0

Prime Intellect

Prime Intellect is a team.

Type
team

Cite

Notes

Only stored in your browser.

Evals
0
Tools
177
Models
1
Papers
3
Boards
0
People
3

Models

1

Ranked by Artificial Analysis Intelligence Index

#ModelReleasedIntelligence
1INTELLECT-327 Nov 202522.2
1 / 1 models

Tools

177

Ifbench RL Env (Prime Intellect)

IFBench evaluation environment

RL EnvIfbench

COPY RLM RL Env (Prime Intellect)

Verbatim text copying RLM environment

RL EnvCopying

DDBC RL Env (Prime Intellect)

browsecomp with deepdive tools

RL EnvSearchQA

Harbor ENV RL Env (Prime Intellect)

Minimal Harbor environment for testing the CLI agent interception framework

RL EnvDummyCli Agent

Alphabet Sort

Toy multi-turn environment where the model must maintain and update an alphabetically sorted list of names across turns; the canonical "hello world" RL env on the Prime Intellect Hub.

RL EnvInstruction FollowingMulti Turn Dialog

Verifiers Math (math-python)

Multi-turn math problem-solving environment where the model proposes Python code in a sandbox to compute and verify numerical answers.

RL EnvMathTool CallingCode Generation

DeepDive (Serper-powered web QA)

Multi-turn open-web research QA environment where the model uses a Serper search tool to answer hard, hop-heavy questions of the BrowseComp / SimpleQA style.

RL EnvRetrievalTool CallingPlanningAgentic

DeepDive

Prime Intellect's multi-turn open-web research RL environment - model uses a Serper search tool to answer BrowseComp/SimpleQA-style hop-heavy questions; reward = answer-correctness from a judge.

RL EnvRetrievalTool CallingPlanningAgentic

mini-swe-agent-plus

Verifiers env that runs the mini-swe-agent harness inside Prime Sandboxes against real GitHub issues; reward is test-suite pass.

RL EnvCode EditingDebuggingTool CallingCode

GPU Puzzles RL Env (Prime Intellect)

An environment for GPU Puzzles by Sasha Rush.

RL Env

Reverse TEXT RL Env (Prime Intellect)

Reverse a given Chinese text; evaluated by LCS similarity between the parsed answer and ground-truth reversal.

RL EnvTransformationChineseMultilingual

Agent PLUS RL Env (Prime Intellect)

Mini SWE Agent Plus environment for solving SWE issues inside Prime Sandboxes.

RL EnvSWECode

Thematic Generalization RL Env (Prime Intellect)

This benchmark measures how effectively various LLMs can infer a narrow or specific "theme" (category/rule) from a small set of examples and anti-examples, then detect which item truly fits that theme among a collection of misleading candidates.

RL EnvReasoningSingle Choice

Jailbreak Bench RL Env (Prime Intellect)

Standardized benchmark environment for evaluating jailbreaking attacks and defenses on large language models as per JailbreakBench (NeurIPS 2024).

RL EnvLLM RobustnessJailbreaking

BFCL V 3 RL Env (Prime Intellect)

BFCL v3 evaluation environment

RL EnvTool Use

Synthetic Clocks RL Env (Prime Intellect)

Environment for evaluating LLMs on synthetic analog clock time reading tasks using image URLs and multiple reward criteria.

RL EnvVisionClocksImage UnderstandingMultimodal

Logic ENV RL Env (Prime Intellect)

Collection of challenging single-turn logic problems

RL EnvLogic

Aiderpolyglot RL Env (Prime Intellect)

Multi-turn environment for testing coding abilities across multiple programming languages using Exercism exercises

RL EnvCodingPolyglotCode

Toxicity Explanation RL Env (Prime Intellect)

Explain why a given text is toxic

RL EnvToxicity Explanation

MATH Group RL Env (Prime Intellect)

Math group environment

RL EnvMathGsm8k

Vision SR 1 RL Env (Prime Intellect)

Vision-SR1 environment (train+eval) using original graders

RL EnvVision Sr1Multi PassVlmMultimodal

Browsecomp Openai RL Env (Prime Intellect)

Tool-use environment for the model to browse the web and locate hard-to-find information; scored using an LLM-as-judge rubric

RL EnvWeb SearchTool UseWeb

Agent Bench RL Env (Prime Intellect)

A realistic virtual EHR environment to benchmark medical LLM agents on clinical tasks.

