RL Environments and AI Benchmarks by Domain
Two kinds of page. Domains on the map are our own: every company and benchmark is placed in one by a quote from its own site or paper. Directory labels are tags other catalogs put on entries; they have no place of their own on the map.
14 domains on the map, 33 pages · 59 directory labels · snapshot 2026-11-05
See who sells what in each domain on the map →
Domains on the map
Each has an area on the map. Some have more than one page, one per label catalogs use for it.
- Coding42 env · 352 bench 394
- Enterprise Workflows as Enterprise work28 env · 139 bench 167
- Healthcare as Health and bio2 env · 148 bench 150
- Computer Use23 env · 95 bench 118
- Math5 env · 95 bench 100
- Science7 env · 70 bench 77
- Finance8 env · 61 bench 69
- Business as Enterprise work0 env · 67 bench 67
- Biomedicine as Health and bio0 env · 59 bench 59
- Legal2 env · 53 bench 55
- Audio as Media1 env · 44 bench 45
- Cross-domain as Multi-domain0 env · 40 bench 40
- Cybersecurity as Security1 env · 38 bench 39
- Game as Games0 env · 34 bench 34
- Embodied as Robotics0 env · 32 bench 32
- Private Codebases as Coding7 env · 24 bench 31
- Software Engineering as Coding0 env · 27 bench 27
- Multi-Domain6 env · 12 bench 25
- Biology as Health and bio0 env · 22 bench 22
- Robotics0 env · 22 bench 22
- Gui as Computer use0 env · 17 bench 17
- Creative as Media4 env · 8 bench 12
- Materials as Science0 env · 10 bench 10
- Creative Media as Media0 env · 8 bench 8
- Security4 env · 2 bench 6
- Chemistry as Science0 env · 5 bench 5
- Spreadsheets as Enterprise work0 env · 5 bench 5
- Browser as Computer use3 env · 0 bench 3
- Chip Design2 env · 1 bench 3
- Text TO Sql as Coding0 env · 3 bench 3
- Games1 env · 0 bench 1
- Image Generation as Media0 env · 1 bench 1
- Video Generation as Media0 env · 1 bench 1
Directory labels
Tags other catalogs put on entries, mostly benchmarks. Each page shows where its entries sit on the map.
- Agentic0 env · 477 bench 477
- Multimodal0 env · 254 bench 254
- Reasoning0 env · 156 bench 156
- Long-Horizon26 env · 122 bench 148
- Knowledge0 env · 144 bench 144
- Safety0 env · 123 bench 123
- Decision Models0 env · 84 bench 84
- Multilingual0 env · 51 bench 51
- Long Context0 env · 40 bench 40
- Video0 env · 36 bench 36
- Retrieval0 env · 35 bench 35
- Instruction Following0 env · 34 bench 34
- Vision0 env · 34 bench 34
- Multimodal Understanding0 env · 33 bench 33
- Alignment3 env · 29 bench 32
- Behavioral0 env · 32 bench 32
- Tool Use3 env · 27 bench 32
- Generalization0 env · 31 bench 31
- Speech0 env · 31 bench 31
- Spatial Reasoning0 env · 30 bench 30
- Data0 env · 25 bench 25
- Factuality0 env · 25 bench 25
- Language0 env · 24 bench 24
- Document Understanding0 env · 23 bench 23
- Translation0 env · 22 bench 22
- Education0 env · 20 bench 20
- Domain0 env · 15 bench 15
- Geospatial0 env · 14 bench 14
- Search0 env · 12 bench 12
- General Knowledge0 env · 11 bench 11
- Machine Learning0 env · 11 bench 11
- ML7 env · 4 bench 11
- Classification0 env · 9 bench 9
- Inference0 env · 9 bench 9
- Question Answering0 env · 9 bench 9
- Korean0 env · 8 bench 8
- Aerospace0 env · 7 bench 7
- Efficiency0 env · 7 bench 7
- Language-understanding0 env · 7 bench 7
- Summarization0 env · 7 bench 7
- Tabular0 env · 6 bench 6
- Uncategorized0 env · 6 bench 6
- Writing0 env · 6 bench 6
- Human-preference0 env · 5 bench 5
- Mobile0 env · 5 bench 5
- Structured Output0 env · 5 bench 5
- Document-ai0 env · 4 bench 4
- Ocr0 env · 4 bench 4
- Climate0 env · 3 bench 3
- Energy0 env · 3 bench 3
- Meta0 env · 3 bench 3
- Truthfulness0 env · 3 bench 3
- Weather0 env · 3 bench 3
- Professional0 env · 2 bench 2
- Self Improvement0 env · 2 bench 2
- Autonomy0 env · 1 bench 1
- Law1 env · 0 bench 1
- Openness0 env · 1 bench 1
- Rlhf1 env · 0 bench 1