APEX Benchmarks
The APEX family of benchmarks assesses whether frontier AI models can perform economically valuable tasks across professional services, medicine, software engineering, and consumer activities.
APEX-Agents
The AI Productivity Index for Agents (APEX-Agents) measures whether frontier AI agents can execute long-horizon, cross-application tasks across three jobs in professional services.
View more
GPT 5.5 (xHigh)
38.4% ± 3.9%
GPT 5.4 (xHigh)
36.0% ± 3.8%
GPT 5.2 (xHigh)
34.4% ± 3.8%
APEX-SWE
The AI Productivity Index for Software Engineers (APEX-SWE) measures whether frontier AI agents can execute high-value engineering work, split across Observability and Integration tasks. Created by Mercor in collaboration with Cognition.
View more
GPT 5.3 Codex (High)
41.5% ± 6.3%
Opus 4.7 (Max)
41.3% ± 6.3%
Opus 4.6 (High)
40.5% ± 6.3%
APEX
The AI Productivity Index (APEX) assesses whether frontier models are capable of performing economically valuable tasks across four jobs: investment banking associate, management consultant, big law associate, and primary care physician (MD).
View more
GPT 5.4 (High)
67.2% ± 2.4%
Opus 4.6 (Max)
65.7% ± 2.6%
Opus 4.6 (High)
65.3% ± 2.7%
APEX NEWSLETTER
The latest on frontier AI performance, straight to your inbox.
New benchmarks, leaderboard shifts, and research from the APEX team.