Open Brain
AI EngineerVideoSource Linked

Our Smaller Model Beat Opus on Finance Tasks - Alexander Shevchenko, Ramp

Ramp describes three ways applied research can improve production agents: a finance specialist model, prebuilt compressed context, and large parallel security sweeps. The gains target latency, cost, and coverage.

AI Engineer · Nov 4, 2026
Open Source Open MarkdownOpen JSON
Source Summary

Ramp says it post-trained a **35B Qwen 3.5** model for financial question answering, reporting higher exact-task accuracy than Opus 4.6 at lower latency. It also describes preparing compressed context overnight for recurring finance work and using **10,000 parallel agents** to scan its systems; the sweep found **seven high-severity vulnerabilities** that were patched.

Practical Implication

For builders, identify a recurring task where frontier orchestration is costly, then test a specialist model or prepare context ahead of time. For broad security checks, parallel agents can expand coverage; Ramp reports open-weight models were up to **five times cheaper** with detection rates that were not five times lower.

Agent-Ready Context
Ramp says it post-trained a **35B Qwen 3.5** model for financial question answering, reporting higher exact-task accuracy than Opus 4.6 at lower latency. It also describes preparing compressed context overnight for recurring finance work and using **10,000 parallel agents** to scan its systems; the sweep found **seven high-severity vulnerabilities** that were patched.

For builders, identify a recurring task where frontier orchestration is costly, then test a specialist model or prepare context ahead of time. For broad security checks, parallel agents can expand coverage; Ramp reports open-weight models were up to **five times cheaper** with detection rates that were not five times lower.

These are Ramp’s reported results, and the talk gives no benchmark setup or full cost and latency measurements. Cartridges may later be offered through model APIs, so their current implementation advantage could change.
Connected Context · Feed7 Judgment

Ramp's report supports trying a specialist model and prepared context on recurring, bounded work, and describes parallel agents as a way to broaden security scanning. The claimed accuracy and cost advantages remain Ramp-reported: without benchmark setup or full measurements, they do not establish a general model-selection rule or transfer to everyday coding.

Context Map
agentsecuritydata#harness-engineering#context-caching#agent-evals
Uncertainty
These are Ramp’s reported results, and the talk gives no benchmark setup or full cost and latency measurements. Cartridges may later be offered through model APIs, so their current implementation advantage could change.