All evaluations

AutomationBench-AA: Agentic SaaS Workflow Benchmark

A benchmark measuring agentic task completion across simulated SaaS application environments, scoring the share of each task's objectives completed without guardrail violations.

AutomationBench measures agentic task completion across simulated SaaS application environments. Unlike Zapier's own hosted AutomationBench leaderboard, which reports the percentage of tasks completed fully, AutomationBench-AA uses a headline metric representing the average share of each task's objectives a model completes without triggering guardrail violations.
The benchmark covers 657 tasks across six business domains (Finance, HR, Marketing, Operations, Sales, Support) using simulated environments for applications including Gmail, Google Sheets, Slack, Salesforce, Zendesk, Jira, and HubSpot.

All evaluations are conducted independently by Artificial Analysis. More information can be found on our Intelligence Benchmarking Methodology page.

Publication

View on arXiv

AutomationBench

Daniel Shepard, Robin Salimans.

Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and messaging platform - requiring the agent to find the right endpoints, follow a policy document, and write correct data to each system. To address this gap, we introduce AutomationBench, a benchmark for evaluating AI agents on cross-application workflow orchestration via REST APIs. Drawing on real workflow patterns from Zapier's platform, tasks span Sales, Marketing, Operations, Support, Finance, and HR domains. Agents must discover relevant endpoints themselves, follow layered business rules, and navigate environments with irrelevant and sometimes misleading records. Grading is programmatic and end-state only: whether the correct data ended up in the right systems. Even the best frontier models currently score below 10%. AutomationBench provides a challenging, realistic measure of where current models stand relative to the agentic capabilities businesses actually need.

AutomationBench-AA

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) scores the highest on AutomationBench-AA with a score of 48.6%, followed by Claude Opus 4.8 (Adaptive Reasoning, Max Effort) with a score of 48.5%, and Gemini 3.5 Flash (high) with a score of 42.6%

Objectives Completed

Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) scores the highest on Objectives Completed with a score of 73%, followed by Claude Opus 4.8 (Adaptive Reasoning, Max Effort) with a score of 72%, and Claude Sonnet 5 (Adaptive Reasoning, Max Effort) with a score of 69%

Average Violations per Task

Gemini 3.5 Flash (high) scores the lowest on Average Violations per Task with a score of 0.46, followed by Grok 4.3 (high) with a score of 0.48, and Claude Opus 4.8 (Adaptive Reasoning, Max Effort) with a score of 0.55

Score

AutomationBench-AA: Score

Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis
Reasoning models are indicated by a lightbulb icon

AutomationBench-AA reports two measures. The Score is the share of task objectives a model completes, where any task with a guardrail violation scores zero. Tasks Completed is the share of tasks completed in full, with every objective met and no guardrail violations. Higher is better for both.

Objectives Completed

AutomationBench-AA: Objectives Completed

Share of task objectives achieved, regardless of guardrail violations · Higher is better
Reasoning models are indicated by a lightbulb icon

The share of task objectives the model achieved, pooled across tasks, regardless of guardrail violations. Higher is better.

Violations

AutomationBench-AA: Objectives per Violation

Total objectives completed per guardrail violation · Higher is better
Reasoning models are indicated by a lightbulb icon

Total task objectives the model completed divided by its total guardrail violations, across the run. Higher is better.

Domain Breakdown

AutomationBench-AA: Objectives Completed Across Domains

Share of task objectives achieved, regardless of guardrail violations · Scores are normalized per domain across the models currently selected, where green represents the highest-performing selected model for that domain and red represents the lowest. Colors rescale when the selection changes.
Reasoning models are indicated by a lightbulb icon

App Breakdown

AutomationBench-AA: Objectives Completed Across Apps

Share of task objectives achieved, regardless of guardrail violations · Scores are normalized per app across the models currently selected, where green represents the best selected model for that app and red represents the worst. Colors rescale when the selection changes.
Reasoning models are indicated by a lightbulb icon

Task Breakdown

AutomationBench-AA: Average Turns per Task

Mean model turns per task
Reasoning models are indicated by a lightbulb icon

Mean number of model turns per task, across the run.

Token Usage

AutomationBench-AA: Token Usage

Tokens used to run the evaluation
Reasoning models are indicated by a lightbulb icon

The number of output tokens used to run the evaluation, including visible answer tokens and reasoning tokens where reported by reasoning models.

Cost

AutomationBench-AA: Cost per Task

Average cost per task (USD), broken down by input, cache hit, cache write, reasoning, and answer tokens
Reasoning models are indicated by a lightbulb icon

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

Score vs. Release Date

AutomationBench-AA: Score vs. Release Date

Most attractive region

Explore Evaluations

Artificial Analysis Intelligence IndexArtificial Analysis Intelligence Index

A composite benchmark aggregating nine challenging evaluations to provide a holistic measure of AI capabilities across mathematics, science, coding, and reasoning.

AA-Briefcase: Agentic Knowledge Work BenchmarkAA-Briefcase: Agentic Knowledge Work Benchmark

A private evaluation developed by Artificial Analysis for frontier agentic capability in long-horizon knowledge work, testing agents on realistic business workflows that require deliverables such as spreadsheets, presentations, and memos.

