{"total_count":1026,"offset":0,"limit":100,"data":[{"id":"vvw3kczbw5tld3qwc6eda0md","name":"mera-rumultiar","description":"MERA ruMultiAr environment for Russian RLVR.","visibility":"PUBLIC","owner":{"type":"user","name":"sofinvalery"},"created_at":"2026-04-12T20:31:54.091000","updated_at":"2026-04-12T20:31:57.202000","tags":["mera","russian","math","arithmetic","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"twszxv4wwi8qn1a2tjkz9a4s","name":"mera-mathlogicqa","description":"MERA MathLogicQA environment for Russian RLVR.","visibility":"PUBLIC","owner":{"type":"user","name":"sofinvalery"},"created_at":"2026-04-12T20:31:54.079000","updated_at":"2026-04-12T20:31:57.131000","tags":["mera","russian","math","logic","multiple-choice","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"ca8r7n8psvbn1dj3z2068fl7","name":"mera-simplear","description":"MERA SimpleAr environment for Russian RLVR.","visibility":"PUBLIC","owner":{"type":"user","name":"sofinvalery"},"created_at":"2026-04-12T20:31:54.053000","updated_at":"2026-04-12T20:31:57.136000","tags":["mera","russian","math","arithmetic","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"f31gslhirpj4lal5d8byykw8","name":"legal-cls","description":"Legal guidance and topic classification over user/assistant conversations (Verifiers environment)","visibility":"PUBLIC","owner":{"type":"user","name":"amirmohseni"},"created_at":"2026-04-11T21:56:19.009000","updated_at":"2026-04-11T22:43:48.056000","tags":["legal","classification","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.8"},{"id":"qbebs2z5jcgwse14hxxs1o6a","name":"chess-env","description":"Chess environment where an agent plays as White against configurable opponents (random, LLM, or Stockfish)","visibility":"PUBLIC","owner":{"type":"team","name":"prime"},"created_at":"2026-04-11T21:54:29.539000","updated_at":"2026-04-11T22:22:45.650000","tags":["multi-turn","game","chess","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"c42lisdyu78wo5jmraf5ykbc","name":"kernelbench-kguard","description":"KernelBench environment with KernelGuard reward hacking detection","visibility":"PUBLIC","owner":{"type":"user","name":"sinatras"},"created_at":"2026-04-09T17:41:46.601000","updated_at":"2026-04-09T19:31:56.945000","tags":["gpu","kernels","security","reward-hacking","triton"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"z46ckucktz3cn38dt4bkv9bz","name":"tau3-bench","description":"τ²-bench evaluation environment. Focus on tau-knowledge.","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-04-09T08:48:40.649000","updated_at":"2026-04-10T11:52:25.762000","tags":["tool-agent-user","tool-use","multi-turn","user-sim","sierra-research"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"s65yclnkbg8nh3bbgfzpf754","name":"first-price-auction","description":"Prime/verifiers single-turn environment for sealed-bid first-price auctions.","visibility":"PUBLIC","owner":{"type":"user","name":"yadnyesh"},"created_at":"2026-04-08T17:32:34.599000","updated_at":"2026-04-08T17:32:40.982000","tags":["single-turn","auctions","economics","strategic-reasoning","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"xiiyiwkpacoc5arfkvdm6dbe","name":"mmlu","description":"MMLU evaluator for multi-subject multiple-choice reasoning.","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-04-07T22:12:57.467000","updated_at":"2026-04-07T22:13:00.688000","tags":["mcq","general-knowledge","nlp"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"x1ah31w9cp3abilulemswtwl","name":"backdoor-toy","description":"Parameterized backdoor reward hack experiment","visibility":"PUBLIC","owner":{"type":"user","name":"jessicafeiyalipi"},"created_at":"2026-04-06T20:46:26.764000","updated_at":"2026-04-08T23:22:22.694000","tags":["reward-hacking","backdoor","toy","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.4"},{"id":"lf95nz53g6islncl4274na6t","name":"dpo-to-rupo","description":"Prime environment that learns rubrics from DPO-style preference pairs","visibility":"PUBLIC","owner":{"type":"user","name":"sumukshashidhar"},"created_at":"2026-04-05T06:57:41.839000","updated_at":"2026-04-06T09:54:30.943000","tags":["rubric-learning","dpo","rupo","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.13"},{"id":"b0fd87of2lnmbizs9xwiwrk5","name":"hermes-agent-reasoning-traces","description":"Replay