"costPerPassUsd":3.22,"costPerEvalUsd":1.5149,"costMeasuredShare":0.94,"costCoverage":1},"CWE-125":{"n":75,"pass":40,"fail":23,"build":12,"rate":53.3,"ci":{"low":37.3,"high":64.4},"clusterCount":32,"costPerPassUsd":2.07,"costPerEvalUsd":1.1016,"costMeasuredShare":0.92,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":1.51,"costPerEvalUsd":0.7527,"costMeasuredShare":1,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":2.26,"costPerEvalUsd":1.1324,"costMeasuredShare":1,"costCoverage":1},"CWE-416":{"n":13,"pass":4,"fail":4,"build":5,"rate":30.8,"ci":{"low":5,"high":66.7},"clusterCount":8,"costPerPassUsd":3.54,"costPerEvalUsd":1.0884,"costMeasuredShare":0.77,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":1.1252,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":1,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":1.1179,"costMeasuredShare":0.5,"costCoverage":1},"CWE-908":{"n":8,"pass":1,"fail":5,"build":2,"rate":12.5,"ci":{"low":null,"high":null},"clusterCount":5,"costPerPassUsd":5.98,"costPerEvalUsd":0.7478,"costMeasuredShare":1,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":1,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":0.4612,"costMeasuredShare":1,"costCoverage":1},"CWE-415":{"n":3,"pass":1,"fail":1,"build":1,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":3.62,"costPerEvalUsd":1.2052,"costMeasuredShare":0.67,"costCoverage":1}},"claude-claude-opus-4-6":{"CWE-125":{"n":75,"pass":52,"fail":13,"build":10,"rate":69.3,"ci":{"low":52.9,"high":81},"clusterCount":32,"costPerPassUsd":2,"costPerEvalUsd":1.3841,"costMeasuredShare":0.97,"costCoverage":1},"CWE-787":{"n":16,"pass":8,"fail":6,"build":2,"rate":50,"ci":{"low":27.8,"high":73.3},"clusterCount":13,"costPerPassUsd":3.75,"costPerEvalUsd":1.8762,"costMeasuredShare":1,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":0.77,"costPerEvalUsd":0.3872,"costMeasuredShare":1,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":1.61,"costPerEvalUsd":0.8056,"costMeasuredShare":1,"costCoverage":1},"CWE-475":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":0.5,"costPerEvalUsd":0.5034,"costMeasuredShare":1,"costCoverage":1},"CWE-476":{"n":2,"pass":1,"fail":1,"build":0,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.76,"costPerEvalUsd":3.3781,"costMeasuredShare":1,"costCoverage":1},"CWE-908":{"n":9,"pass":1,"fail":7,"build":1,"rate":11.1,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":34.26,"costPerEvalUsd":3.8068,"costMeasuredShare":1,"costCoverage":1},"CWE-562":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":3.54,"costPerEvalUsd":3.5379,"costMeasuredShare":1,"costCoverage":1},"CWE-416":{"n":11,"pass":7,"fail":1,"build":3,"rate":63.6,"ci":{"low":25,"high":100},"clusterCount":6,"costPerPassUsd":1.8,"costPerEvalUsd":1.1471,"costMeasuredShare":0.91,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":3.19,"costPerEvalUsd":2.1298,"costMeasuredShare":1,"costCoverage":1}},"codex-gpt-5.2":{"CWE-787":{"n":16,"pass":12,"fail":0,"build":4,"rate":75,"ci":{"low":52.6,"high":100},"clusterCount":13,"costPerPassUsd":4.11,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":74,"pass":52,"fail":6,"build":16,"rate":70.3,"ci":{"low":57.1,"high":79.2},"clusterCount":31,"costPerPassUsd":4.38,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":4,"fail":1,"build":8,"rate":30.8,"ci":{"low":12.5,"high":50},"clusterCount":8,"costPerPassUsd":10.01,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":2,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":3.08,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":2,"fail":5,"build":2,"rate":22.2,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":13.86,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":3.08,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":4.62,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}},"codex-gpt-5.2-codex":{"CWE-787":{"n":17,"pass":11,"fail":2,"build":4,"rate":64.7,"ci":{"low":38.9,"high":88.2},"clusterCount":14,"costPerPassUsd":4.76,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":75,"pass":42,"fail":17,"build":16,"rate":56,"ci":{"low":41,"high":66.3},"clusterCount":32,"costPerPassUsd":5.5,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":2,"fail":4,"build":7,"rate":15.4,"ci":{"low":0,"high":40},"clusterCount":8,"costPerPassUsd":20.02,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":3.08,