Economics Index
Assesses model performance across the economics domain. Capabilities evaluated include domain-specific knowledge (microeconomics, macroeconomics, public finance), analysis and forecasting, research synthesis, quantitative modeling, and more.
See representative workflowsThe Artificial Analysis Economics Index combines performance across benchmarks chosen for economics work, spanning economics knowledge, agentic execution, reasoning, and long-context reading. We map common tasks from O*NET occupational classifications, then select benchmarks that represent this real-world work. Weights are derived from how often capabilities appear across those tasks.
This composite metric provides a single score for tracking model performance across economics tasks. All underlying benchmarks are run independently by Artificial Analysis. See our Intelligence Benchmarking Methodology for how evaluations are conducted.
| Capability | Weight | Evaluations |
|---|---|---|
| Economics Knowledge | 35% | AA-Omniscience Business Accuracy |
| Reasoning | 35% | HLE |
| Agentic Knowledge Work | 25% | GDPval-AA v2 and AA-Briefcase |
| Long-Context Reasoning | 5% | LCR |
Score
Artificial Analysis Economics Index
Artificial Analysis Economics Index: Capability Breakdown
Capability Breakdown
Artificial Analysis Economics Index: Economics Knowledge
Representative Workflows
Real-world workflows that exercise the capabilities the Economics Index weights most heavily.
Example: Estimate the impact of a proposed tariff change by applying incidence and elasticity theory to trade data, then quantify the resulting welfare trade-offs.
Example: Reconcile two studies reaching opposite conclusions on the same minimum-wage question to read both in full, compare their identification strategies, and recommend the more defensible interpretation.
Example: Build a forecasting workbook in Python that ingests several FRED data series to run a baseline ARIMA model, chart the projections, and produce a short written interpretation of the outputs.
Cost
Artificial Analysis Economics Index: Cost per Task
Artificial Analysis Economics Index vs. Cost per Task
Speed
Artificial Analysis Economics Index: Time per Task
Output Tokens
Artificial Analysis Economics Index: Output Tokens per Task
Release Date
Artificial Analysis Economics Index vs. Release Date
Frequently Asked Questions
Based on the Artificial Analysis Economics Index, the top-performing AI models for economics work are currently Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) (62), Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback) (62), and Claude Opus 5 (Adaptive Reasoning, Max Effort) (61). Rankings are updated as new models are released.
Yes. The Economics Index from Artificial Analysis is an independent benchmark of how AI models perform on economics work. It measures performance on the economics domain, including economics knowledge, quantitative reasoning, agentic execution, and long-context analysis.
The Economics Index is a composite benchmark from Artificial Analysis that assesses model performance across the economics domain. Capabilities evaluated include domain-specific knowledge (microeconomics, macroeconomics, public finance), analysis and forecasting, research synthesis, quantitative modeling, and more.
The Economics Index is calculated as a weighted average of its capability sub-scores. The sub-scores and their weights are: Economics Knowledge (35%), Reasoning (35%), Agentic Knowledge Work (25%), and Long-Context Reasoning (5%).
The Economics Index includes AA-Omniscience Business Accuracy, HLE, GDPval-AA v2, AA-Briefcase, and LCR.
Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) currently has the highest Economics Index score, with a score of 62 among models with published results. View model
A higher Economics Index score indicates stronger overall performance across the benchmarks that make up the index. For a specific use case, individual benchmark results may be more informative than the composite score.