# The AI Productivity Index (APEX)

arXiv: https://arxiv.org/abs/2509.25721 · HTML: https://mlsanity.com/paper/2509.25721/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 8 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 1 of 1)

- [Large Language Model Hacking: Quantifying the Hidden Risks of Using LLMs for Text Annotation](https://mlsanity.com/paper/2509.08825/) (2025)

## Built on by (most cited first, 10 of 10)

- [PRBench: Large-Scale Expert Rubrics for Evaluating High-Stakes Professional Reasoning](https://mlsanity.com/paper/2511.11562/) (2025)
- [APEX-Agents](https://mlsanity.com/paper/2601.14242/) (2026)
- [Remote Labor Index: Measuring AI Automation of Remote Work](https://mlsanity.com/paper/2510.26787/) (2025)
- [BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents](https://mlsanity.com/paper/2606.03829/) (2026)
- [UpBench: A Dynamically Evolving Real-World Labor-Market Agentic Benchmark Framework Built for Human-Centric AI](https://mlsanity.com/paper/2511.12306/) (2025)
- [OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding](https://mlsanity.com/paper/2607.27155/) (2026)
- [CollabSkill: Evaluating Human-Agent Collaboration On Real-World Tasks](https://mlsanity.com/paper/2606.09833/) (2026)
- [KWBench: Measuring Unprompted Problem Recognition in Knowledge Work](https://mlsanity.com/paper/2604.15760/) (2026)
- [DAYJOB: A Benchmark for Long-Horizon Professional Work](https://mlsanity.com/paper/2610.01306/) (2026)
- [MA-Bench: Measuring Operational Planning in Language Models](https://mlsanity.com/paper/2610.19138/) (2026)

## Abstract (arXiv)

We present an extended version of the AI Productivity Index (APEX-v1-extended), a benchmark for assessing whether frontier models are capable of performing economically valuable tasks in four jobs: investment banking associate, management consultant, big law associate, and primary care physician (MD). This technical report details the extensions to APEX-v1, including an increase in the held-out evaluation set from n = 50 to n = 100 cases per job (n = 400 total) and updates to the grading methodology. We present a new leaderboard, where GPT5 (Thinking = High) remains the top performing model with a score of 67.0%. APEX-v1-extended shows that frontier models still have substantial limitations when performing typical professional tasks. To support further research, we are open sourcing n = 25 non-benchmark example cases per role (n = 100 total) along with our evaluation harness.