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":1,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":2,"fail":3,"build":4,"rate":22.2,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":13.86,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":1,"fail":0,"build":2,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":9.24,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}},"cursor-composer-1.5":{"CWE-787":{"n":17,"pass":10,"fail":5,"build":2,"rate":58.8,"ci":{"low":40,"high":80},"clusterCount":14,"costPerPassUsd":2.98,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":73,"pass":39,"fail":19,"build":15,"rate":53.4,"ci":{"low":38.6,"high":65.8},"clusterCount":31,"costPerPassUsd":3.28,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":3.5,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":3.5,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":2,"fail":4,"build":7,"rate":15.4,"ci":{"low":0,"high":45.5},"clusterCount":8,"costPerPassUsd":11.38,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":1,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":2,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":1,"fail":7,"build":1,"rate":11.1,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":15.75,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":1,"fail":1,"build":1,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":5.25,"costPerEvalUsd":1.75,"costMeasuredShare":0,"costCoverage":1}},"cursor-gpt-5.2":{"CWE-787":{"n":16,"pass":11,"fail":4,"build":1,"rate":68.8,"ci":{"low":50,"high":86.7},"clusterCount":13,"costPerPassUsd":4.48,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":72,"pass":40,"fail":18,"build":14,"rate":55.6,"ci":{"low":39.5,"high":67.9},"clusterCount":30,"costPerPassUsd":5.54,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":2,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":3,"fail":6,"build":0,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":9.24,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":11,"pass":3,"fail":4,"build":4,"rate":27.3,"ci":{"low":6.3,"high":60},"clusterCount":6,"costPerPassUsd":11.29,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":4.62,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}},"cursor-gpt-5.3-codex":{"CWE-787":{"n":17,"pass":10,"fail":5,"build":2,"rate":58.8,"ci":{"low":37.5,"high":81.3},"clusterCount":14,"costPerPassUsd":5.24,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":74,"pass":41,"fail":22,"build":11,"rate":55.4,"ci":{"low":36.8,"high":68.2},"clusterCount":31,"costPerPassUsd":5.56,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":3,"fail":5,"build":5,"rate":23.1,"ci":{"low":4.5,"high":55.6},"clusterCount":8,"costPerPassUsd":13.35,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":3.08,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":1,"fail":1,"build":0,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":2,"fail":6,"build":1,"rate":22.2,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":13.86,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":1,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":4.62,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}},"cursor-opus-4.6":{"CWE-787":{"n":17,"pass":13,"fail":2,"build":2,"rate":76.5,"ci":{"low":58.8,"high":93.8},"clusterCount":14,"costPerPassUsd":28.93,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":75,"pass":49,"fail":14,"build":12,"rate":65.3,"ci":{"low":50,"high":77.7},"clusterCount":32,"costPerPassUsd":33.86,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":44.25,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":44.25,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":6,"fail":2,"build":5,"rate":46.2,"ci":{"low":20,"high":87.5},"clusterCount":8,"costPerPassUsd":47.94,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":22.13,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":44.25,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":3,"fail":6,"build":0,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":66.38,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":22.13,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":33.19,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1}},"gemini-gemini-3-pro-preview":{"CWE-787":{"n":17,"pass":8,"fail":6,"build":3,"rate":47.1,"ci":{"low":25,"high":68.8},"clusterCount":14,"costPerPassUsd":4.17,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