diff --git a/guides/use-cases/run-batch-evals.mdx b/guides/use-cases/run-batch-evals.mdx
index 4c202a7d..d24f9d6a 100644
--- a/guides/use-cases/run-batch-evals.mdx
+++ b/guides/use-cases/run-batch-evals.mdx
@@ -502,8 +502,8 @@ print(tabulate(display_df, headers='keys', tablefmt='simple', showindex=False))
 
 The script outputs a CSV with your evaluation results. Here's what matters:
 
-- **status_code 246**: Request passed JSON schema validation ✅
-- **status_code 446**: Request failed JSON schema validation ❌
+- **status_code 200**: Request passed JSON schema validation ✅
+- **status_code 246**: Request failed JSON schema validation ❌
 
 Example output:
 ```
@@ -523,7 +523,7 @@ parse_error 2
 
 <Steps>
 <Step title="Fix Schema Failures">
-If you see 446 status codes, check:
+If you see 246 status codes, check:
 - Is your prompt output format clear?
 - Did you include enough examples?
 - Is the JSON structure in your prompt exactly right?