RL EnvMedicalEhrClinical

FH Aviary RL Env (Prime Intellect)

Future House Aviary wrapper for verifiers - Scientific reasoning environments with tools

RL EnvAviaryScientific ReasoningToolsScience

AGI TOOL RL Env (Prime Intellect)

ARC-AGI 1 + 2 with tool calling (Abstract and Reasoning Corpus)

RL EnvArc AGITool UseReasoningGames

Ifeval RL Env (Prime Intellect)

IFEval evaluation environment

RL EnvIfeval

DEEP Consult RL Env (Prime Intellect)

Pairwise evaluation environment for consulting-style research reports, using rubric-based GPT metrics to compare responses on instruction following...

RL EnvConsultingDeep Research

Skyrl SQL RL Env (Prime Intellect)

Multi-turn Text-to-SQL environment with interactive database feedback following SkyRL-SQL methodology

RL EnvSQLText to SQLDatabaseCode

Alphabet SORT RL Env (Prime Intellect)

This task requires the model to maintain and update an alphabetically sorted list of names across multiple conversation turns.

RL EnvSortingNamesTools

Reverse TEXT RL Env (Prime Intellect)

Reverse a given text; evaluated by LCS similarity between the parsed answer and ground-truth reversal.

RL EnvTransformation

Agentharm RL Env (Prime Intellect)

AgentHarm environment to evaluate agentic reasoning and safety

RL EnvSafetyAgentTool UseSecurity

Terminus Harbor RL Env (Prime Intellect)

Terminus agent on Harbor tasks

RL Env

Taxcalc Bench RL Env (Prime Intellect)

TaxCalcBench environment for LLM tax calculation

RL EnvTax

Acereason MATH RL Env (Prime Intellect)

Single-turn math word problems from NVIDIA AceReason-Math with boxed numeric answers and CoT.

RL EnvMath

UQ Project RL Env (Prime Intellect)

UQ: Assessing Language Models on Unsolved Questions from Stack Exchange

RL EnvUqUnsolved QuestionsStack Exchange

GREP ENV RL Env (Prime Intellect)

Reimplementation of Cognition's SWE Grep Agent

RL Env

MATH Python RL Env (Prime Intellect)

Solve math problems using Python in a sandbox environment

RL EnvTool UseMathPrime Sandboxes

R 1 ISH RL Env (Prime Intellect)

A RL environment for QA with a search tool over web or wikipedia

RL EnvSearchRAG

Simpleqa Verified RL Env (Prime Intellect)

SimpleQA-Verified evaluation environment with accuracy scoring.

RL EnvSimpleqaSimpleqa VerifiedKnowledge

Longbench V 2 RL Env (Prime Intellect)

LongBench v2 environment for evaluating and training LLMs on long-context multiple-choice reasoning tasks

RL EnvLong ContextReasoning

Misguided ATTN RL Env (Prime Intellect)

MisguidedAttention evaluation environment

RL EnvReasoningRiddles

AIME 2026 RL Env (Prime Intellect)

AIME-26 evaluation environment

RL EnvMath

Webexplorer RL Env (Prime Intellect)

WebExplorer-QA evaluation environment for long-horizon web navigation

RL EnvWeb SearchTool UseWeb NavigationWeb

Literature Review RL Env (Prime Intellect)

Generated environment

RL Env

MATH ENV RL Env (Prime Intellect)

Single-turn math training environment

RL EnvMath

HLE RL Env (Prime Intellect)

