diff --git a/evalharness/eval/runner.py b/evalharness/eval/runner.py
index 97da2ba..ba96821 100644
--- a/evalharness/eval/runner.py
+++ b/evalharness/eval/runner.py
@@ -120,6 +120,15 @@ def evaluate(
         each sample gets its own container/workdir)."""
         result = _shell(sample, pred)
         raw = result.raw_prediction
+        # hybrid-thinking backends sometimes inline the reasoning channel
+        # into content wrapped in <think>...</think> (or leave a stray
+        # closer): extractors then fish answers out of reasoning text
+        # ('3</think>Let me analyze...'). Strip the blocks before extract.
+        if '<think>' in raw or '</think>' in raw:
+            import re as _re0
+
+            raw = _re0.sub(r'<think>.*?</think>', '', raw, flags=_re0.S)
+            raw = raw.replace('</think>', '')
         try:
             if bp is not None and sample.sandbox and sample.sandbox.image:
                 bp.ensure(sample.sandbox.image)  # wait only if this one still pulling