All capability indexes

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.

  • ๐œยณ-Banking

    A fintech customer-support benchmark from the ๐œ-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

Measures performance in agentic workflows, focusing on behaviors like tool use, planning, autonomy, and complex problem solving.
Reasoning models are indicated by a lightbulb icon

Release Date

Artificial Analysis Agentic Index vs. Release Date

Most attractive region

Cost

Artificial Analysis Agentic Index: Cost per Task

Average cost per task (USD), broken down by input, cache hit, cache write, reasoning, and answer tokens

Average cost per task in the index. Costs are split by input, cache hit, cache write, reasoning, and answer token pricing where canonical token counts are available.

Artificial Analysis Agentic Index: Total Cost

Total cost (USD) to run the index

The cost to run the index, calculated using the model's input and output token pricing and the number of tokens used.

Speed

Artificial Analysis Agentic Index: Time per Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time ยท Lower is better

The weighted average time (minutes) per index task. This is calculated by dividing output tokens per task by output speed, weighted by the relative weights of each benchmark in the index.

Output Tokens

Artificial Analysis Agentic Index: Output Tokens per Task

Output tokens used to run one task, broken down by reasoning and answer tokens

The average number of answer and reasoning tokens produced per benchmark task in this index.

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 ๐œยณ-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.