CortexRetrievalBench: New benchmark tests retrieval on financial docs with 140 diligence queries

Exp_Mark · x · 2026-10-03

micro1 released CortexRetrievalBench, a benchmark for evaluating retrieval and reranking systems on financial documents.

• The benchmark pairs a corpus of financial documents with 140 diligence queries, each tied to the authoritative sources that should answer it.
• Systems are scored on whether they retrieve the right documents and rank them at the top.
• The hardest case is when multiple documents look suitable — e.g. a current filing vs. a superseded one, or a primary source vs. a secondary summary. Across tested systems, the authoritative document often failed to appear in the top positions.

Original post →

More from Research

• Creative chess puzzle generation with diffusion models: new RL recipe, open weights — TZahavy · 2026-10-03
• Traditional nDCG agrees with humans only 53% of the time, RCP-nDCG hits 97% — Nils_Reimers · 2026-10-03
• MemFold: Fixed-Budget Soft Memory Tops PersonaMem via On-Policy Optimization — Jingxuan Wu · 2026-10-03
• AI agents still fall short of scientists, yielding far fewer insights — typewriters · 2026-10-03
• ezyang's DeepSeek-V3 series part 3: roofline analysis for training DSv3 on Hopper — ezyang · 2026-10-03
• 36B Open-Source Robot Model Isaac 0.5 Runs Real-Time Under 50ms Without Local GPU — AkshatS07 · 2026-10-03

Research channel →