> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galileo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Ground Truth Adherence

> Measure semantic equivalence between model outputs and reference answers using Galileo's Guardrail Metrics to ensure alignment with expected responses

export const BooleanClassificationReport = ({report, negativeLabel = "Not Advanced", positiveLabel = "Advanced", negativeClass = "False", positiveClass = "True", maxWidth = 520}) => {
  const parseReport = reportStr => {
    const lines = reportStr.trim().split('\n').filter(line => line.trim());
    const result = {
      classes: [],
      accuracy: null,
      macroAvg: null,
      weightedAvg: null,
      totalSupport: null
    };
    for (const line of lines) {
      const parts = line.trim().split(/\s+/);
      if (parts[0] === 'precision') continue;
      if (parts.length >= 5 && !['accuracy', 'macro', 'weighted'].includes(parts[0])) {
        result.classes.push({
          name: parts[0],
          precision: parseFloat(parts[1]),
          recall: parseFloat(parts[2]),
          f1: parseFloat(parts[3]),
          support: parseInt(parts[4], 10)
        });
      }
      if (parts[0] === 'accuracy') {
        result.accuracy = parseFloat(parts[1]);
        result.totalSupport = parseInt(parts[2], 10);
      }
      if (parts[0] === 'macro' && parts[1] === 'avg') {
        result.macroAvg = {
          precision: parseFloat(parts[2]),
          recall: parseFloat(parts[3]),
          f1: parseFloat(parts[4]),
          support: parseInt(parts[5], 10)
        };
      }
      if (parts[0] === 'weighted' && parts[1] === 'avg') {
        result.weightedAvg = {
          precision: parseFloat(parts[2]),
          recall: parseFloat(parts[3]),
          f1: parseFloat(parts[4]),
          support: parseInt(parts[5], 10)
        };
      }
    }
    return result;
  };
  const parsed = parseReport(report);
  if (parsed.classes.length < 2) {
    return <div style={{
      color: "red",
      padding: "1rem",
      border: "1px solid red"
    }}>BooleanClassificationReport: Could not parse report. Expected at least 2 classes.</div>;
  }
  const negClass = parsed.classes.find(c => c.name === negativeClass) || parsed.classes[0];
  const posClass = parsed.classes.find(c => c.name === positiveClass) || parsed.classes[1];
  const tnPlusFp = negClass.support;
  const tpPlusFn = posClass.support;
  const tn = Math.round(negClass.recall * tnPlusFp);
  const fp = tnPlusFp - tn;
  const tp = Math.round(posClass.recall * tpPlusFn);
  const fn = tpPlusFn - tp;
  const tnPct = tn / tnPlusFp * 100;
  const fpPct = fp / tnPlusFp * 100;
  const fnPct = fn / tpPlusFn * 100;
  const tpPct = tp / tpPlusFn * 100;
  const rowStyle = {
    borderBottom: "1px solid rgba(148, 163, 184, 0.3)"
  };
  const cellStyle = {
    padding: "0.5rem 0.125rem"
  };
  const centerCellStyle = {
    textAlign: "center",
    padding: "0.5rem 0.125rem"
  };
  return <div>
      {}
      <table style={{
    width: "auto",
    borderCollapse: "collapse",
    marginBottom: "1.5rem",
    fontSize: "0.875rem"
  }}>
        <thead>
          <tr style={{
    borderBottom: "2px solid rgba(148, 163, 184, 0.5)"
  }}>
            <th style={{
    textAlign: "center",
    padding: "0.5rem 0.125rem",
    fontWeight: "600"
  }}></th>
            <th style={{
    textAlign: "center",
    padding: "0.5rem 0.125rem",
    fontWeight: "600"
  }}>Precision</th>
            <th style={{
    textAlign: "center",
    padding: "0.5rem 0.125rem",
    fontWeight: "600"
  }}>Recall</th>
            <th style={{
    textAlign: "center",
    padding: "0.5rem 0.125rem",
    fontWeight: "600"
  }}>F1-Score</th>
          </tr>
        </thead>
        <tbody>
          {}
          <tr style={rowStyle}>
            <td style={cellStyle}>{negativeLabel}</td>
            <td style={centerCellStyle}>{negClass.precision.toFixed(2)}</td>
            <td style={centerCellStyle}>{negClass.recall.toFixed(2)}</td>
            <td style={centerCellStyle}>{negClass.f1.toFixed(2)}</td>
          </tr>
          <tr style={rowStyle}>
            <td style={cellStyle}>{positiveLabel}</td>
            <td style={centerCellStyle}>{posClass.precision.toFixed(2)}</td>
            <td style={centerCellStyle}>{posClass.recall.toFixed(2)}</td>
            <td style={centerCellStyle}>{posClass.f1.toFixed(2)}</td>
          </tr>
          
