Domain on the map
Multi-domain RL environments and general AI benchmarks
Builders and suites that span many subject areas at once, such as expert networks covering several professions and benchmarks that mix coding, finance and other professional work.
- RL environments
- 11
- AI benchmarks
- 11
- Shares entries with
- 15 categories
Snapshot 2026-11-05. How categories are built · Where the data comes from
In short
- What are RL environments for many domains at once?
- A simulated workplace where an AI agent practises a task (a code repository, a browser, business software) and an automatic grader scores each attempt. Labs train on thousands of these attempts. Bought to improve models. For many domains at once, that means builders and suites that span many subject areas at once, such as expert networks covering several professions and benchmarks that mix coding, finance and other professional work.
- Who builds RL environments for many domains at once?
- Scale AI, Snorkel AI, AfterQuery, Mercor, micro1 and Handshake, among 11 confirmed below.
- What are the main multi-domain benchmarks?
- SWE-bench Pro, APEX, FinanceBench, TRAIL, CoreCraft and Realm, among 10 confirmed below.
RL environments 11
-
Scale AI
No line from its own site or paper places it in Multi-Domain yet; the catalog lists it here.
-
Snorkel AI
Sells RL environments“Snorkel helps frontier labs and AI teams develop specialized training data and environments that set their models and agents apart.” source ↗
-
AfterQuery
Sells RL environments“Provides custom RL environments built on top of real APIs, MCP servers, and developer tools” source ↗
-
Mercor
Sells RL environments“Benchmarks and RL environments built on real professional work (APEX).” source ↗
-
micro1
Sells RL environments“RL environments that mirror real-world scenarios to generate world-class human data for agentic actions and elevate model reasoning” source ↗
-
Handshake
Sells RL environments“Gandalf runs inside the rollout environment, uses the same tools as the agent, and beats the strongest baseline at ~10x less cost.” source ↗
-
Surge AI
Sells RL environments“We create rich, complex RL environments that challenge agentic models in novel ways, and design verifiers that reward their behavior.” source ↗
-
Toloka
Sells RL environments“Push your agent on context-rich simulated environments and specialized RL-gyms.” source ↗
-
Fleet AI
Sells RL environments“an applied research lab dedicated to the scale out of environments - diverse and high-fidelity training gyms that accurately model the real world” source ↗
-
Patronus AI
Sells RL environments“We build simulated applications and workflows where agents can execute complex tasks, delivered to run within your training infrastructure.” source ↗
-
Pareto
No line from its own site or paper places it in Multi-Domain yet; the catalog lists it here.
AI benchmarks 11
-
SWE-bench Pro
No line from its own site or paper places it in Multi-Domain yet; the catalog lists it here.
-
APEX
Mercor · built it“the AI Productivity Index (APEX), Mercor’s family of benchmarks that measure economically valuable capabilities” source ↗
-
FinanceBench
No line from its own site or paper places it in Multi-Domain yet; the catalog lists it here.
-
TRAIL
No line from its own site or paper places it in Multi-Domain yet; the catalog lists it here.
-
CoreCraft
Surge · built it“We introduce CoreCraft, the first environment in EnterpriseBench, Surge AI's suite of agentic RL environments.” source ↗
-
Realm
micro1 · built it“We built Realm legal-reasoning to evaluate legal reasoning as a skill that develops across multiple steps.” source ↗
-
AppBench
No line from its own site or paper places it in Multi-Domain yet; the catalog lists it here.
-
Leap
Pareto · built it“we built LEAPBench (Learning Efficiency in Adaptive Processes): a benchmark intentionally designed to measure the in-context learning efficiency of LLMs” source ↗
-
Attune
Pareto · built it with others“This work was a collaboration between Pareto AI’s Research team, led by Mark Whiting, and Thoughtful Lab, led by Karina Nguyen.” source ↗
-
Toloka Arena
Toloka · built it“Compare leading LLMs on our suite of private benchmarks.” source ↗
1 not yet confirmedListed in the catalog; no line from its own site or paper confirms it yet.
Data 23
-
AfterQuery
Sells data“Draws on 300,000+ verified practitioners across medicine, law, finance, engineering, and more” source ↗
-
Align AI
Sells data“we source, verify, and manage hundreds of licensed domain experts — clinicians, scientists, operators — within days, not months.” source ↗
-
Anthromind
Sells data“Fully managed, large-scale data curation with dedicated expert teams.” source ↗
-
Aptura
Sells data“Physicians, attorneys, and investment analysts with years of high-stakes experience, supported by a platform built for structured, high-quality data collection at scale.” source ↗
-
Aviro
Sells data“We turn these worlds into post-training datasets and reinforcement learning environments” source ↗
-
Collinear
Sells data“500B+ tokens of agent training data generated” source ↗
-
Handshake
Sells data“Exploring why human judgment, skill, and expertise remain essential to training modern AI and how people shape the future of artificial intelligence.” source ↗
-
HUD
Sells data“DataVendorConnect post-training suppliers with labs.” source ↗
-
Huzzle Labs
Sells data“Our **AI recruiter** sources vetted specialists for any domain, on demand.” source ↗
-
Mercor
Sells data“30k+ experts: physicians, lawyers, engineers, consultants.” source ↗
-
micro1
Sells data“We're building the infrastructure for advancing intelligence through expert human data, real-world training environments, and contextual evaluations” source ↗
-
Patronus AI
Sells data“Expert-validated outputs that establish what successful completion looks like” source ↗
-
ReasonCore
Sells data“We produce exclusive and off-the-shelf (OTS) datasets built around multi-step hierarchical reasoning, tool-augmented workflows, and domain-specific problems” source ↗
-
Refresh
Sells data“Email contact@refresh.dev to request environments or discuss a bespoke dataset” source ↗
-
Rise Data Labs
Sells data“We power training, evaluation, and next-gen generative AI with elite US-based, context-aware human trainers paired with automation that scales quality.” source ↗
-
Scale AI
Sells data“We source contributors with precision (25% have advanced degrees) and deliver at the bar frontier AI demands.” source ↗
-
Snorkel AI
Sells data“Snorkel helps frontier labs and AI teams develop specialized training data and environments that set their models and agents apart.” source ↗
-
Surge AI
Sells data“We look for the most brilliant minds on the planet in every domain – doctors, lawyers, investment bankers, Fields Medalists, Harvard professors” source ↗
-
Symbal
Sells data“Private evals, and data for SWE, Tau, MLE, MMMU, and more” source ↗
-
Theta
No line from its own site or paper places it here yet.
-
Toloka
Sells data“Our vast network of vetted coding experts offers scalable data production for the languages, coding domains, and programming expertise of your choice.” source ↗
-
Turing
Sells data“Request dataset samples or join our global expert network to advance superintelligence.” source ↗
-
Vetto AI
Sells data“Data grounded in real expertise, from practitioners at the frontier of the sciences, medicine, law, finance, engineering, and the humanities.” source ↗
Next: pick another domain. Tags come from the RL Research daily scrape, canonicalized nightly.