Expert agentic work
APEX-Agents
expert-level agentic work tasks (AI Productivity Index)
Rankings
Higher is betterAPEX-Agents — frequently asked questions
- What is APEX-Agents?
- expert-level agentic work tasks (AI Productivity Index)
- Which AI model scores highest on APEX-Agents?
- Grok 4.6 by SpaceXAI holds the best APEX-Agents result among tracked models, at 57.5% (released Aug 12 2026). Higher scores are better on this benchmark.
- What are the top 2 models on APEX-Agents?
- 1. Grok 4.6 (SpaceXAI) — 57.5%; 2. Grok 4.5 (SpaceXAI) — 47.1%.
- How many models have a published APEX-Agents score?
- 2 tracked models have a published APEX-Agents score. Scores are the figures reported by each lab at that model's release, so this page is a record of results over time rather than a re-run leaderboard.