#performance

Performance

Efficiency, speed, and resource usage benchmarks for financial AI systems

July 8, 20266 min read

JSONSchemaBench: Real-World Schema Complexity Breaks LLM Structured Output Guarantees

JSONSchemaBench finds coverage collapses from 86% on simple schemas to 3% on complex ones, so LLM structured output can silently emit non-compliant JSON.

Mike Thrift

llmaimachine-learning

May 31, 20265 min read

Single-Agent: equals MAS on multi-hop at equal tokens

Under equal thinking-token budgets, single-agent LLMs match or beat multi-agent systems on multi-hop reasoning—favor simpler finance agent designs.

Mike Thrift

aillmmachine-learning

Start Free→Documentation