RL environment built from the lambda/hermes-agent-reasoning-traces dataset.","visibility":"PUBLIC","owner":{"type":"user","name":"shekswess"},"created_at":"2026-04-04T22:15:35.569000","updated_at":"2026-04-04T22:15:39.719000","tags":["agent","tool-calling","rl","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"umkuknlsm6zovsikpx0n0pfz","name":"infraresolutionbench","description":"Prime verifiers environment for InfraResolutionBench","visibility":"PUBLIC","owner":{"type":"user","name":"kariminal"},"created_at":"2026-04-04T20:14:44.333000","updated_at":"2026-04-09T10:37:48.391000","tags":[],"stars":1,"latest_ci_status":null,"latest_version":"0.1.12"},{"id":"ea0gqlea8svokf4vbbquehe7","name":"opencode-continual-learning","description":"A continual learning environment for OpenCode","visibility":"PUBLIC","owner":{"type":"user","name":"13point5"},"created_at":"2026-04-03T21:49:03.526000","updated_at":"2026-04-04T18:35:31.416000","tags":["continual-learning","opencode","agent","multi-turn"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"qtzuj0m9mbka00p9yrwu9ag0","name":"slitherlink-env","description":"Multi-turn Slitherlink environment with exact rule-based verification","visibility":"PUBLIC","owner":{"type":"team","name":"cssavi"},"created_at":"2026-04-03T02:39:18.514000","updated_at":"2026-04-04T00:18:06.320000","tags":["slitherlink","puzzle","reasoning","constraints","grid","multi-turn","train","eval"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.8"},{"id":"gwuuesuxjj0hqgnbfnq9ygtf","name":"reasoning-gym-env","description":"ReasoningGym suite of programmatically-generated reasoning tasks","visibility":"PUBLIC","owner":{"type":"user","name":"israel-adewuyi"},"created_at":"2026-04-02T10:09:08.369000","updated_at":"2026-04-03T11:31:42.059000","tags":["reasoning-gym","logic","puzzles","math","train"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.5"},{"id":"hch4ro67ucw6wsjp5vcfxxqq","name":"if-summarize-judge","description":"Verifiers environment for evaluating instruction-following on Wikipedia article summarization with held-out constraint types.","visibility":"PUBLIC","owner":{"type":"user","name":"kalomaze"},"created_at":"2026-04-01T22:47:29.218000","updated_at":"2026-04-01T22:50:05.644000","tags":[],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"u6zteuubly649v8lmrcyygf4","name":"mcp-atlas","description":"MCP-Atlas tool-use evaluation environment","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-04-01T13:49:32.529000","updated_at":"2026-04-01T13:50:47.524000","tags":["tool-use","mcp","llm-as-judge","multi-turn"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"qd4ynzv2kwl0fn3c0ni3bo1m","name":"advanced-if","description":"Verifiers-native rubric discovery environment over facebook/AdvancedIF trajectories.","visibility":"PUBLIC","owner":{"type":"user","name":"stochi0"},"created_at":"2026-03-31T22:42:03.055000","updated_at":"2026-03-31T23:06:01.206000","tags":["advanced-if","verifiers","datasets","single-turn","rubric","judge","advancedif"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"ipp5mbbmk3auemtf9315v3kl","name":"long-context-retrieval","description":"RLM environment package built on the published verifiers package","visibility":"PUBLIC","owner":{"type":"user","name":"stochi0"},"created_at":"2026-03-31T07:57:47.043000","updated_at":"2026-03-31T08:34:08.351000","tags":["multi-turn","tool-use","rlm","long-context","retrieval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"klyad40vjllvl2ln4ln0fw8w","name":"style-if","description":"Pareto frontier experiment: objective vs subjective reward signals","visibility":"PUBLIC","owner":{"type":"user","name":"jessicafeiyalipi"},"created_at":"2026-03-31T03:29:38.603000","updated_at":"2026-04-07T23:08:04.063000","tags":["style","instruction-following","subjective-reward","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.8"},{"id":"hv2oui3uclyjsv706i5azxzz","name":"hanabi","description":"Hanabi