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
Gemini 4 Carbon solidified its position at the top of the leaderboard with a score of 88.38, while Moonshot AI's Kimi K3.1 Pro entered the ranked leaderboard at position 13 with a score of 74.61. NVIDIA expanded its transcription portfolio with Nemotron 3.5 Transcribe 30B A4B.
Google
Gemini 4 Carbon Tightens Its Lead
Google's Gemini 4 Carbon nudged up to 88.38, extending its margin at the top of the overall leaderboard. Claude Opus 5.5 holds rank 2 (score unchanged), while GPT-6 Astra at rank 3 slipped a fraction to 86.07 — keeping the top three stable but confirming Carbon's growing cushion.
Kimi K3.1 Pro Joins the Ranked Leaderboard
The debut pushes GPT-5.5 Pro down one slot to rank 14.
NVIDIA
NVIDIA Adds a Specialized Transcription Model
NVIDIA's Nemotron 3.5 Transcribe 30B A4B joined the model field today, extending the Nemotron 3.5 family into automatic speech recognition with a 30-billion-parameter mixture-of-experts architecture.
Seven New Benchmarks Expand Evaluation Coverage
Seven new benchmarks entered the field on October 30, bringing the total to 3,668. While specific titles are spread across agentic, reasoning, and domain-specific categories, the additions continue the October trend of broad benchmark growth that has added hundreds of evaluations over the month.
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?
- 71 companies we track sell RL environments, evals or verifiers, among them AfterQuery, HUD, Mercor, Symbal, Turing, Align AI, BenchFlow and Cua. 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.