Knowledge Workers ≠ Developers
The AI industry optimizes for developers. Frontier models are benchmarked on code generation, competitive math, and multi-step agentic reasoning — tasks where raw capability is the bottleneck and cost is secondary. That makes sense for developers: they write novel code, debug complex systems, and need the model to think as hard as possible.
But knowledge workers — the hundreds of millions of people in spreadsheets, email, and documents every day — have structured, domain-specific tasks where speed and cost matter more than ceiling capability. They draft reports, build trackers, write formulas. The ceiling on most of these tasks is not model intelligence; it's context, speed, and reliability.
This distinction has massive economic implications. If 80% of knowledge-worker requests can be served by a model that costs 10× less and responds 2× faster, defaulting every request to a frontier model isn't a quality strategy — it's a waste strategy.
Core Thesis
Most knowledge-worker tasks sit well within the capability of small, domain-tuned models. The right architecture is not "always use the best model" — it's "always use the right model", selected automatically by a lightweight router.
The Proof: #2 on GDPVal With a Nano Router
GDPVal is OpenAI's benchmark for real-world knowledge work — 220 tasks across 44 occupations (accountants, financial managers, engineers, clerks), each graded by human experts against professional deliverables. The GDPval-AA leaderboard by Artificial Analysis ranks 368 model configurations on these tasks.
We built a nano-model-based router that classifies each task with a sub-cent nano-class model and dispatches to either GPT-5.5 (for hard tasks) or GPT-5.4 Mini (for everything else). It reaches #2 overall:
#ModelELOClass
1GPT-5.5 (xhigh)1769Frontier
2Nano-Routed (GPT-5.5 + GPT-5.4 Mini)1759Router
3Claude Opus 4.7 (max)1753Frontier
4Claude Sonnet 4.6 (max)1676Frontier
5GPT-5.4 (xhigh)1674Frontier
6MiMo-V2.5-Pro1571Mid-tier
7DeepSeek V4 Pro (Max)1554Mid-tier
14GPT-5.4 mini (xhigh)1417Small
19Gemini Flash1197Small
GDPval-AA ELO Leaderboard (selected, June 2026). Source: Artificial Analysis.
GPT-5.4 Mini alone scores 1417. GPT-5.5 alone scores 1769. The nano-routed combination lands at 1759 — within 10 points of pure frontier — by using the cheap model wherever it's good enough and the expensive one only where it matters. It beats Claude Opus 4.7 and every other single-model entry. The cost difference between GPT-5.5 and GPT-5.4 Mini is over 10×, but the routed quality loss is just 10 ELO points.
The architecture is simple:
📝 Task User request arrives
→
Nano Classifier
Link preview
GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks
We introduce GDPval, a benchmark evaluating AI model capabilities on real-world economically valuable tasks. GDPval covers the majority of U.S. Bureau of Labor Statistics Work Activities for 44 occupations across the top 9 sectors contributing to U.S. GDP (Gross Domestic Product). Tasks are constructed from the representative work of industry professionals with an average of 14 years of experience. We find that frontier model performance on GDPval is improving roughly linearly over time, and that the current best frontier models are approaching industry experts in deliverable quality. We analyze the potential for frontier models, when paired with human oversight, to perform GDPval tasks cheaper and faster than unaided experts. We also demonstrate that increased reasoning effort, increased task context, and increased scaffolding improves model performance on GDPval. Finally, we open-source a gold subset of 220 tasks and provide a public automated grading service at evals.openai.com to facilitate future research in understanding real-world model capabilities. mukulsingh105.github.io · arxiv.org
Comments