<?xml version="1.0" encoding="UTF-8"?>
<testsuites name="agentkit-evals" tests="3" failures="0" skipped="0" time="14.587">
  <testsuite name="agentkit-evals" tests="3" failures="0" skipped="0" time="14.587">
    <testcase name="benchmarks/swe-tool" classname="agentkit-evals" time="7.359">
    </testcase>
    <testcase name="benchmarks/gpqa-json" classname="agentkit-evals" time="6.790">
    </testcase>
    <testcase name="benchmarks/unknown-judge" classname="agentkit-evals" time="7.789">
      <system-out>judge.closedQA(says it has no data on this benchmark and does not invent d…)=1.000 (&gt;= 0.8)</system-out>
    </testcase>
  </testsuite>
</testsuites>
