diff --git a/benchmarks/runtime/README.md b/benchmarks/runtime/README.md
index bbb17bec1..9dea0a3ea 100644
--- a/benchmarks/runtime/README.md
+++ b/benchmarks/runtime/README.md
@@ -16,6 +16,7 @@ Application-shaped workloads for measuring the speed of compiled executables. Ea
 | `numeric-kernels` | cpu | sieve, hashing, `number[][]` matmul, `Float64Array` |
 | `validate-errors` | cpu | throw/catch on a fraction of inputs, small call chains |
 | `csv-numbers` | cpu | `split`, `Number`, `parseInt`, `toFixed` |
+| `log-lines` | cpu | 200k immediate `console.log`/`process.stdout.write` lines into the runner's pipe |
 | `log-summary`, `inventory-report` | cpu | the multi-module applications from `benchmarks/builds`, on 300k-line inputs |
 | `cli-config` | startup | a `deploy-plan` CLI: read a ~110 KB JSON manifest, validate, interpolate env values, order 80 services into dependency waves, print a summary |
 | `http-api` | server | a `node:http` JSON API: routing, query parsing, a seeded catalog, per-cart state, typed JSON bodies, `ETag`/`If-None-Match`, auth and request-id headers |
diff --git a/benchmarks/runtime/workloads.json b/benchmarks/runtime/workloads.json
index 59dfba452..5e7ebfce9 100644
--- a/benchmarks/runtime/workloads.json
+++ b/benchmarks/runtime/workloads.json
@@ -84,6 +84,13 @@
         "1"
       ]
     },
+    {
+      "name": "log-lines",
+      "entry": "workloads/log-lines.ts",
+      "args": [
+        "4"
+      ]
+    },
     {
       "name": "log-summary",
       "entry": "../builds/log-summary/main.ts",
diff --git a/benchmarks/runtime/workloads/log-lines.ts b/benchmarks/runtime/workloads/log-lines.ts
new file mode 100644
index 000000000..c13d52bff
--- /dev/null
+++ b/benchmarks/runtime/workloads/log-lines.ts
@@ -0,0 +1,62 @@
+// A logging-heavy CLI: one console line per record, written immediately.
+// Mixes the common console shapes (a single template literal, string plus
+// number arguments, several primitive arguments) with process.stdout.write
+// chunks and an occasional console.error line.
+interface LogRecord {
+  id: number;
+  method: string;
+  path: string;
+  status: number;
+  latency: number;
+  cached: boolean;
+}
+
+const methods = ["GET", "POST", "PUT", "DELETE"];
+const paths = ["/api/users", "/api/orders", "/health", "/static/app.js", "/api/search?q=caf\u00e9"];
+
+let seed = 7;
+function random(): number {
+  seed = (Math.imul(seed, 1103515245) + 12345) >>> 0;
+  return seed / 4294967296;
+}
+
+function makeRecord(id: number): LogRecord {
+  const r = random();
+  return {
+    id,
+    method: methods[id % methods.length]!,
+    path: paths[Math.floor(random() * paths.length)]!,
+    status: r < 0.9 ? 200 : r < 0.97 ? 404 : 500,
+    latency: Math.round(random() * 250000) / 1000,
+    cached: random() < 0.3,
+  };
+}
+
+const scale = Number(process.argv[2] ?? "1");
+const count = Math.round(50000 * scale);
+let errors = 0;
+let bytes = 0;
+for (let i = 0; i < count; i++) {
+  const rec = makeRecord(i);
+  switch (i % 4) {
+    case 0:
+      console.log(`${rec.method} ${rec.path} ${rec.status} ${rec.latency}ms`);
+      break;
+    case 1:
+      console.log("request", rec.id, rec.method, rec.status);
+      break;
+    case 2:
+      console.log("latency", rec.latency, "cached", rec.cached);
+      break;
+    default: {
+      const chunk = "[" + rec.id + "] " + rec.path + (rec.cached ? " (cached)" : "") + "\n";
+      bytes += chunk.length;
+      process.stdout.write(chunk);
+    }
+  }
+  if (rec.status === 500) {
+    errors++;
+    if (errors % 100 === 0) console.error("error budget: " + errors + " server errors at record " + rec.id);
+  }
+}
+console.log("records", count, "errors", errors, "chunk chars", bytes);