Humanity's Last Exam evaluation environment

RL EnvMulti ModalTool UseAcademicMultimodal

Deepdive RLM RL Env (Prime Intellect)

DeepDive QA RL environment with a Serper-powered search tool using RLM

RL EnvSearchQA

Bench 2 RL Env (Prime Intellect)

Terminal-Bench 2.1 Harbor taskset with Terminus2 as the default harness

RL EnvCli AgentTerminal Bench

MCP Universe RL Env (Prime Intellect)

MCP Universe environment for evaluating LLMs in wide range of tasks with MCP server

RL EnvMcpToolsTool Calling

RISK Assessment RL Env (Prime Intellect)

This environment assesses a model's ability to identify and quantify financial risks based on provided company data. It evaluates understanding of ...

RL EnvFinance

Minif2f RL Env (Prime Intellect)

Verifiers port of the minif2f benchmark

RL EnvTheorem ProvingFormal VerificationMath

Agency Bench RL Env (Prime Intellect)

HumanAgencyBench: Benchmark measuring AI assistants' support for human agency across 6 dimensions (3000 prompts, LLM-as-judge)

RL EnvHuman Agency

Graphwalks RL Env (Prime Intellect)

GraphWalks graph traversal evaluation environment (single-turn)

RL EnvLong ContextGraph

DATA DEMO RL Env (Prime Intellect)

RLMEnv demo for custom data serialization

RL EnvSerialization

WMDP RL Env (Prime Intellect)

Measuring and Reducing Malicious Use With Unlearning (WMDP)

RL EnvBiosecurity

Backend Bench RL Env (Prime Intellect)

BackendBench environment for LLM kernel benchmarking

RL EnvKernels

Writing Detection RL Env (Prime Intellect)

Environment for AI writing detection using hybrid reward system

RL EnvAI Writing Detection

Uncertaintybench RL Env (Prime Intellect)

Implementation of UncertaintyBench

RL Env

Opencode SWE RL Env (Prime Intellect)

OpenCode SWE environment for solving SWE issues inside Prime Sandboxes.

RL EnvSWECode

Diagnosis Assistant RL Env (Prime Intellect)

Generated environment

RL Env

MMLU PRO RL Env (Prime Intellect)

MMLU-Pro evaluation environment

RL EnvStemMMLU

Stepfun Prover RL Env (Prime Intellect)

A multi-turn RL environment for formal theorem proving in Lean 4, where models alternate between reasoning, sketching proof code, and receiving verifier feedback.

RL EnvMathTheorem ProvingLean4

Seeclick RL Env (Prime Intellect)

Test model's ability to correctly click on target UI

RL EnvMultimodal

Simple Bench RL Env (Prime Intellect)

A single-turn reasoning environment based on the SimpleBench dataset, where models are evaluated on their ability to answer multiple-choice questions.

RL EnvReasoning

Haystack RLM RL Env (Prime Intellect)

Needle-in-haystack environment using RLM with Python REPL

RL EnvSearchPythonCode

Verifiers

Prime Intellect's library for defining RL environments - a task dataset, a tool/sandbox harness, and a reward rubric - usable across training, eval, and synthetic-data workflows.

FrameworkRL EnvironmentsReward DesignAgentic

Writing Bench RL Env (Prime Intellect)

WritingBench eval environment

RL EnvLong Form TextCustom Prompt

Lisanbench RL Env (Prime Intellect)

Single-turn evaluation where the model is tasked to generate the longest valid chain of 1-word edits from a given starting word. The final score is the sum of the longest valid chains across all starting words.

RL EnvWord Game

Environments Hub

Prime Intellect's community-powered aggregator of versioned, train-ready RL environments - the "HuggingFace for environments."

FrameworkEnvironment AggregationAgent TrainingAgentic

TURN MATH RL Env (Prime Intellect)

Single-turn math training environment

RL EnvMath

Technical Analysis RL Env (Prime Intellect)

Technical analysis of patent claims, technical innovations, and differentiations

RL EnvPatentsAgentic SearchRAGLegal

Ascii TREE RL Env (Prime Intellect)

Single-turn evaluation where the model generates ASCII tree diagrams from prompts.

