diff --git a/evalharness/data/datasets/swe_bench_verified.py b/evalharness/data/datasets/swe_bench_verified.py
index 5415fd7..1d7263b 100644
--- a/evalharness/data/datasets/swe_bench_verified.py
+++ b/evalharness/data/datasets/swe_bench_verified.py
@@ -19,10 +19,17 @@ from ..spec import DatasetSpec
 def swe_bench_verified():
     def to_sample(record: dict) -> Sample:
         instance_id = record['instance_id']
+        # image naming: local swebench/ set uses {repo}_1776_{repo}-{num}; the
+        # newer official layout is sweb.eval.x86_64.{repo}__{repo}-{num}
+        img = f'sweb.eval.x86_64.{instance_id}'
+        if '__' in instance_id:
+            repo, num = instance_id.rsplit('-', 1)
+            r = repo.split('__')[0]
+            img = f'swebench/sweb.eval.x86_64.{r}_1776_{r.split("__")[-1]}-{num}'
         return Sample(
             input=record['problem_statement'],
             target=record['patch'],  # gold patch (for oracle/oracle-check only)
-            sandbox=SandboxSpec(image=f'sweb.eval.x86_64.{instance_id}'),  # official image naming
+            sandbox=SandboxSpec(image=img),
             metadata={
                 'instance_id': instance_id,
                 'repo': record['repo'],