        </tbody>
      </table>

      {}
      <BooleanConfusionMatrix actualNegativeLabel={negativeLabel} actualPositiveLabel={positiveLabel} predictedNegativeLabel={negativeLabel} predictedPositiveLabel={positiveLabel} tnPct={tnPct.toString()} fpPct={fpPct.toString()} fnPct={fnPct.toString()} tpPct={tpPct.toString()} displayFormat="fraction" maxWidth={maxWidth} />
    </div>;
};

export const BooleanConfusionMatrix = ({actualNegativeLabel = "Not Advanced", actualPositiveLabel = "Advanced", predictedNegativeLabel = "Not Advanced", predictedPositiveLabel = "Advanced", tnCount, tnPct, fpCount, fpPct, fnCount, fnPct, tpCount, tpPct, matrix, maxWidth = 520, displayFormat = "percentage", fractionDigits = 3, percentageDigits = 1, titlePrefix = ""}) => {
  const parseNum = val => val !== undefined && val !== null ? Number(val) : undefined;
  const clampPct = pct => Math.max(0, Math.min(100, Number(pct) || 0));
  const formatValue = pct => {
    const p = clampPct(pct);
    if (displayFormat === "fraction") {
      const digits = Number.isFinite(Number(fractionDigits)) ? Number(fractionDigits) : 3;
      return (p / 100).toFixed(digits);
    }
    const digits = Number.isFinite(Number(percentageDigits)) ? Number(percentageDigits) : 1;
    return `${p.toFixed(digits)}%`;
  };
  const palette = ["#f8fafc", "#eff6ff", "#dbeafe", "#bfdbfe", "#93c5fd", "#60a5fa", "#3b82f6", "#2563eb", "#1d4ed8", "#1e40af"];
  const getBg = pct => {
    const p = clampPct(pct);
    const idx = p === 100 ? 9 : Math.floor(p / 10);
    return palette[idx];
  };
  const getColor = pct => clampPct(pct) >= 60 ? "#ffffff" : "#1e3a8a";
  const rawTn = parseNum(tnCount);
  const rawFp = parseNum(fpCount);
  const rawFn = parseNum(fnCount);
  const rawTp = parseNum(tpCount);
  const rawTnPct = parseNum(tnPct);
  const rawFpPct = parseNum(fpPct);
  const rawFnPct = parseNum(fnPct);
  const rawTpPct = parseNum(tpPct);
  const hasCounts = rawTn !== undefined && rawFp !== undefined && rawFn !== undefined && rawTp !== undefined;
  const hasPcts = rawTnPct !== undefined && rawFpPct !== undefined && rawFnPct !== undefined && rawTpPct !== undefined;
  let resolvedMatrix;
  let showCounts;
  if (matrix) {
    resolvedMatrix = matrix;
    showCounts = matrix.tn?.count !== undefined;
  } else if (hasCounts) {
    const actualNegTotal = rawTn + rawFp;
    const actualPosTotal = rawFn + rawTp;
    resolvedMatrix = {
      tn: {
        count: rawTn,
        pct: actualNegTotal > 0 ? rawTn / actualNegTotal * 100 : 0
      },
      fp: {
        count: rawFp,
        pct: actualNegTotal > 0 ? rawFp / actualNegTotal * 100 : 0
      },
      fn: {
        count: rawFn,
        pct: actualPosTotal > 0 ? rawFn / actualPosTotal * 100 : 0
      },
      tp: {
        count: rawTp,
        pct: actualPosTotal > 0 ? rawTp / actualPosTotal * 100 : 0
      }
    };
    showCounts = true;
  } else if (hasPcts) {
    resolvedMatrix = {
      tn: {
        pct: rawTnPct
      },
      fp: {
        pct: rawFpPct
      },
      fn: {
        pct: rawFnPct
      },
      tp: {
        pct: rawTpPct
      }
    };
    showCounts = false;
  } else {
    return <div style={{
      color: "red",
      padding: "1rem",
      border: "1px solid red"
    }}>BooleanConfusionMatrix: Provide either all counts or all percentages</div>;
  }
  const cellStyle = pct => ({
    background: getBg(pct),
    color: getColor(pct),
    padding: "1rem",
    textAlign: "center",
    borderRadius: "8px",
    aspectRatio: "1 / 1",
    width: "100%",
    display: "flex",
    flexDirection: "column",
    alignItems: "center",
    justifyContent: "center",
    border: "1px solid rgba(148, 163, 184, 0.35)"
  });
  const displayPredictedLabels = {
    left: predictedPositiveLabel,
    right: predictedNegativeLabel
  };
  const displayActualLabels = {
    top: actualPositiveLabel,
    bottom: actualNegativeLabel
  };
  const displayMatrix = {
    tl: resolvedMatrix.tp,
    tr: resolvedMatrix.fn,
    bl: resolvedMatrix.fp,
    br: resolvedMatrix.tn
  };
  return <div style={{
    maxWidth: maxWidth + "px",
    margin: "1rem 0"
  }}>
      <div style={{
    display: "grid",
    gridTemplateColumns: "auto auto 1fr 1fr",
    gridTemplateRows: "auto auto auto 1fr 1fr auto",
    gap: "2px"
  }}>
        {}
        <div></div>
        <div></div>
        <div style={{
    gridColumn: "3 / 5",
    textAlign: "center",
    padding: "0.5rem",
    fontWeight: "600",
    fontSize: "1rem"
  }}>
          {titlePrefix}Confusion Matrix (Normalized)
        </div>

