Agentic Index
Measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.
The headline score is the average of the benchmarks listed below. Each row links to its result chart further down the page when one is available, or out to the underlying benchmark.
- GDPval-AA v2
GDPval-AA v2 is Artificial Analysis' evaluation framework for OpenAI's GDPval dataset. It tests AI models on real-world tasks across 44 occupations and 9 major industries. Models are given shell access and web browsing capabilities in an agentic loop via Stirrup to solve tasks, with Elo ratings derived from blind pairwise comparisons.
- ๐ยณ-Banking
A fintech customer-support benchmark from the ๐-Knowledge framework that tests whether agents can navigate a large unstructured knowledge base and execute multi-step tool calls to resolve realistic banking workflows.
Score
Artificial Analysis Agentic Index
Release Date
Artificial Analysis Agentic Index vs. Release Date
Cost
Artificial Analysis Agentic Index: Cost per Task
Artificial Analysis Agentic Index: Total Cost
Speed
Artificial Analysis Agentic Index: Time per Task
Output Tokens
Artificial Analysis Agentic Index: Output Tokens per Task
Frequently Asked Questions
Based on the Artificial Analysis Agentic Index, the top-performing AI models for agentic tasks are currently GPT-5.6 Sol (max) (54), Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) (53), and GPT-5.6 Sol (xhigh) (52). Rankings are updated as new models are released.
Yes. The Agentic Index from Artificial Analysis is an independent benchmark of how AI models perform on agentic tasks. It measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.
The Agentic Index is a composite benchmark from Artificial Analysis that measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.
The Agentic Index is calculated as an equal-weighted average of its underlying benchmark scores, on the same scale as the Artificial Analysis Intelligence Index.
The Agentic Index includes GDPval-AA v2 and ๐ยณ-Banking.
GPT-5.6 Sol (max) currently has the highest Agentic Index score, with a score of 54 among models with published results. View model
A higher Agentic 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.