GDPval-AA v2 LeaderboardGDPval-AA v2 Leaderboard

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.

APEX-Agents-AA Benchmark LeaderboardAPEX-Agents-AA Benchmark Leaderboard

Artificial Analysis' implementation of the APEX-Agents benchmark, testing AI agents on long-horizon, cross-application tasks in professional-services environments with realistic application tooling.

𝜏²-Bench Telecom Benchmark Leaderboard𝜏²-Bench Telecom Benchmark Leaderboard

A dual-control conversational AI benchmark simulating technical support scenarios where both agent and user must coordinate actions to resolve telecom service issues.

𝜏³-Banking Benchmark Leaderboard𝜏³-Banking Benchmark Leaderboard

A fintech customer-support benchmark from the 𝜏-Knowledge framework that tests whether agents can navigate a large unstructured knowledge base and execute multi-step tool calls to resolve realistic banking workflows.

Terminal-Bench Hard Benchmark LeaderboardTerminal-Bench Hard Benchmark Leaderboard

An agentic benchmark evaluating AI capabilities in terminal environments through software engineering, system administration, and data processing tasks.

Terminal-Bench v2.1 Benchmark LeaderboardTerminal-Bench v2.1 Benchmark Leaderboard

A verified refresh of Terminal-Bench v2.0 — 89 curated tasks across software engineering, system administration, data processing, model training, and security, with environment and instruction fixes so scores reflect agent capability rather than environment gaps.

SciCode Benchmark LeaderboardSciCode Benchmark Leaderboard

A scientist-curated coding benchmark featuring 288 test set subproblems from 80 laboratory problems across 16 scientific disciplines.

Artificial Analysis Long Context Reasoning Benchmark LeaderboardArtificial Analysis Long Context Reasoning Benchmark Leaderboard

A challenging benchmark measuring language models' ability to extract, reason about, and synthesize information from long-form documents ranging from 10k to 100k tokens (measured using the cl100k_base tokenizer).

AA-Omniscience: Knowledge and Hallucination BenchmarkAA-Omniscience: Knowledge and Hallucination Benchmark

A benchmark measuring factual recall and hallucination across various economically relevant domains.

IFBench Benchmark LeaderboardIFBench Benchmark Leaderboard

A benchmark evaluating precise instruction-following generalization on 58 diverse, verifiable out-of-domain constraints that test models' ability to follow specific output requirements.

Humanity's Last Exam Benchmark LeaderboardHumanity's Last Exam Benchmark Leaderboard

A frontier-level benchmark with 2,500 expert-vetted questions across mathematics, sciences, and humanities, designed to be the final closed-ended academic evaluation.

GPQA Diamond Benchmark Leaderboard

The most challenging 198 questions from GPQA, where PhD experts achieve 65% accuracy but skilled non-experts only reach 34% despite web access.

CritPt Benchmark LeaderboardCritPt Benchmark Leaderboard

A benchmark designed to test LLMs on research-level physics reasoning tasks, featuring 71 composite research challenges.

ITBench-AA Benchmark LeaderboardITBench-AA Benchmark Leaderboard

Artificial Analysis' implementation of IBM's ITBench benchmark, testing AI agents on Kubernetes incident root-cause analysis from offline incident snapshots. The agent inspects alerts, events, traces, and topology and identifies the contributing-factor entities (deployments, pods, namespaces, network policies, etc.) responsible for the failure.

Artificial Analysis Openness IndexArtificial Analysis Openness Index

A composite measure providing an industry standard to communicate model openness for users and developers.

MMLU-Pro Benchmark LeaderboardMMLU-Pro Benchmark Leaderboard

An enhanced version of MMLU with 12,000 graduate-level questions across 14 subject areas, featuring ten answer options and deeper reasoning requirements.

Global-MMLU-Lite Benchmark LeaderboardGlobal-MMLU-Lite Benchmark Leaderboard

A lightweight, multilingual version of MMLU, designed to evaluate knowledge and reasoning skills across a diverse range of languages and cultural contexts.

LiveCodeBench Benchmark LeaderboardLiveCodeBench Benchmark Leaderboard

A contamination-free coding benchmark that continuously harvests fresh competitive programming problems from LeetCode, AtCoder, and CodeForces, evaluating code generation, self-repair, and execution.

MATH-500 Benchmark LeaderboardMATH-500 Benchmark Leaderboard

A 500-problem subset from the MATH dataset, featuring competition-level mathematics across six domains including algebra, geometry, and number theory.

AIME 2025 Benchmark LeaderboardAIME 2025 Benchmark Leaderboard

All 30 problems from the 2025 American Invitational Mathematics Examination, testing olympiad-level mathematical reasoning with integer answers from 000-999.

MMMU-Pro Benchmark LeaderboardMMMU-Pro Benchmark Leaderboard

An enhanced MMMU benchmark that eliminates shortcuts and guessing strategies to more rigorously test multimodal models across 30 academic disciplines.

AutomationBench-AA: Agentic SaaS Workflow BenchmarkAutomationBench-AA: Agentic SaaS Workflow Benchmark

A benchmark measuring agentic task completion across simulated SaaS application environments, scoring the share of each task's objectives completed without guardrail violations.