        {}
        <div></div>
        <div></div>
        <div style={{
    gridColumn: "3 / 5",
    textAlign: "center",
    padding: "0.5rem",
    fontWeight: "600",
    fontSize: "0.875rem"
  }}>
          Predicted
        </div>

        {}
        <div></div>
        <div></div>
        <div style={{
    textAlign: "center",
    padding: "0.5rem",
    fontSize: "0.75rem",
    fontWeight: "500",
    display: "flex",
    alignItems: "center",
    justifyContent: "center"
  }}>{displayPredictedLabels.left}</div>
        <div style={{
    textAlign: "center",
    padding: "0.5rem",
    fontSize: "0.75rem",
    fontWeight: "500",
    display: "flex",
    alignItems: "center",
    justifyContent: "center"
  }}>{displayPredictedLabels.right}</div>

        {}
        <div style={{
    gridRow: "4 / 6",
    writingMode: "vertical-rl",
    transform: "rotate(180deg)",
    textAlign: "center",
    fontWeight: "600",
    fontSize: "0.875rem",
    padding: "0 0.5rem",
    display: "flex",
    alignItems: "center",
    justifyContent: "center"
  }}>
          Actual
        </div>
        <div style={{
    padding: "0.5rem",
    fontSize: "0.75rem",
    fontWeight: "500",
    display: "flex",
    alignItems: "center",
    justifyContent: "flex-end"
  }}>{displayActualLabels.top}</div>
        <div style={cellStyle(displayMatrix.tl.pct)}>
          {showCounts && <div style={{
    fontSize: "1.5rem",
    fontWeight: "700",
    lineHeight: 1
  }}>{displayMatrix.tl.count}</div>}
          <div style={{
    fontSize: showCounts ? "0.75rem" : "1rem",
    fontWeight: showCounts ? "400" : "700",
    opacity: showCounts ? 0.8 : 1
  }}>{formatValue(displayMatrix.tl.pct)}</div>
        </div>
        <div style={cellStyle(displayMatrix.tr.pct)}>
          {showCounts && <div style={{
    fontSize: "1.5rem",
    fontWeight: "700",
    lineHeight: 1
  }}>{displayMatrix.tr.count}</div>}
          <div style={{
    fontSize: showCounts ? "0.75rem" : "1rem",
    fontWeight: showCounts ? "400" : "700",
    opacity: showCounts ? 0.8 : 1
  }}>{formatValue(displayMatrix.tr.pct)}</div>
        </div>

