diff --git a/CHANGELOG.md b/CHANGELOG.md
index 64f51d9f9..85c9d6a29 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -15,6 +15,7 @@
 * **Remove `page_number` metadata fields** for HTML partition until we have a better strategy to decide page counting.
 * **Extract OCRAgent.get_agent().** Generalize access to the configured OCRAgent instance beyond its use for PDFs.
 * **Add calculation of table related metrics which take into account colspans and rowspans**
+* **Evaluation: skip accuracy calculation** for files for which output and ground truth sizes differ greatly
 
 ### Features
 
diff --git a/unstructured/metrics/evaluate.py b/unstructured/metrics/evaluate.py
index 2b3900a5c..dd0062397 100755
--- a/unstructured/metrics/evaluate.py
+++ b/unstructured/metrics/evaluate.py
@@ -116,7 +116,13 @@ def measure_text_extraction_accuracy(
             except Exception:
                 # if any of the output/source file is unable to open, skip the loop
                 continue
-            accuracy = round(calculate_accuracy(output_cct, source_cct, weights), 3)
+            # NOTE(amadeusz): Levenshtein distance calculation takes too long
+            # skip it if file sizes differ wildly
+            if 0.5 < len(output_cct.encode()) / len(source_cct.encode()) < 2.0:
+                accuracy = round(calculate_accuracy(output_cct, source_cct, weights), 3)
+            else:
+                # 0.01 to distinguish it was set manually
+                accuracy = 0.01
             percent_missing = round(calculate_percent_missing_text(output_cct, source_cct), 3)
             rows.append([filename, doctype, connector, accuracy, percent_missing])