Skip to content
CDSBench
Benchmark category · v0.1 · 2 verified questions

Restructuring

Applying the restructuring credit-event definition to what actually happened: binding on all holders, deterioration in creditworthiness, the listed changes.

CSV
Ranking

Accuracy on restructuring questions

Compare →
#ModelAccuracyCorrect
1Claude Sonnet 5100%2/2
2Gemini 2.5 Pro100%2/2
3GPT -50%0/2
Reference · CDSBench’s own system · not ranked
Mastermind100%2/2
Common failures

How models go wrong here

Failed multi document reasoning2
Overconfident2

Across every model’s latest official run. Failure taxonomy →

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