        {}
        <div style={{
    padding: "0.5rem",
    fontSize: "0.75rem",
    fontWeight: "500",
    display: "flex",
    alignItems: "center",
    justifyContent: "flex-end"
  }}>{displayActualLabels.bottom}</div>
        <div style={cellStyle(displayMatrix.bl.pct)}>
          {showCounts && <div style={{
    fontSize: "1.5rem",
    fontWeight: "700",
    lineHeight: 1
  }}>{displayMatrix.bl.count}</div>}
          <div style={{
    fontSize: showCounts ? "0.75rem" : "1rem",
    fontWeight: showCounts ? "400" : "700",
    opacity: showCounts ? 0.8 : 1
  }}>{formatValue(displayMatrix.bl.pct)}</div>
        </div>
        <div style={cellStyle(displayMatrix.br.pct)}>
          {showCounts && <div style={{
    fontSize: "1.5rem",
    fontWeight: "700",
    lineHeight: 1
  }}>{displayMatrix.br.count}</div>}
          <div style={{
    fontSize: showCounts ? "0.75rem" : "1rem",
    fontWeight: showCounts ? "400" : "700",
    opacity: showCounts ? 0.8 : 1
  }}>{formatValue(displayMatrix.br.pct)}</div>
        </div>

        {}
        <div></div>
        <div></div>
        <div style={{
    gridColumn: "3 / 5",
    marginTop: "0.5rem",
    display: "flex",
    alignItems: "center",
    gap: "0.5rem"
  }}>
          <span style={{
    fontSize: "0.75rem",
    fontWeight: "500"
  }}>{displayFormat === "fraction" ? "0.0" : "0%"}</span>
          <div style={{
    display: "flex",
    flex: 1,
    height: "12px",
    borderRadius: "4px",
    overflow: "hidden",
    border: "1px solid rgba(148, 163, 184, 0.35)"
  }}>
            {palette.map((color, idx) => <div key={idx} style={{
    flex: 1,
    height: "100%",
    background: color
  }} />)}
          </div>
          <span style={{
    fontSize: "0.75rem",
    fontWeight: "500"
  }}>{displayFormat === "fraction" ? "1.0" : "100%"}</span>
        </div>
      </div>
    </div>;
};

export const DefinitionCard = ({children}) => {
  return <Card variant="secondary">
    <div style={{
    padding: '0.5rem',
    border: '5px solid var(--primary-light)',
    borderRadius: '0.5rem',
    fontSize: '1.3rem',
    lineHeight: '1.4',
    boxShadow: '0 0 10px 10px var(--primary-light)'
  }}>
        {children}
      </div>

</Card>;
};

export const Scale = ({low, mid, high, lowLabel = "Low", midLabel = "Mid", highLabel = "High", lowDescription, midDescription, highDescription, midColor = "yellow", inverted = false}) => {
  const lowColor = inverted ? "green" : "red";
  const highColor = inverted ? "red" : "green";
  const gradientId = inverted ? "greenToRed" : "redToGreen";
  return <div style={{
    display: 'flex',
    flexDirection: 'column',
    width: '100%'
  }}>
      <svg width="100%" height="30" style={{
    marginBottom: '8px'
  }}>
        <defs>
          <linearGradient id={gradientId} x1="0%" y1="0%" x2="100%" y2="0%">
            <stop offset="0%" stopColor={lowColor} />
            <stop offset="100%" stopColor={highColor} />
          </linearGradient>
        </defs>
        <rect width="100%" height="100%" fill={`url(#${gradientId})`} rx="4" ry="4" />
      </svg>

      <div style={{
    display: 'flex',
    justifyContent: 'space-between',
    width: '100%',
    marginBottom: '16px'
  }}>
        <p style={{
    margin: 0,
    fontSize: '12px'
  }}>{low}</p>
        {mid && <p style={{
    margin: 0,
    fontSize: '12px'
  }}>{mid}</p>}
        <p style={{
    margin: 0,
    fontSize: '12px'
  }}>{high}</p>
      </div>