":75,"pass":40,"fail":15,"build":20,"rate":53.3,"ci":{"low":39.7,"high":63.3},"clusterCount":32,"costPerPassUsd":3.67,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":3.92,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":0,"fail":0,"build":2,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":3,"fail":6,"build":4,"rate":23.1,"ci":{"low":6.7,"high":44.4},"clusterCount":8,"costPerPassUsd":8.49,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":2,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":1,"fail":7,"build":1,"rate":11.1,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":17.64,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":1,"fail":0,"build":2,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":5.88,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1}},"gemini31-gemini-3.1-pro-preview":{"CWE-787":{"n":16,"pass":10,"fail":3,"build":3,"rate":62.5,"ci":{"low":42.1,"high":81.3},"clusterCount":14,"costPerPassUsd":3.14,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":65,"pass":43,"fail":9,"build":13,"rate":66.2,"ci":{"low":50,"high":79},"clusterCount":28,"costPerPassUsd":2.96,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":1.96,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":3.92,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":1.96,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":1,"fail":1,"build":0,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":3.92,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":4,"pass":0,"fail":2,"build":2,"rate":0,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":null,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":12,"pass":4,"fail":3,"build":5,"rate":33.3,"ci":{"low":5.9,"high":70},"clusterCount":7,"costPerPassUsd":5.88,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":2,"pass":2,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":1.96,"costPerEvalUsd":1.96,"costMeasuredShare":0,"costCoverage":1}},"opencode-claude-opus-4-5":{"CWE-787":{"n":17,"pass":7,"fail":3,"build":7,"rate":41.2,"ci":{"low":20,"high":62.5},"clusterCount":14,"costPerPassUsd":32.97,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":74,"pass":31,"fail":17,"build":26,"rate":41.9,"ci":{"low":23.1,"high":56.1},"clusterCount":32,"costPerPassUsd":32.4,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":27.15,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":0,"fail":0,"build":2,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":3,"fail":3,"build":7,"rate":23.1,"ci":{"low":5,"high":50},"clusterCount":8,"costPerPassUsd":58.82,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":8,"pass":2,"fail":3,"build":3,"rate":25,"ci":{"low":null,"high":null},"clusterCount":5,"costPerPassUsd":54.3,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":1,"fail":1,"build":1,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":40.72,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":1,"pass":0,"fail":1,"build":0,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":13.575,"costMeasuredShare":0,"costCoverage":1}},"opencode-claude-opus-4-6":{"CWE-125":{"n":75,"pass":40,"fail":9,"build":26,"rate":53.3,"ci":{"low":32.1,"high":69.3},"clusterCount":32,"costPerPassUsd":41.48,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-787":{"n":15,"pass":6,"fail":3,"build":6,"rate":40,"ci":{"low":17.6,"high":66.7},"clusterCount":12,"costPerPassUsd":55.31,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":44.25,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":0,"fail":0,"build":2,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":44.25,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":8,"pass":2,"fail":2,"build":4,"rate":25,"ci":{"low":null,"high":null},"clusterCount":5,"costPerPassUsd":88.5,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":11,"pass":4,"fail":1,"build":6,"rate":36.4,"ci":{"low":11.8,"high":75},"clusterCount":6,"costPerPassUsd":60.84,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":33.19,"costPerEvalUsd":22.125,"costMeasuredShare":0,"costCoverage":1}},"opencode-gemini-gemini-3.1-pro-preview":{"CWE-787":{"n":16,"pass":8,"fail":2,"build":6,"rate":50,"ci":{"low":25,"high":78.6},"clusterCount":14,"costPerPassUsd":6.08,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":72,"pass":45,"fail":16,"build":11,"rate":62.5,"ci":{"low":50,"high":75},"clusterCount":31,"costPerPassUsd":4.86,