Benchmark·Public sample

APEX

An expert-authored benchmark of economically valuable tasks in finance, consulting, law, and medicine.

ConfirmedConfidence: high·Last verified: 2026-08-16·How verification works
Access
Public / Open
Profile completeness 100%
Research overview ↗Dataset ↗

What it is

The AI Productivity Index assesses model performance on professional work across investment banking, management consulting, law, and primary care. Mercor provides public research, data, code, and sample-task links.

Capabilities

Only evidenced capabilities are shown as Yes. Missing evidence remains Unknown.

StatefulUnknown
Long horizonUnknown
Multi-turnUnknown
Multi-agentUnknown
AdversarialUnknown
MultimodalUnknown
Tool useUnknown
Browser useUnknown
Computer useUnknown
Code executionUnknown
File manipulationUnknown
API interactionUnknown
MCP supportUnknown
SandboxedUnknown
Deterministic resetUnknown
Stochastic behaviorUnknown
Human in the loopYes
Expert authoredYes
SyntheticUnknown
Production derivedUnknown
Real application replicaUnknown
Partial observabilityUnknown
Persistent stateUnknown
Cross-applicationUnknown

Sources & provenance

  1. Mercor · official · accessed 2026-08-16 · company-reported
  2. Mercor · dataset · accessed 2026-08-16 · confirmed

Related artifacts