game","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T21:40:26.860000","updated_at":"2026-03-29T21:40:30.050000","tags":["multi-agent"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"kce2f7p2slz29tq2sjispng3","name":"BigBench-BBH","description":"Big Bench + BBH implementation","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T21:31:06.176000","updated_at":"2026-03-29T21:31:09.187000","tags":["bigbench","bbh","evaluation","nlp"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"sfvxllfwudvow00rlead3t3p","name":"triton-codebase-search","description":"Codebase search environment for Triton GPU programming library - tests agent's ability to navigate and answer questions about the Triton codebase u...","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T12:29:53.877000","updated_at":"2026-03-29T12:29:56.273000","tags":["codebase-search","tool-use","multi-turn","triton","gpu"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.7"},{"id":"aei8uycuk90j5vdld4ag9fhd","name":"seeclick","description":"Test model's ability to correctly click on target UI","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T12:29:44.024000","updated_at":"2026-03-29T12:29:46.538000","tags":["multimodal"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"rt1rq7pwgn4ep71mo82yr325","name":"llm-writer-negative-style","description":"ENV for self-grading for LLM Writer Style.","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T12:29:26.783000","updated_at":"2026-03-29T12:29:30.290000","tags":["eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"lv79wi45zx5fdskl3irg3fvu","name":"legalbench","description":"LegalBench environment for legal reasoning tasks","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T12:28:56.700000","updated_at":"2026-03-29T12:28:59.347000","tags":["legalbench","legal","single-turn","reasoning","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"y0jg5ja7cu8wkv1o5x964cns","name":"hle-web-py","description":"Humanity's Last Examination (HLE) benchmark environment for Prime Community Environments","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-29T12:28:55.606000","updated_at":"2026-03-29T12:28:59.176000","tags":["hle","multi-modal","tool-use","eval","academic","reasoning"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"z3hn21cjrumib64oos743oce","name":"asteroid","description":"Qdrant-native agent toolkit for multi-hop search","visibility":"PUBLIC","owner":{"type":"user","name":"thierrydamiba"},"created_at":"2026-03-28T00:58:50.902000","updated_at":"2026-03-28T03:44:15.318000","tags":[],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"r8x0wb5dgfu3eqhos7cd0eu6","name":"asteroid-search","description":"Qdrant-native agentic search environment with 3-level curriculum","visibility":"PUBLIC","owner":{"type":"user","name":"thierrydamiba"},"created_at":"2026-03-28T00:47:51.022000","updated_at":"2026-03-28T10:11:58.949000","tags":["search","retrieval","qdrant","agentic","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"xqvocg9ubqpos94ufuxsihgu","name":"reverse-text","description":"Reverse a given text; evaluated by LCS similarity between the parsed answer and ground-truth reversal.","visibility":"PUBLIC","owner":{"type":"user","name":"13point5"},"created_at":"2026-03-27T20:26:18.135000","updated_at":"2026-03-27T22:06:45.221000","tags":["text","transformation","single-turn","xml"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.4"},{"id":"v8ahu8hiuea3gvs0uumlqde1","name":"overpass-rl","description":"RL environment for training Overpass QL generation via tool calling with LLM judge reward","visibility":"PUBLIC","owner":{"type":"user","name":"laulauland"},"created_at":"2026-03-27T19:27:03.041000","updated_at":"2026-04-10T11:47:24.505000","tags":["multi-turn","tool-use","geospatial","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.2.17"},{"id":"zhj5pwcufu5ldopzm56crstw","name":"context-1","description":"multiturn retrieval-subagent environment inspired by chroma context-1.","visibility":"PUBLIC","owner":{"type":"user","name":"krishna"},"created_at":"2026-03-27T16:11:11.873000","updated_at":"2026-03-27T16:11:17.323000","tags":["search-agent","retrieval","multi-turn","tool-use","benchmark"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"mekd0054wi5yabsepvujiudn","name":"translation-cycles","description":"Cycle-consistency