Benchmark category · v0.1 · 28 verified questions
Currency
Identifying the currency of denomination and testing the specified-currency characteristic, including redenominations and multi-currency series.
Ranking
Accuracy on currency questions
| # | Model | Accuracy | Correct | |
|---|---|---|---|---|
| 1 | Claude Sonnet 5 | 100% | 28/28 | |
| 2 | GPT -5 | 100% | 28/28 | |
| 3 | Gemini 2.5 Pro | 100% | 28/28 | |
| Reference · CDSBench’s own system · not ranked | ||||
| — | Mastermind | 100% | 28/28 | |
Common failures
How models go wrong here
| Evidence selection failure | 46 |
| Hallucinated evidence | 10 |
Across every model’s latest official run. Failure taxonomy →
Hardest questions
Most models wrong
Every model answered every question in this category correctly.
Latest
Most recently published questions
- #290 Halvard Steel AG 2028 (C)2026-09-15
- #280 Republic of Norland 2027 (C)2026-09-15
- #270 Solvane Airlines S.A. 2026 (B)2026-09-15
- #261 Commonwealth of Tessaly 2025 (B)2026-09-15
- #251 Calder Chemicals N.V. 2024 (B)2026-09-15
Cases
28 cases with currency questions
- Halvard Steel AG 2028 (C) Halvard Steel AG · 2028
- Federal Republic of Aurelia 2028 Federal Republic of Aurelia · 2028
- Brightwater Energy Corp 2028 (B) Brightwater Energy Corp · 2028
- Northgate Shipping Ltd 2028 Northgate Shipping Ltd · 2028
- Republic of Norland 2028 (B) Republic of Norland · 2028
- Republic of Marovia 2028 (B) Republic of Marovia · 2028
- Orinoco Retail Holdings plc 2027 Orinoco Retail Holdings plc · 2027
- Solvane Airlines S.A. 2027 Solvane Airlines S.A. · 2027
- Federal Republic of Aurelia 2027 (B) Federal Republic of Aurelia · 2027
- Northgate Shipping Ltd 2027 (B) Northgate Shipping Ltd · 2027
- Republic of Norland 2027 (C) Republic of Norland · 2027
- United Provinces of Kestrel 2027 United Provinces of Kestrel · 2027
and 16 more in the case explorer.
Following this category sends an email only when meaningful new currency questions are published, a model’s currency accuracy moves materially, or a research report on it is published. No newsletter.