RL EnvAscii

AIME 2025 RL Env (Prime Intellect)

AIME-25 evaluation environment

RL EnvMath

Intellect MATH RL Env (Prime Intellect)

Single-turn INTELLECT-2 math problems with boxed numeric answers and CoT.

RL EnvMath

Skywork MATH RL Env (Prime Intellect)

Single-turn Skywork math problems with boxed numeric answers and CoT.

RL EnvMath

Pydantic Adherence RL Env (Prime Intellect)

Single-turn JSON-structured output validated against per-sample Pydantic models.

RL EnvStructurePydanticParsing

Deepscaler MATH RL Env (Prime Intellect)

Single-turn DeepScaleR math problems with boxed numeric answers and CoT.

RL EnvMath

General Agent RL Env (Prime Intellect)

A self-growing toolbench environment - early signs of self-improving agentic capability

RL EnvAgentTool Use

APEX Shortlist RL Env (Prime Intellect)

MathArena Apex Shortlist final-answer evaluation environment

RL EnvMathScience

Frontierscience RL Env (Prime Intellect)

FrontierScience PhD-level science evaluation environment

RL EnvScience

CUA Example RL Env (Prime Intellect)

Example environment demonstrating CUA (Computer Use Agent) mode browser automation

RL EnvBrowserBrowserbaseCuaWeb

BB Browsecomp RL Env (Prime Intellect)

BrowserEnv[DOM] Environment on Browsecomp

RL Env

Clause Identification RL Env (Prime Intellect)

This environment tests an agent's ability to review legal contracts, identify specific clauses based on given criteria, and extract relevant inform...

RL EnvLawLegal

SWE GREP RL Env (Prime Intellect)

Your environment description here

RL Env

Opencode Science RL Env (Prime Intellect)

Solve science problems using OpenCode agent via ComposableEnv.

RL EnvScienceOpencode

Oolong RLM RL Env (Prime Intellect)

Oolong long-context evaluation environment using RLM with Python REPL

RL EnvLong ContextPythonCode

ENV RLM RL Env (Prime Intellect)

Multi-turn math environment using RLM with Python REPL and hybrid verification

RL EnvMathPython

Science ENV RL Env (Prime Intellect)

A collection of challenging single-turn science problems

RL EnvScience

Verbatim COPY RL Env (Prime Intellect)

Copy auto-generated text verbatim

RL EnvCopying

TOOL TEST RL Env (Prime Intellect)

Test environment for tool use

RL EnvTool TestTool UseDebug

SELF Reward RL Env (Prime Intellect)

Environment models self-rewarding their own responses

RL EnvSelf RewardKnowledge

Gsm8k RL Env (Prime Intellect)

GSM8K environment

RL EnvGsm8kMath

Search ENV RL Env (Prime Intellect)

MCP Search Environment Example

RL Env

AND A RL Env (Prime Intellect)

Advanced Agentic RAG over patent documents for Q&A with more comparisons and lookups

RL EnvPatentsAgentic SearchRAGLegal

Sentence Repeater RL Env (Prime Intellect)

Interactively repeat sentences from a paragraph in a random order

RL EnvSentence Repeater

Color Codeword RL Env (Prime Intellect)

Multi-turn VLM environment for testing image accumulation across turns

RL EnvVlmMultimodal

Deepswe RL Env (Prime Intellect)

DeepSWE environment for solving SWE issues inside Prime Sandboxes.

RL EnvSWECode

META ARE RL Env (Prime Intellect)

Meta Research Agent Environment

RL Env

Androidworld RL Env (Prime Intellect)

AndroidWorld benchmark for evaluating autonomous agents on real Android apps with 116 tasks across 20 apps

RL EnvMobileAndroidTool UseMultimodal

Balrog Bench RL Env (Prime Intellect)

BALROG benchmark integration for verifiers: unified RL evaluation across game environments.

