diff --git a/api-reference/openapi.json b/api-reference/openapi.json
index 35a8713..d3db457 100644
--- a/api-reference/openapi.json
+++ b/api-reference/openapi.json
@@ -5186,6 +5186,7 @@
                     }
                   ],
                   "summary": {
+                    "overall_score": 72,
                     "granular_counts": {
                       "Accuracy": {
                         "Mistranslation": {
@@ -8888,10 +8889,18 @@
           "summary": {
             "type": "object",
             "required": [
+              "overall_score",
               "granular_counts"
             ],
-            "description": "Aggregate counts of issues across all segments.",
+            "description": "Aggregate quality results across all segments.",
             "properties": {
+              "overall_score": {
+                "type": "integer",
+                "minimum": 0,
+                "maximum": 100,
+                "description": "Overall translation quality, from 0 (lowest) to 100 (highest). See [Summary](/api-reference/quality-evaluation/poll#summary).",
+                "example": 72
+              },
               "granular_counts": {
                 "type": "object",
                 "description": "Nested counts keyed by `type`, then `sub_type`, then `severity`. Leaf values are integer counts.",
diff --git a/api-reference/openapi.yaml b/api-reference/openapi.yaml
index 2b93a65..fdfe197 100644
--- a/api-reference/openapi.yaml
+++ b/api-reference/openapi.yaml
@@ -3520,6 +3520,7 @@ paths:
                           - start: 38
                             end: 48
                 summary:
+                  overall_score: 72
                   granular_counts:
                     Accuracy:
                       Mistranslation:
@@ -6618,9 +6619,16 @@ components:
         summary:
           type: object
           required:
+            - overall_score
             - granular_counts
-          description: Aggregate counts of issues across all segments.
+          description: Aggregate quality results across all segments.
           properties:
+            overall_score:
+              type: integer
+              minimum: 0
+              maximum: 100
+              description: Overall translation quality, from 0 (lowest) to 100 (highest). See [Summary](/api-reference/quality-evaluation/poll#summary).
+              example: 72
             granular_counts:
               type: object
               description: Nested counts keyed by `type`, then `sub_type`, then `severity`. Leaf values are integer counts.
diff --git a/api-reference/quality-evaluation/poll.mdx b/api-reference/quality-evaluation/poll.mdx
index 618f5b1..50b2f8e 100644
--- a/api-reference/quality-evaluation/poll.mdx
+++ b/api-reference/quality-evaluation/poll.mdx
@@ -5,6 +5,13 @@ title: "Poll for the evaluation result"
 
 See the [Quality Evaluation overview](/api-reference/quality-evaluation) for severity values, sub-types, span semantics, and limits.
 
+### Summary
+
+The `summary` object aggregates the results across all segments:
+
+* `overall_score` rates the overall translation quality from 0 (lowest) to 100 (highest). The score is based on the severity of detected issues and adjusts for the length of the text, so a single issue has less impact on a longer translation than on a shorter one.
+* `granular_counts` breaks down the number of issues, nested by `type`, then `sub_type`, then `severity`.
+
 ### Severity values
 
 | **severity** | **Description** |