Skip to content
CDSBench
Benchmark category · v0.1 · 30 verified questions

Seniority

Determining ranking (senior, subordinated, secured) from the terms, and testing the not-subordinated characteristic.

CSV
Ranking

Accuracy on seniority questions

Compare →
#ModelAccuracyCorrect
1Claude Sonnet 5100%30/30
2GPT -5100%30/30
3Gemini 2.5 Pro100%30/30
Reference · CDSBench’s own system · not ranked
Mastermind100%30/30
Common failures

How models go wrong here

Evidence selection failure50
Hallucinated evidence10

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

Cases

30 cases with seniority questions

and 18 more in the case explorer.

Following this category sends an email only when meaningful new seniority questions are published, a model’s seniority accuracy moves materially, or a research report on it is published. No newsletter.

Seniority — CDS benchmark category · CDSBench