RL Env

Penrose Diagrams RL Env (Prime Intellect)

Environment for training LLMs to generate LaTeX/TikZ diagrams

RL EnvLatexDiagram GenerationMultimodal

Dabstep RL Env (Prime Intellect)

Data Agent Benchmark for Multi-step Reasoning benchmark

RL EnvData AnalysisOpenai CompatibleCodingCode

Kernelbench RL Env (Prime Intellect)

KernelBench environment for verifiers - GPU kernel generation benchmark

RL EnvKernelbenchPerformanceCodingCode

Psycho Bench RL Env (Prime Intellect)

PsychoBench per‑instrument and per‑subscale evaluation for LLMs

RL EnvPsychologyPersonality

Reward Bench RL Env (Prime Intellect)

Evaluates pair-wise answers from RewardBench datasets

RL EnvMulti LingualReward BenchSafetySecurity

Clockbench RL Env (Prime Intellect)

ClockBench: multimodal clock reading and reasoning benchmark implemented for verifiers.

RL EnvClockbenchMultimodalVision

Bixbench RL Env (Prime Intellect)

BixBench scientific reasoning evaluation environment

RL EnvScientific ReasoningOpen AnswerScience

Synlogic RL Env (Prime Intellect)

SynLogic evaluation environment (SingleTurn) for verifiers

RL EnvSynlogicLogicReasoning

Aidanbench RL Env (Prime Intellect)

AidanBench multi-turn environment for Verifiers

RL EnvAidanbenchNovelty

Deepscaler RL Env (Prime Intellect)

Training environment for DeepScaleR, containing single-turn math problems with rule-based grading

RL EnvMath

WEB PY RL Env (Prime Intellect)

Humanity's Last Examination (HLE) benchmark environment for prime-environments

RL EnvHleMulti ModalTool UseMultimodal

Browsecomp RL Env (Prime Intellect)

BrowseComp evaluation environment

RL EnvWeb SearchTool UseWeb

RUST Cargo RL Env (Prime Intellect)

Rust with cargo reward

RL EnvCodeRust

Livecodebench RL Env (Prime Intellect)

LiveCodeBench evaluation environment

RL EnvCode

TAU 2 Bench RL Env (Prime Intellect)

τ²-bench evaluation environment

RL EnvTool Agent UserTool UseUser Sim

Simpleqa RL Env (Prime Intellect)

SimpleQA evaluation environment

RL EnvSimpleqaKnowledge

Unscramble RL Env (Prime Intellect)

Single-turn transformation where the model unscrambles numbered sentences into the correct order.

RL EnvOrdering

Hendrycks MATH RL Env (Prime Intellect)

Single-turn Hendrycks MATH-style problems with boxed numeric answers and CoT.

RL EnvMath

Swebench PRO RL Env (Prime Intellect)

SWE-bench Pro environment backed by Harbor tasks.

RL EnvV1SWESWE BenchCode

Clause Review RL Env (Prime Intellect)

This environment tests an agent's ability to review legal contracts, identify specific clauses, and assess their compliance with predefined legal s...

RL EnvLawLegal

Legalbench RL Env (Prime Intellect)

LegalBench environment for legal reasoning tasks

RL EnvLegalbenchLegalReasoning

Wildjailbreak RL Env (Prime Intellect)

WildJailbreak eval environment

RL Env

Harmeval RL Env (Prime Intellect)

HarmEval - 550 harmful questions designed to test LLM safety alignment

RL EnvHarmevalSafetySecurity

Spiral Bench RL Env (Prime Intellect)

Multi-turn text-based environment for evaluating agents on the Spiral-Bench dataset.

RL EnvLong HorizonSafetyRiskSecurity

SWE RL Env (Prime Intellect)

SWE tasks (R2E-Gym, SWE-bench, ...).