      <div style={{
    display: 'flex',
    justifyContent: 'space-between',
    width: '100%'
  }}>
        <div style={{
    maxWidth: '40%'
  }}>
          <div style={{
    display: 'flex',
    alignItems: 'center',
    marginBottom: '4px'
  }}>
            <div style={{
    width: '12px',
    height: '12px',
    backgroundColor: lowColor,
    borderRadius: '50%',
    marginRight: '8px'
  }}></div>
            <p style={{
    margin: 0,
    fontWeight: 'bold',
    fontSize: '14px'
  }}>{lowLabel}</p>
          </div>
          {lowDescription && <p style={{
    margin: 0,
    fontSize: '14px',
    color: '#666',
    maxWidth: '250px',
    lineHeight: '1.4'
  }}>{lowDescription}</p>}
        </div>
        {mid && <div style={{
    maxWidth: '40%',
    textAlign: 'center'
  }}>
            <div style={{
    display: 'flex',
    alignItems: 'center',
    justifyContent: 'center',
    marginBottom: '4px'
  }}>
              <div style={{
    width: '12px',
    height: '12px',
    backgroundColor: midColor,
    borderRadius: '50%',
    marginRight: '8px'
  }}></div>
              <p style={{
    margin: 0,
    fontWeight: 'bold',
    fontSize: '14px'
  }}>{midLabel}</p>
            </div>
            {midDescription && <p style={{
    margin: 0,
    fontSize: '14px',
    color: '#666',
    maxWidth: '250px',
    textAlign: 'center',
    lineHeight: '1.4'
  }}>{midDescription}</p>}
          </div>}


        <div style={{
    maxWidth: '40%',
    textAlign: 'right'
  }}>
          <div style={{
    display: 'flex',
    alignItems: 'center',
    justifyContent: 'flex-end',
    marginBottom: '4px'
  }}>
            <p style={{
    margin: 0,
    fontWeight: 'bold',
    fontSize: '14px'
  }}>{highLabel}</p>
            <div style={{
    width: '12px',
    height: '12px',
    backgroundColor: highColor,
    borderRadius: '50%',
    marginLeft: '8px'
  }}></div>
          </div>
          {highDescription && <p style={{
    margin: 0,
    fontSize: '14px',
    color: '#666',
    maxWidth: '250px',
    marginLeft: 'auto',
    lineHeight: '1.4'
  }}>{highDescription}</p>}
        </div>
      </div>
    </div>;
};

<DefinitionCard>
  <strong>Ground Truth Adherence</strong> measures whether a model's response is semantically equivalent to your reference answer (Ground Truth).
</DefinitionCard>

Ground Truth Adherence is a continuous metric ranging from 0 to 1:

<Scale low="0" lowLabel="Low Adherence" high="1" highLabel="High Adherence" lowDescription="The model's response is semantically different from the Ground Truth" highDescription="The model's response is semantically equivalent to the Ground Truth" />

This metric helps evaluate how closely your model's outputs match expected or ideal responses, which is particularly valuable for:

* Evaluating model performance against a benchmark dataset
* Ensuring consistency in critical applications
* Measuring the impact of model or prompt changes

<Note>
  This metric is only supported in experiments, and requires a Ground Truth to be set in the `output` column of your experiment's [dataset](/sdk-api/experiments/datasets).
</Note>

## Calculation method

Ground Truth Adherence is computed through a multi-step process:

<Steps>
  <Step title="Model Request">
    Additional evaluation requests are sent to OpenAI's GPT4o model to analyze the semantic relationship between responses.
  </Step>

  <Step title="Prompt Engineering">
    A carefully engineered chain-of-thought prompt asks the model to evaluate whether the response and Ground Truth convey the same meaning.
  </Step>

  <Step title="Multiple Evaluations">
    The system requests multiple distinct responses to this prompt to ensure robust evaluation through consensus.
  </Step>

  <Step title="Result Analysis">
    Each evaluation generates both an explanation of the reasoning and a binary judgment (yes/no) on semantic equivalence.
  </Step>

  <Step title="Score Calculation">
    The final Ground Truth Adherence score is computed as the ratio of 'yes' responses to the total number of evaluation responses.
  </Step>
</Steps>

We also surface one of the generated explanations, always choosing one that aligns with the majority judgment among the responses.

<Note>
  This metric is computed by prompting an LLM multiple times, and thus requires additional LLM calls to compute, which may impact usage and billing.
</Note>

## Understanding ground truth adherence

<Card>
  <div style={{display: 'flex', alignItems: 'center', gap: '0.5rem', marginBottom: '0.75rem'}}>
    <div style={{fontSize: '1.25rem', color: 'var(--primary-color)'}}>
      <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
        <path d="M12 22c5.523 0 10-4.477 10-10S17.523 2 12 2 2 6.477 2 12s4.477 10 10 10z" />

        <path d="m9 12 2 2 4-4" />
      </svg>
    </div>

    <h3 style={{margin: 0, fontSize: '1.25rem', fontWeight: '600'}}>Differentiating from Other Metrics</h3>
  </div>

