diff --git a/apps/studio/src/routes/benchmarks/$benchmarkId_/evals/$runId.$evalId.tsx b/apps/studio/src/routes/benchmarks/$benchmarkId_/evals/$runId.$evalId.tsx
index c3c916341..169d6d643 100644
--- a/apps/studio/src/routes/benchmarks/$benchmarkId_/evals/$runId.$evalId.tsx
+++ b/apps/studio/src/routes/benchmarks/$benchmarkId_/evals/$runId.$evalId.tsx
@@ -7,7 +7,7 @@ import { useState } from 'react';
import { EvalDetail } from '~/components/EvalDetail';
import { RunEvalModal } from '~/components/RunEvalModal';
-import { useBenchmarkRunDetail, useStudioConfig } from '~/lib/api';
+import { isPassing, useBenchmarkRunDetail, useStudioConfig } from '~/lib/api';
export const Route = createFileRoute('/benchmarks/$benchmarkId_/evals/$runId/$evalId')({
component: BenchmarkEvalDetailPage,
@@ -50,6 +50,12 @@ function BenchmarkEvalDetailPage() {
);
}
+ const passThreshold = config?.threshold ?? config?.pass_threshold ?? 0.8;
+ const passed =
+ isPassing(result.score, passThreshold) &&
+ result.executionStatus !== 'error' &&
+ result.executionStatus !== 'failed';
+
return (
@@ -57,7 +63,12 @@ function BenchmarkEvalDetailPage() {
Run: {runId} / Eval: {evalId}
-
{evalId}
+
+
+ {passed ? '✓' : '✗'}
+
+ {evalId}
+
{!isReadOnly && (