RL EnvSWECode

GEM Wordle RL Env (Prime Intellect)

Gym-compatible Wordle environment powered by AxonRL's GEM framework

RL EnvGemReasoningGameGames

GYM ENV RL Env (Prime Intellect)

ReasoningGym suite of programmatically-generated reasoning tasks

RL EnvLogicPuzzlesMathGames

Wordle RL Env (Prime Intellect)

Wordle game environment

RL EnvTextarenaReasoningGameGames

Mastermind RL Env (Prime Intellect)

Mastermind multi-turn game environment for Verifiers

RL EnvGameReasoningGames

Enigmata RL Env (Prime Intellect)

Enigmata environment for verifiers

RL EnvEnigmataReasoningPuzzlesGames

WIKI RACE RL Env (Prime Intellect)

Environment for the game Wiki Race

RL EnvGameNavigationGames

DOM Example RL Env (Prime Intellect)

Example environment demonstrating DOM mode browser automation with Stagehand

RL EnvBrowserBrowserbaseDomWeb

MMMU RL Env (Prime Intellect)

Multimodal benchmark environment

RL EnvMultimodal

Phybench RL Env (Prime Intellect)

PHYBench eval environment

RL EnvReasoningPhysicsScience

Sycophancy EVAL RL Env (Prime Intellect)

Evaluates sycophantic behavior in LLMs across four tasks from Sharma et al. (ICLR 2024).

RL EnvSycophancyBiasLanguage Models

Doublecheck RL Env (Prime Intellect)

Test environment for double-checking math answers

RL EnvDoublecheckMathHendrycks

AIME 2024 RL Env (Prime Intellect)

AIME-24 evaluation environment

RL EnvMath

MATH 500 RL Env (Prime Intellect)

MATH-500 evaluation environment

RL EnvMath

Interaction Checker RL Env (Prime Intellect)

This environment tests an agent's ability to identify potential drug-drug interactions given a patient's current medications and a newly prescribed...

RL EnvMedicineMedical

TURN CODE RL Env (Prime Intellect)

Single-turn code training environment

RL EnvCodingCode

CODE ENV RL Env (Prime Intellect)

Single-turn code training environment

RL EnvCodingCode

Scicode RL Env (Prime Intellect)

Scicode evaluation environment

RL EnvCodePythonStem

Harbor RL Env (Prime Intellect)

Harbor (terminal-bench-style) tasks via ComposableEnv.

RL EnvTerminal Bench

TAU 3 Bench RL Env (Prime Intellect)

τ²-bench evaluation environment. Focus on tau-knowledge.

RL EnvTool Agent UserTool UseUser Sim

Opencode MATH RL Env (Prime Intellect)

Solve math problems using OpenCode agent via ComposableEnv.

RL EnvMathOpencode

Opencode Deepdive RL Env (Prime Intellect)

OpenCode DeepDive QA environment with web research tools

RL EnvSearchQA

Sudoku Solver RL Env (Prime Intellect)

Generated environment

RL Env

Opencode Lean

OpenCode Lean 4 theorem proving via ComposableEnv.

RL EnvLeanTheorem ProvingOpencodeMath

DDBC RLM RL Env (Prime Intellect)

BrowseComp with DeepDive tools using RLM

RL EnvSearchQA

Openenv ECHO RL Env (Prime Intellect)

OpenEnv Echo environment via the OpenEnvEnv adapter

RL EnvOpenenvMcpTools

RLM Secrets RL Env (Prime Intellect)

File puzzle environment for testing RLM capabilities: root tools, sub-LLM tools, file operations

RL EnvTools

Opencode Harbor RL Env (Prime Intellect)

Opencode agent on Harbor tasks

RL EnvCli Agent

MCP Atlas RL Env (Prime Intellect)

MCP-Atlas tool-use evaluation environment

RL EnvTool UseMcp

Continuation Quality RL Env (Prime Intellect)

Single-turn quality grades on base model continuations using a judge model.