translation environment: English -> target language -> English, scored by chrF/BLEU.","visibility":"PUBLIC","owner":{"type":"user","name":"michaelginn"},"created_at":"2026-03-27T06:08:57.188000","updated_at":"2026-03-30T05:30:19.574000","tags":["translation","cycle-consistency","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"mg748qs9wjvi46no4nwrs2pg","name":"noodle-flights","description":"Prime environment package for the Noodle Flights deterministic flight-search simulator.","visibility":"PUBLIC","owner":{"type":"user","name":"wyatt"},"created_at":"2026-03-26T21:32:56.605000","updated_at":"2026-03-30T15:50:10.608000","tags":["openenv","mcp","flight-search","tool-use","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"og41av5w3lk809h328xx58y0","name":"molmo-browserbase","description":"MolmoWeb task-prompt browser environment aligned to WebVoyager-style evaluation","visibility":"PUBLIC","owner":{"type":"user","name":"13point5"},"created_at":"2026-03-26T20:56:36.796000","updated_at":"2026-03-26T21:05:22.466000","tags":["browser","browserbase","molmo","rl","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"bvvhegbfeey0ob5pzuqr68lp","name":"learn-helpsteer3-pointwise","description":"Verifiers environment for learning HelpSteer3 pointwise scores","visibility":"PUBLIC","owner":{"type":"user","name":"djdumpling"},"created_at":"2026-03-26T03:00:00.705000","updated_at":"2026-03-27T00:11:37.223000","tags":["pointwise","verifiers","xml","helpsteer3"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"kyttfxjta52hd6vfbsks9kif","name":"learn-helpsteer3","description":"Verifiers environment for learning HelpSteer3 preference rubrics","visibility":"PUBLIC","owner":{"type":"user","name":"djdumpling"},"created_at":"2026-03-26T02:59:39.013000","updated_at":"2026-03-27T00:12:24.247000","tags":["preferences","verifiers","xml","helpsteer3"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"y1ji3x24s09wdvunk77fuvws","name":"artblocks-collector","description":"RL training and eval environment for Art Blocks, the leading generative art platform. 207 Q&A pairs across 12 categories: artists, editions, script...","visibility":"PUBLIC","owner":{"type":"user","name":"jordanlyall"},"created_at":"2026-03-25T19:53:15.884000","updated_at":"2026-03-31T17:38:46.683000","tags":["eval","train","art","nft","blockchain","knowledge","generative-art"],"stars":0,"latest_ci_status":null,"latest_version":"0.4.0"},{"id":"k8n67gxecs3ry4zqrkazgk6z","name":"loca-bench-rlm","description":"Standalone RLM environment for LOCA-bench task configs","visibility":"PUBLIC","owner":{"type":"user","name":"stochi0"},"created_at":"2026-03-24T22:57:50.474000","updated_at":"2026-03-31T23:39:47.596000","tags":["rlm","benchmark","agent","loca-bench","tool-use"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"hxwn0ar8ip77cpy1kiwthhwp","name":"learn-coval-pointwise-sdpo","description":"SDPO-inspired feedback-conditioned rubric learning with 2-phase multi-turn rollout","visibility":"PUBLIC","owner":{"type":"user","name":"djdumpling"},"created_at":"2026-03-24T21:24:55.492000","updated_at":"2026-03-24T21:59:36.934000","tags":["pointwise","sdpo","multi-turn","verifiers","xml","coval","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"hebpz8bgg01ulrihj6wq0qxe","name":"lhaw_rlm","description":"LHAW RLM environment: underspecified prompts, simulated user clarification (ask_user), and LLM judge scoring on the ScaleAI/lhaw dataset.","visibility":"PUBLIC","owner":{"type":"user","name":"stochi0"},"created_at":"2026-03-24T21:10:21.858000","updated_at":"2026-03-25T05:43:02.537000","tags":["rlm","lhaw","multi-turn","clarification","verifiers","datasets"],"stars":2,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"khjks0oozbor95lra76vrmur","name":"sdr-arena","description":"SDR-Arena: Verifiers environment for SDR-Bench — benchmarking LLM personalization capabilities on B2B sales research with time-restricted web