diff --git a/evalharness/eval/recipes/agent.py b/evalharness/eval/recipes/agent.py index 0fc2b77..8c657a4 100644 --- a/evalharness/eval/recipes/agent.py +++ b/evalharness/eval/recipes/agent.py @@ -375,8 +375,8 @@ def _swe_official_reward(pred, target, sample, ctx): if have: try: res = _official_swebench_eval(md, patch) - return ({'acc': res.get('resolved', 0.0)}, - {'acc': {'mode': 'official_swebench', + return ({'resolved': res.get('resolved', 0.0)}, + {'resolved': {'mode': 'official_swebench', 'resolved': res.get('resolved'), 'error': res.get('error', ''), 'turns_used': es.get('turns_used')}})