RL Env

SAD RL Env (Prime Intellect)

Self-Awareness Detection (SAD) environment for measuring LLM awareness of being evaluated

RL EnvSelf AwarenessIntrospection

Opencode CP RL Env (Prime Intellect)

Solve competitive programming problems using OpenCode agent via ComposableEnv.

RL EnvCodingOpencodeCode

Medsafetybench RL Env (Prime Intellect)

Evaluating and Improving the Medical Safety of Large Language Models

RL EnvMedical SafetyMedical AI SafetyLLM Safety

CODE Debugger RL Env (Prime Intellect)

Add your description here

RL Env

TEXT Quests RL Env (Prime Intellect)

Classic Infocom interactive fiction games (Zork, Enchanter, etc.) for evaluating LLM reasoning, planning, and world modeling

RL EnvText GamesReasoningPlanning

WIKI Search RL Env (Prime Intellect)

Agentic RAG over Wikipedia pages for trivia Q&A

RL EnvWikipediaAgentic SearchRAG

Allenai Ifeval RL Env (Prime Intellect)

IFEval single-turn environment using AllenAI RLVR-IFeval

RL EnvIfevalConstraints

Diagnosis Differential RL Env (Prime Intellect)

This environment tests an agent's ability to perform differential diagnosis by iteratively gathering patient information and consulting medical kno...

RL EnvMedicineMedical

Antislop RL Env (Prime Intellect)

Rank model on anti-slop score

RL EnvCreative Writing

ART E RL Env (Prime Intellect)

ART-E: a tool-using email research RL environment for Verifiers

RL EnvEmailResearchTool Use

Vrcli RL Env (Prime Intellect)

RL for next chapter prediction for a story.

RL EnvNext Chapter PredictionLong Story GenerationPlan Generation

GPQA RL Env (Prime Intellect)

GPQA evaluation environment

RL Env

Openenv Textarena RL Env (Prime Intellect)

OpenEnv TextArena (Wordle-v0) environment via the OpenEnvEnv adapter

RL EnvOpenenvTextarenaWordleGames

AND A RL Env (Prime Intellect)

Basic agentic RAG over patent documents for Q&A

RL EnvPatentsAgentic SearchRAGLegal

Coconot RL Env (Prime Intellect)

Contextual noncompliance evaluation using the AllenAI CoCoNot dataset

RL EnvCoconotSafetySecurity

AGI 3 RL Env (Prime Intellect)

ARC-AGI-3 environment using the official agent API

RL Env

Negative Style RL Env (Prime Intellect)

ENV for self-grading for LLM Writer Style.

RL Env

Creative Writing RL Env (Prime Intellect)

Creative writing environment with multi-judge evaluation

RL EnvCreative Writing

Browsecomp PLUS RL Env (Prime Intellect)

Verifiers environment for BrowseComp-Plus Deep-Research Agent Benchmark. Controlled agent/retriever evaluation on the fixed human-verified corpus.

RL EnvSearch AgentDeep ResearchRetriever

Agent DOJO RL Env (Prime Intellect)

Benchmark for agent robustness against prompt injection attacks in tool-use scenarios

RL EnvSecurityPrompt InjectionTool Use

Deepdive RL Env (Prime Intellect)

DeepDive QA RL environment with a Serper-powered search tool

RL EnvSearchQA

UQ RL Env (Prime Intellect)

Evaluate language models on genuinely unsolved questions from Stack Exchange using oracle-free validation strategies with 3-stage sequential pipeline

RL EnvUnsolved QuestionsOracle FreeValidation

Gauss RL Env (Prime Intellect)

GAUSS (General Assessment of Underlying Structured Skills) - Comprehensive mathematical reasoning benchmark evaluating 12 structured skill dimensions

RL EnvMathematicsReasoningStructured SkillsMath

Papers

3

DeepDive: Reinforcement Learning Environments for Deep Research Agents

blog

2025

verifiers: Reinforcement Learning with LLMs in Verifiable Environments

blog

2025

Introducing the Environments Hub

blog

2025