LawBenchmark.pl›Benchmark 02›Questions›P12

P12 · Enforcement clause (court endorsement authorising enforcement) against the debtor's spouse

civil procedure · closed question (yes / no / it depends…) · with a trap · key v1 of 2026-10-10 · legal-state date 1 October 2026

W0GPT-6.1 Sol W0: poprawnie ugruntowanaGPT-6 Astra W0: poprawnie ugruntowanaGPT-5.6 Terra W0: poprawnie ugruntowanaClaude Opus 5.5 W0: halucynacja TClaude Sonnet 5.5 W0: halucynacja TClaude Haiku 5.5 W0: halucynacja TGemini 3.8 Flash W0: poprawnie ugruntowanaGemini 4 Argon W0: halucynacja TW1GPT-6.1 Sol W1: poprawnie ugruntowanaGPT-6 Astra W1: poprawnie ugruntowanaGPT-5.6 Terra W1: poprawnie ugruntowanaClaude Opus 5.5 W1: poprawnie ugruntowanaClaude Sonnet 5.5 W1: halucynacja F,TClaude Haiku 5.5 W1: bez halucynacji, nie ugruntowanaGemini 3.8 Flash W1: poprawnie ugruntowanaGemini 4 Argon W1: halucynacja TSolAstraTerraOpusSonnetHaikuFlashArgon

correctly groundedno hallucinationhallucinated · rows: W0 no tools, W1 with web search

The question as used in the run (Polish)#

Klauzula wykonalności na małżonka, pozew był związany z działalnością gospodarczą, ale w NZ nie ma nic na temat "prowadzący działalnosc" w klauzuli jest PESEL i nie ma żadnej wzmianki nt. dzialalności, czy można wnosić o klauzulę na małżonka w "normalnym trybie'? tj. czy można wnieść o egzkeucję "bez ograniczeń", które wynikają z 781[1] k.p.c. ?

Original wording, exactly as the lawyer typed it into the chat (Polish); typos kept.

The trap

Three false assumptions in the question: (1) that there is an "unrestricted" enforcement clause against a spouse; (2) that the available route depends on the content of the payment order or the clause (mention of business activity, PESEL number), whereas it depends on the substantive condition of art. 787 or 787¹; (3) the provision number: art. 781¹ sets the time limit for deciding the application, while the restriction to the enterprise follows from art. 787¹.

The correct answer according to the key#

Core answer. Not in the sense asked: there is no "unrestricted" clause against a spouse. Every enforcement clause against the debtor's spouse is limited: to the joint marital property (art. 787 of the Code of Civil Procedure, where the claim arose from a legal act done with the spouse's consent) or to the enterprise forming part of the joint property (art. 787¹, where the claim arose in connection with running the enterprise).

Required bases. art. 787 Code of Civil Procedure; art. 787¹ Code of Civil Procedure

Expected calibration: conditional. spouse's consent to the act → art. 787 (joint property); no consent, claim from running the enterprise → art. 787¹ (the enterprise); neither → no clause against the spouse (art. 776¹ of the Code of Civil Procedure)

The full key (rubric, penalties, quotation patterns from the source, known rulings) is in the repository in keys/P12_klauzula_malzonek_787.yaml. Every legal basis was checked in the official text as of the legal-state date. Rules of the key.

Results of the eight models#

Hallucinated answers (of 8)W0: 4 · W1: 2
Correctly grounded (of 8)W0: 4 · W1: 5
Error classes W0T 4
Error classes W1F 1, T 2
Mean block A score (16 answers)79.1 %
Full core (A-R = 2)13 of 16
ModelConditionBlock A %ResultCard
GPT-6.1 SolW090✓card
W190✓card
GPT-6 AstraW090✓card
W190✓card
GPT-5.6 TerraW090✓card
W195✓card
Claude Opus 5.5W080Tcard
W1100✓card
Claude Sonnet 5.5W065Tcard
W160FTcard
Claude Haiku 5.5W025Tcard
W155–card
Gemini 3.8 FlashW080✓card
W190✓card
Gemini 4 ArgonW080Tcard
W185Tcard

correctly groundedno hallucination; not correctly groundedhallucinatedprovider blockColumns: models in report order; rows: W0 no tools, W1 with web search.

✓ correctly grounded · – no hallucination, but the core is incomplete or no source was checked · T W F S error classes in a hallucinated answer (definitions) · block text blocked by the provider's filter, no label · block A = criteria checked against the key and the source (scoring criteria)

The numbers concern one answer of each model to this question in each condition. They say nothing about run-to-run variance or about other questions in this field.

← P10all questionsP13 →