benchmarks/k32-seed0-20260927T174023Z: 2026-09-27T18-54-44Z-million-in-memoryagentbench-nmem_deep_k32_qwindow-29a513 json_answer_v1 rescore

benchmarks/k32-seed0-20260927T174023Z/runs/2026-09-27T18-54-44Z-million-in-memoryagentbench-nmem_deep_k32_qwindow-29a513/scores.json_answer_v1.json

@@ -0,0 +1,11 @@
+{
+  "detective_qa": {
+    "n": 71,
+    "parser": "json_answer_v1",
+    "base_scorer_sha256": "d77976be409298970614d477a9d8003850caddb0510e56a7e821a037d98493a2",
+    "json_answers_found": 71,
+    "exact_match": 42.25,
+    "f1": 47.27,
+    "substring_exact_match": 42.25
+  }
+}