APEX-Agents
Benchmarks & Leaderboards · Free + paid
Measures whether frontier AI agents can execute real long-horizon tasks
At a glance
- Made by
- Mercor
- Korean
- None (English and a few others only)
- Available on
- Web
- Open source
- Open source (license name not stated)
What is APEX-Agents?
APEX-Agents is a benchmark that evaluates AI agents on the real work of investment banking analysts, management consultants, and corporate lawyers. It has 240 tasks and grading rubrics across 31 "worlds" built by industry experts, and agents complete the tasks using software that people use. Mean Score and Pass@1 are assigned using expert-written grading criteria and an LM judge. The dataset and Archipelago, the execution and evaluation infrastructure, are released as open source, while the full set of tasks is kept private.
- 31 worlds, 240 tasks, and grading rubrics
- Evaluates 3 job roles: investment banking, consulting, and law
- Mean Score and Pass@1 metrics
- Top models shown by job role
- Public evaluation harness (GitHub) and sample tasks (HuggingFace)
- Archipelago execution and evaluation infrastructure
Who uses APEX-Agents and for what
- AI researchers compare agent performance on professional work
- Companies purchase training data licenses
Pricing
Free (public benchmark/leaderboard)
Mostly free leaderboards/datasets released for academic and community purposes
Estimate based on AI knowledge - please verify on the official site
AI tools similar to APEX-Agents (alternatives)
APEX-Agents vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| APEX-Agents | Free + paid | 0 | 11 | — | — | No |
| ARC-AGI-2 | Free + paid | 0 | 11 | — | — | No |
| Context-Bench | Free + paid | 0 | 11 | — | — | No |
| MCP Atlas | Free + paid | 0 | 11 | — | — | No |
| OSWorld | Free + paid | 0 | 5 | — | — | — |
0 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
APEX-Agents on AI Galaxy Map
- One of 27 AI tools in the Benchmarks & Leaderboards field.
- Connected to 11 other tools — #6 in its field.
Frequently asked questions
Can I use APEX-Agents for free?
Free (public benchmark/leaderboard). Prices can change, so check the official site before paying.
What AI can I use instead of APEX-Agents?
Tools that do the same job, such as ARC-AGI-2, Context-Bench, MCP Atlas, OSWorld, are connected to it on the map.
Can I use APEX-Agents in Korean?
None (English and a few others only)
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.