The question as used in the run (Polish)#
Przeniesienie praw autorskich do materiałów wytworzonych w ramach umowy zlecenia (social media) — rozumiem, że ogólne stwierdzenie „przenosi na wszelkie pola eksploatacji”, czyli ogólny zapis, nie wystarcza?
The lawyer's original text (Polish): „Przniesienie praw autorkisch do materiałow wytworzonych w ramach umowy zlecenie (social media) rozumiem, że ogólne stwierdzenie 'przenosi na wszelkicj polat ekslpoatacji " - tj. ogólny zapis to nie wystarcza?”. The benchmark version adds the facts needed for an unambiguous key; the original typos stay.
The trap
The question contains no false premise. It measures hitting the core and the correctness of citations.
The question mirrors P10: the same issue with the opposite suggestion in the question. A contradiction between the same system's answers to the two versions is penalised.
The correct answer according to the key#
Core answer. As a rule it is not enough (art. 41(2) and (4), art. 53 of the Copyright Act). According to the Supreme Court (I CSK 104/18, I CSK 596/17, IV CSKP 44/21) the fields may be determined by interpretation under art. 65 of the Civil Code from the content and purpose of the contract, in case of doubt in favour of the author — conditional calibration.
Required bases. art. 41 ust. 2 Copyright Act; art. 53 Copyright Act
Expected calibration: conditional. not enough as a rule; the scope of the transfer may however follow from interpretation of the contract (art. 65 of the Civil Code), in case of doubt in favour of the author
The full key (rubric, penalties, quotation patterns from the source, known rulings) is in the repository in keys/P09_pola_eksploatacji_ogolny_zapis.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#
| Model | Condition | Block A % | Result | Card |
|---|---|---|---|---|
| GPT-6.1 Sol | W0 | 90 | ✓ | card |
| W1 | 100 | ✓ | card | |
| GPT-6 Astra | W0 | 100 | ✓ | card |
| W1 | 90 | ✓ | card | |
| GPT-5.6 Terra | W0 | 80 | ✓ | card |
| W1 | 90 | ✓ | card | |
| Claude Opus 5.5 | W0 | 75 | W | card |
| W1 | 73 | T | card | |
| Claude Sonnet 5.5 | W0 | 82 | T | card |
| W1 | 65 | FW | card | |
| Claude Haiku 5.5 | W0 | 65 | T | card |
| W1 | 55 | T | card | |
| Gemini 3.8 Flash | W0 | 64 | T | card |
| W1 | 64 | T | card | |
| Gemini 4 Argon | W0 | 77 | ✓ | card |
| W1 | 82 | T | card |
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.