diff --git a/docs/help/testing-live.md b/docs/help/testing-live.md
index 0162b28bb27..51ec6f89917 100644
--- a/docs/help/testing-live.md
+++ b/docs/help/testing-live.md
@@ -53,7 +53,7 @@ Live tests are split into two layers so we can isolate failures:
   - or `OPENCLAW_LIVE_MODELS="openai/gpt-5.2,openai-codex/gpt-5.2,anthropic/claude-opus-4-6,..."` (comma allowlist)
   - Modern/all sweeps default to a curated high-signal cap; set `OPENCLAW_LIVE_MAX_MODELS=0` for an exhaustive modern sweep or a positive number for a smaller cap.
   - Exhaustive sweeps use `OPENCLAW_LIVE_TEST_TIMEOUT_MS` for the whole direct-model test timeout. Default: 60 minutes.
-  - Set `OPENCLAW_LIVE_MODEL_CONCURRENCY=20` to run direct-model probes in parallel. Default: 1.
+  - Direct-model probes run with 20-way parallelism by default; set `OPENCLAW_LIVE_MODEL_CONCURRENCY` to override.
 - How to select providers:
   - `OPENCLAW_LIVE_PROVIDERS="google,google-antigravity,google-gemini-cli"` (comma allowlist)
 - Where keys come from:
diff --git a/src/agents/models.profiles.live.test.ts b/src/agents/models.profiles.live.test.ts
index 2e13a477e01..4b9e9bb1594 100644
--- a/src/agents/models.profiles.live.test.ts
+++ b/src/agents/models.profiles.live.test.ts
@@ -57,7 +57,8 @@ const LIVE_TEST_TIMEOUT_MS = Math.max(
   1_000,
   toInt(process.env.OPENCLAW_LIVE_TEST_TIMEOUT_MS, 60 * 60 * 1000),
 );
-const LIVE_MODEL_CONCURRENCY = Math.max(1, toInt(process.env.OPENCLAW_LIVE_MODEL_CONCURRENCY, 1));
+const DEFAULT_LIVE_MODEL_CONCURRENCY = 20;
+const LIVE_MODEL_CONCURRENCY = resolveLiveModelConcurrency();
 const LIVE_MODELS_JSON_TIMEOUT_MS = resolveLiveModelsJsonTimeoutMs();
 const LIVE_FILE_PROBE_ENABLED = isLiveModelProbeEnabled(process.env, LIVE_MODEL_FILE_PROBE_ENV);
 const LIVE_IMAGE_PROBE_ENABLED = isLiveModelProbeEnabled(process.env, LIVE_MODEL_IMAGE_PROBE_ENV);
@@ -317,6 +318,21 @@ function toInt(value: string | undefined, fallback: number): number {
   return Number.isFinite(parsed) ? parsed : fallback;
 }
 
+function resolveLiveModelConcurrency(raw = process.env.OPENCLAW_LIVE_MODEL_CONCURRENCY): number {
+  return Math.max(1, toInt(raw, DEFAULT_LIVE_MODEL_CONCURRENCY));
+}
+
+describe("resolveLiveModelConcurrency", () => {
+  it("defaults direct-model probes to 20-way concurrency", () => {
+    expect(resolveLiveModelConcurrency(undefined)).toBe(20);
+  });
+
+  it("accepts explicit concurrency overrides", () => {
+    expect(resolveLiveModelConcurrency("7")).toBe(7);
+    expect(resolveLiveModelConcurrency("0")).toBe(1);
+  });
+});
+
 function resolveLiveModelsJsonTimeoutMs(
   modelsJsonTimeoutRaw = process.env.OPENCLAW_LIVE_MODELS_JSON_TIMEOUT_MS,
   setupTimeoutMs = LIVE_SETUP_TIMEOUT_MS,