  It's important to understand how Ground Truth Adherence differs from related metrics:

  <div style={{ marginTop: "1rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Ground Truth Adherence:</strong> Measures semantic equivalence to a reference answer.
  </div>

  <div style={{ marginTop: "0.75rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Correctness:</strong> Measures factual accuracy regardless of any reference answer.
  </div>

  <div style={{ marginTop: "0.75rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Context Adherence:</strong> Measures alignment with provided context, not a reference answer.
  </div>
</Card>

## Optimizing your AI system

<Card>
  <div style={{display: 'flex', alignItems: 'center', gap: '0.5rem', marginBottom: '0.75rem'}}>
    <div style={{fontSize: '1.25rem', color: 'var(--primary-color)'}}>
      <svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2" strokeLinecap="round" strokeLinejoin="round">
        <path d="M12 20h9" />

        <path d="M16.5 3.5a2.121 2.121 0 0 1 3 3L7 19l-4 1 1-4L16.5 3.5z" />
      </svg>
    </div>

    <h3 style={{margin: 0, fontSize: '1.25rem', fontWeight: '600'}}>Addressing Low Ground Truth Adherence</h3>
  </div>

  When responses have low Ground Truth Adherence scores, your model is generating outputs that differ semantically from your reference answers. To improve your system:

  <div style={{ marginTop: "1rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Analyze divergence patterns:</strong> Identify common ways in which responses differ from ground truth.
  </div>

  <div style={{ marginTop: "0.75rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Refine your prompts:</strong> Adjust instructions to guide the model toward your expected output format and content.
  </div>

  <div style={{ marginTop: "0.75rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Consider few-shot examples:</strong> Provide examples in your prompt that demonstrate the desired response pattern.
  </div>

  <div style={{ marginTop: "0.75rem", paddingTop: "0.75rem", borderTop: "1px solid rgba(209, 213, 219, 0.33)" }}>
    <strong>Evaluate ground truth quality:</strong> Ensure your reference answers are clear, consistent, and representative of ideal responses.
  </div>
</Card>

## Best practices

<CardGroup cols={2}>
  <Card title="Maintain Diverse Ground Truths" icon="layer-group">
    Create a varied set of reference answers that cover different response styles and edge cases.
  </Card>

  <Card title="Set Clear Evaluation Criteria" icon="list-check">
    Define what constitutes semantic equivalence for your specific use case and domain.
  </Card>

  <Card title="Monitor Across Model Versions" icon="chart-line">
    Track Ground Truth Adherence when upgrading models to ensure consistent performance.
  </Card>

  <Card title="Balance with Other Metrics" icon="scale-balanced">
    Use Ground Truth Adherence alongside metrics like Correctness and Instruction Adherence for a complete evaluation.
  </Card>
</CardGroup>

<Note>
  When optimizing for Ground Truth Adherence, remember that there may be multiple valid ways to express the same information. Consider whether strict adherence to specific wording is necessary, or if semantic equivalence is sufficient for your use case.
</Note>

## Performance Benchmarks

We evaluated Ground Truth Adherence against human expert labels on an internal dataset using top frontier models.

| Model                   | F1 (True) |
| :---------------------- | :-------: |
| GPT-4.1                 |    0.90   |
| GPT-4.1-mini (judges=3) |    0.91   |
| Claude Sonnet 4.5       |    0.91   |
| Gemini 3 Flash          |    0.94   |

### GPT-4.1 Classification Report

<BooleanClassificationReport
  report={`            precision    recall  f1-score   support

False       0.9749    0.8083    0.8838      1346
True       0.8363    0.9792    0.9021      1346

accuracy                          0.8938      2692
macro avg     0.9056    0.8938    0.8930      2692
weighted avg  0.9056    0.8938    0.8930      2692`}
  negativeLabel="False"
  positiveLabel="True"
  negativeClass="False"
  positiveClass="True"
/>

<Note>
  Benchmarks based on internal evaluation dataset. Performance may vary by use case.
</Note>

## Related Resources

If you would like to dive deeper or start implementing Ground Truth Adherence, check out the following resources:

### Related Concepts

* [Context Adherence](/concepts/metrics/rag/generation-quality/context-adherence)
* [Context Relevance](/concepts/metrics/rag/retrieval-quality/context-relevance)
* [Correctness](/concepts/metrics/response-quality/correctness)