Model failure · Orinoco Retail Holdings plc 2027 · JPY 2035 Notes · CDSBench #36 · benchmark v0.1
Gemini reached the verified outcome but cited evidence that does not exist
Question
Is the instrument transferable without the consent of the Issuer?
- Verified answer
- Yes Stated in the transfer condition.
- Gemini answered
- Yes Based on the transferable provision, the answer is YES.
- Decisive issue
- Transferability
- Evidence for the label
- Gemini cited
- 1 non-existentevidence score 0%
Failure classification
Hallucinated evidence
- Hallucinated evidence. 1 cited section id(s) do not exist in the case record.
Classifications are produced by the failure analyzer against the verified label and the evidence map; the model never grades itself. Failure taxonomy →
Everyone else
The same question, every other participant
- MastermindAbstainedanswered Reviewits failure page →
- ClaudeAbstainedanswered Reviewits failure page →
- GPTCorrectanswered Yesits failure page →
Related failures
No other transferability misses on this run
Benchmark version
v0.1
This page records Gemini’s answer from its latest official run on the frozen benchmark v0.1. If the model is re-run and the answer changes, the page shows the new result and the model page keeps the full run history. Corrections policy →
Same kind of question on your own documents?
Mastermind runs the deterministic tests, the skeptic and the evidence verification on your record. Private documents never enter the benchmark.
Analyze your own documents →