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":0,"fail":1,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.08,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":3.04,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":1,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":8,"pass":4,"fail":4,"build":0,"rate":50,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":6.08,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":12,"pass":6,"fail":0,"build":6,"rate":50,"ci":{"low":15,"high":91.7},"clusterCount":7,"costPerPassUsd":6.08,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":1,"fail":1,"build":1,"rate":33.3,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":9.12,"costPerEvalUsd":3.04,"costMeasuredShare":0,"costCoverage":1}},"opencode-gpt-5.2":{"CWE-787":{"n":16,"pass":8,"fail":1,"build":7,"rate":50,"ci":{"low":27.8,"high":73.3},"clusterCount":13,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":72,"pass":45,"fail":5,"build":22,"rate":62.5,"ci":{"low":45.5,"high":75.3},"clusterCount":30,"costPerPassUsd":4.93,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":0,"fail":0,"build":2,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":1,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":2,"fail":3,"build":4,"rate":22.2,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":13.86,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":12,"pass":4,"fail":1,"build":7,"rate":33.3,"ci":{"low":12.5,"high":54.5},"clusterCount":7,"costPerPassUsd":9.24,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":3,"pass":2,"fail":0,"build":1,"rate":66.7,"ci":{"low":null,"high":null},"clusterCount":3,"costPerPassUsd":4.62,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}},"opencode-gpt-5.2-codex":{"CWE-787":{"n":17,"pass":7,"fail":3,"build":7,"rate":41.2,"ci":{"low":16.7,"high":68.8},"clusterCount":14,"costPerPassUsd":7.48,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-125":{"n":75,"pass":31,"fail":19,"build":25,"rate":41.3,"ci":{"low":22.8,"high":55.2},"clusterCount":32,"costPerPassUsd":7.45,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-1284":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-843":{"n":2,"pass":0,"fail":0,"build":2,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-416":{"n":13,"pass":4,"fail":2,"build":7,"rate":30.8,"ci":{"low":6.7,"high":62.5},"clusterCount":8,"costPerPassUsd":10.01,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-475":{"n":1,"pass":0,"fail":0,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-476":{"n":2,"pass":0,"fail":1,"build":1,"rate":0,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":null,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-908":{"n":9,"pass":2,"fail":6,"build":1,"rate":22.2,"ci":{"low":null,"high":null},"clusterCount":6,"costPerPassUsd":13.86,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-562":{"n":1,"pass":1,"fail":0,"build":0,"rate":100,"ci":{"low":null,"high":null},"clusterCount":1,"costPerPassUsd":3.08,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1},"CWE-415":{"n":2,"pass":1,"fail":0,"build":1,"rate":50,"ci":{"low":null,"high":null},"clusterCount":2,"costPerPassUsd":6.16,"costPerEvalUsd":3.08,"costMeasuredShare":0,"costCoverage":1}}},"license":{"name":"CC-BY-4.0","url":"https://creativecommons.org/licenses/by/4.0/","note":"Aggregate cell outcomes only. Attribute the XOR benchmark and the corpus version."},"citation":"@dataset{xor_appsec_benchmark,\n  title     = {XOR AppSec benchmark — per-cell results by model and weakness class},\n  author    = {XOR},\n  year      = {2026},\n  publisher = {XOR},\n  note      = {Corpus cve-bench-136; models evaluated 2026-02-22; manifest rebuilt 2026-08-25},\n  url       = {https://www.xor.tech/benchmarks.json}\n}","documentation":{"rate":"Pass rate over scored attempts (infrastructure failures excluded from the denominator).","ci":"95% interval from a cluster bootstrap over codebases. Null when a single cluster carries no between-cluster information.","clusterCount":"Distinct codebases contributing to the cell.","costPerPassUsd":"Mean cost per successful repair, where cost was recorded. Null when nothing was recorded.","costMeasuredShare":"Share of cost figures that were metered rather than estimated from turn counts.","stages":"Which capability stages this corpus publishes. Stages listed as declaredNotPublished are unmeasured here, not zero."}}