Announcement
ClaimBench launches to test how AI models assess claims against financial documents
ValsAI says it evaluated 15 models on 1,960 claims paired with 10-K excerpts, with Decider V1.2 leading the decision models.
TLDR
ValsAI has released ClaimBench, a benchmark that tests whether a model can tell if a financial document supports, contradicts or doesn’t address a claim. The company says it evaluated 15 models on 1,960 claims paired with 10-K excerpts, with Decider V1.2 leading the decision models.
Combined views
10.1K
3 Sources, first seen ago
