Skip to content
CDSBench
Release analysis · draft, not yet published as a report

Gemini 2.5 Pro on CDSBench v0.1

Gemini is reliable on transferability (100%) but evidence remains its weakest category at 0%; its citations need checking before use (21.3% non-existent evidence).

Score
58.6
Previous generation
Change
Headline

What the measurements say

  • Gemini 2.5 Pro scores 58.6 on 296 verified questions, 3rd of 3 frontier models on CDSBench v0.1.
  • This is the first Gemini generation on this benchmark version, so there is no predecessor to compare with.
  • Weakest category: evidence at 0% (0/30), against 100% for Claude.
  • It cited evidence that does not exist in the record in 21.3% of answers, and answered wrongly at ≥ 80% confidence in 22.3%.
  • On the 66 verified questions it missed, Mastermind (CDSBench's own system, reference only, 91.2) answered 56 correctly.
Categories

Accuracy by category

CategoryAcc.nΔ
Evidence0%30
Fact extraction68%56
Uncertainty69%32
Deliverability73%30
Currency100%28
Maturity100%26
Seniority100%30
Entity match100%30
Multi-document100%2
Restructuring100%2
Transferability100%30
Hardest failures

Highest confidence first

The founder publishes this as a versioned report from the workbench release workflow; it then lives under /research with PDF, citation and share actions. Model page →