diff --git a/evalharness/model/runner.py b/evalharness/model/runner.py
index 1c2ee5f..b03a225 100644
--- a/evalharness/model/runner.py
+++ b/evalharness/model/runner.py
@@ -419,18 +419,15 @@ async def generate_predictions(
         # backoff so one ConnectError burst cannot kill the whole batch --
         # the adapter already retries 5xx/429 and the pool fails over per
         # instance; this is the last line of defense around asyncio.gather
-        for attempt in range(3):
-            try:
-                pred = await one(s)
-                break
-            except Exception:
-                if attempt == 2:
-                    if progress_reporter is not None:
-                        progress_reporter.advance(success=False)
-                    raise
-                # minute-scale backoff: cluster routes flap in multi-minute
-                # bursts; short retries exhaust inside one dead window
-                await asyncio.sleep((10, 20, 40)[attempt])
+        # NO outer retry: the adapter retries internally; a second loop
+        # here multiplied worst-case time (42+ attempts before this fix).
+        # One pass, one result or one error.
+        try:
+            pred = await one(s)
+        except Exception:
+            if progress_reporter is not None:
+                progress_reporter.advance(success=False)
+            raise
         if ckpt_store is not None:
             ckpt_store.append(keys[i], pred)
         return i, pred