Claude · Claude Sonnet 5 · benchmark v0.1
Claude missed 4 verified fact extraction questions
Wrong answers, abstentions the record did not justify, and correct answers with unsupported evidence. Every row has a permanent page that can be cited or forwarded.
| # | Question | Category | Verified | Claude | Failure |
|---|---|---|---|---|---|
| 140 | Republic of Norland 2028 (B) · CHF 2047 Notes In which currency is the instrument denominated? Answer with the ISO currency code. | Fact extraction | CHF | Correct | Hallucinated evidence. 1 cited section id(s) do not exist in the case record. |
| 209 | Meridian Telecom S.A. 2025 (B) · EUR 2031 Notes What is the maturity date of the instrument? Answer as YYYY-MM-DD. | Fact extraction | 2031-10-10 | Correct | Hallucinated evidence. 1 cited section id(s) do not exist in the case record. |
| 219 | United Provinces of Kestrel 2026 (B) · GBP 2033 Notes In which currency is the instrument denominated? Answer with the ISO currency code. | Fact extraction | GBP | Correct | Hallucinated evidence. 1 cited section id(s) do not exist in the case record. |
| 278 | Republic of Norland 2027 (C) · JPY 2040 Notes In which currency is the instrument denominated? Answer with the ISO currency code. | Fact extraction | JPY | Correct | Hallucinated evidence. 1 cited section id(s) do not exist in the case record. |
Categories on this page: Fact extraction. Category pages explain what each one tests: fact extraction.