RL environments and AI benchmarks, cataloged daily.
Who builds RL environments, who funds them and how models score, rebuilt every morning from public sources. Every placement links to the line on the company's own site that puts it there.
Today in RL
November 4, 2026 brought two new benchmarks and one new model. OpenAI introduced LifeVal, a practical everyday-task benchmark for personal assistants, and IBM Research launched ScarfBench, targeting enterprise Java migration across Jakarta EE, Quarkus, and Spring. Phonic debuted its first model, Phonic-1. Three Design Arena leaderboards and the Artificial Analysis Speech Arena each added new evaluation entries.
OpenAI
OpenAI Launches LifeVal
Benchmarking the Personal Assistant: LifeVal evaluates how well AI handles the practical tasks people delegate to a personal assistant — finding childcare, navigating government services, budgeting, shopping, and caregiving. The benchmark signals a shift in evaluation focus from narrow reasoning puzzles toward the messy, multi-step real-world tasks that determine whether AI is genuinely useful in daily life.
IBM
IBM Research Targets Enterprise Java Migration with ScarfBench
ScarfBench challenges coding agents to migrate complete enterprise Java applications across three major frameworks — Jakarta EE, Quarkus, and Spring — while keeping them functional throughout. The benchmark addresses a high-value, high-risk category of software engineering that existing code benchmarks rarely touch: large-scale legacy modernization.
Phonic Enters the Model Field with Phonic-1
Phonic-1 is the debut model from Phonic, marking the company's first entry into the AI model landscape. No benchmark scores are yet attached, making it one to watch as evaluations come in.
Multimodal and Audio Leaderboards Continue Steady Growth
Design Arena's Frontend Web Apps, SVG Design, and Text to Speech leaderboards each gained a new human-preference evaluation entry, while Artificial Analysis Speech Arena — Provider Voices grew from 100 to 103 evaluated voices. The consistent week-over-week expansion of these community-judged arenas reflects sustained demand for preference-based evaluation of generative and multimodal AI.
The catalog
The top of each list. Every list has a full table, sortable and filterable.
Models
By overall score
- 1Gemini 4 Carbon88.38
- 2Claude Opus 5.586.29
- 3GPT-6 Astra86.07
- 4GPT-6.1 Sol85.27
- 5Gemini 4 Argon82.28
RL environment companies
By tier, X reputation, benchmarks built
Benchmarks
S tier: the ones frontier labs report
Infrastructure companies
By tier, X reputation, benchmarks built
Browse by domain
All 92 domains and labelsOn the map. Our domains: every company and benchmark sits in one, placed by a quote from its own site or paper.
- Coding
- Enterprise work
- Health and bio
- Computer use
- Math
- Science
- Finance
- Legal
- Media
- Security
- Games
- Robotics
- Multi-domain
- Chip design
Directory labels. Tags other catalogs put on entries. Not domains on the map.
- Agentic
- Multimodal
- Reasoning
- Long-Horizon
- Knowledge
- Safety
- Decision Models
- Multilingual
- Long Context
- Video
The other 68 pages
More pages for domains on the map
- Business Enterprise work
- Biomedicine Health and bio
- Private Codebases Coding
- Software Engineering Coding
- Multi-Domain Multi-domain
- Biology Health and bio
- Robotics Robotics
- Gui Computer use
- Creative Media
- Materials Science
- Creative Media Media
- Security Security
- Chemistry Science
- Spreadsheets Enterprise work
- Browser Computer use
- Text TO Sql Coding
- Games Games
- Image Generation Media
- Video Generation Media
More directory labels
- Retrieval
- Instruction Following
- Vision
- Multimodal Understanding
- Alignment
- Behavioral
- Tool Use
- Generalization
- Speech
- Spatial Reasoning
- Data
- Factuality
- Language
- Document Understanding
- Translation
- Education
- Domain
- Geospatial
- Search
- General Knowledge
- Machine Learning
- ML
- Classification
- Inference
- Question Answering
- Korean
- Aerospace
- Efficiency
- Language-understanding
- Summarization
- Tabular
- Uncategorized
- Writing
- Human-preference
- Mobile
- Structured Output
- Document-ai
- Ocr
- Climate
- Energy
- Meta
- Truthfulness
- Weather
- Self Improvement
- Autonomy
- Law
- Openness
- Professional
- Rlhf
The map
Every company we track, placed in the domain it leads with. Click one for the line on its own website that puts it there.
Every company we track, whatever it sells, placed in the domain it leads with. Companies that cover many domains with none leading sit in the middle.
Domains
The galaxy could not load. See every vendor on the board.
How to read it
A company, in the domain its own site leads with. The logo is its own; the glow is what it mainly sells.
Also covers: a ring at a domain's edge for a company that leads with another domain but also covers this one. A faint line runs to where it leads.
Dots around it: the other things it sells. Hollow while it is still expanding into them.
Click any star for the lines from its own website that put it there.
How to read it
A benchmark, in the domain most of its tasks are in. The logo is who built it.
Also covers: a benchmark mostly about another domain that also tests this one.
Lineage: a line from a benchmark to one built on it: its next version, a subset, an extension, or an index that combines it.
Click any star for the line from its own page or paper that put it there, and to light its lineage.
Research
All research posts- OpenAI now runs every frontier RL training run in an offline copy of the web: what its containment red team means for RL environments
- 94 AI benchmarks in one week: 54 came from papers, and 29 of 40 leaderboard additions were versions of existing benchmarks
- Penalize a reward hack and it goes silent: Gemini 4 Argon's hidden shortcuts tripled after a chain-of-thought penalty
- RL environment vendors are now the sandbox industry's customers: Daytona at a $1B valuation, Modal's sandboxes at a $300M run rate
In short
RL environments, in short
- What are RL environments?
- 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. More in the glossary.
- Who sells RL environments?
- 73 companies we track sell RL environments, evals or verifiers, among them AfterQuery, HUD, Mercor, Symbal, Turing, Align AI, BenchFlow and Contra Labs. Each is placed by a line from its own website; see them all on the RL environments page.
- What is the difference between an RL environment and a benchmark?
- An RL environment is for training: a model practises in it and a grader scores each attempt. A benchmark or eval is for measuring: a fixed, held-out set of tasks with fixed scoring, used to measure and compare models. Never trained on, so the score means something. Used to measure models.
- What are the main AI benchmarks for agents and LLMs?
- Among the most referenced: Humanity's Last Exam, Terminal-Bench 2.1, SWE-bench Verified, AIME 2025, Terminal-Bench Hard, GPQA Diamond, GPQA-D and MMLU-Pro. See the full AI benchmarks list.
- Where does this data come from?
- Every placement is read from the company's own website or the benchmark's own page or paper, quoted and linked, and the catalog is rebuilt daily from public sources. How the data is built.
From the builders
What vendors are posting
The newest post on X from each RL environment vendor we track, refreshed with every build. Scroll the feed for more. How we find their accounts.