searc...","visibility":"PUBLIC","owner":{"type":"team","name":"hashkat"},"created_at":"2026-03-24T20:41:34.748000","updated_at":"2026-03-24T20:41:42.560000","tags":["benchmark","personalization","b2b-sales","deep-research","agent-evaluation","tool-use","multi-turn","eval","train"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"ed8w1w1au8j2dn79lr014u7i","name":"openrca-env","description":"OpenRCA root cause analysis benchmark environment for Verifiers (ICLR 2025)","visibility":"PUBLIC","owner":{"type":"team","name":"prime"},"created_at":"2026-03-24T20:34:32.746000","updated_at":"2026-03-24T21:15:01.159000","tags":["multi-turn","tool-use","devops","rca","eval","train"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"h2mx8ql7sbf0o98umtzmd9of","name":"arc-agi-3-env","description":"PrimeIntellect RL environment for ARC-style maze and ARC-AGI games","visibility":"PUBLIC","owner":{"type":"user","name":"ryanznie"},"created_at":"2026-03-23T00:11:05.765000","updated_at":"2026-03-23T00:45:19.802000","tags":["game","arc","arc-agi","maze","multi-turn","rl"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"yelnab7rdy7d26wc2gehaonm","name":"cwe-agent-prod-1","description":"Exact-match CWE Top-25 classification environment for evaluation and future RL experiments.","visibility":"PUBLIC","owner":{"type":"user","name":"nevi"},"created_at":"2026-03-22T21:49:30.776000","updated_at":"2026-03-22T22:20:07.223000","tags":["security","cwe","classification","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"xffct34uxhcspw5np5walibr","name":"research-hypothesis-analysis","description":"Synthetic Bayesian multi-turn environment for epistemic experiment selection and belief revision","visibility":"PUBLIC","owner":{"type":"user","name":"jbarnes850"},"created_at":"2026-03-22T21:28:42.289000","updated_at":"2026-03-22T21:54:24.356000","tags":["prime-rl","multi-turn","bayesian","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"naqwk35nmz1c7j0mmkv33sx5","name":"clinical-trial-prediction","description":"Your environment description here","visibility":"PUBLIC","owner":{"type":"team","name":"sundai-march-22"},"created_at":"2026-03-22T19:40:02.819000","updated_at":"2026-03-24T02:00:34.589000","tags":["placeholder-tag","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"dwfxr9h906ql685et2ic7ms5","name":"pydantic-adherence","description":"Multi-turn JSON-structured output validated against per-sample Pydantic models.","visibility":"PUBLIC","owner":{"type":"user","name":"andrewmead"},"created_at":"2026-03-22T19:05:15.048000","updated_at":"2026-03-22T21:36:06.039000","tags":["json","structure","multi-turn","pydantic","parsing"],"stars":0,"latest_ci_status":null,"latest_version":"0.2.4"},{"id":"vb9m7e76a7q1buz6ette6xha","name":"spam-detection-rl-environment","description":"A reinforcement learning environment for training models to detect spam messages","visibility":"PUBLIC","owner":{"type":"team","name":"rl-envs-team"},"created_at":"2026-03-22T06:39:09.401000","updated_at":"2026-03-22T19:14:02.081000","tags":["spam-detection","text-classification","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"fzl8uvmi8bmc17igvw8muoa6","name":"lean-code","description":"Agentic Lean 4 environment with bash + str_replace tools for theorem proving","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-19T08:19:37.449000","updated_at":"2026-03-19T08:19:40.646000","tags":["lean4","theorem-proving","multi-turn","agentic","sandbox"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"ztk92qq8ktc8gxlr674yydn0","name":"aime2026","description":"AIME-26 evaluation environment","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-19T08:17:41.234000","updated_at":"2026-04-10T09:38:03.239000","tags":["math","eval","single-turn"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"td1q8b2romxux3wttfw9rll5","name":"gutenberg-env","description":"Agentic RAG over Sherlock Holmes short stories for literary Q&A","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-18T18:58:30.632000","updated_at":"2026-03-18T18:58:33.808000","tags":["gutenberg","multi-turn","agentic-search","rag","train","eval","llm-judge"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.6"},{"id":"df89k7faz8m4vxijhub96r3s","name":"medconcepts-train","description":"Your environment description here","visibility":"PUBLIC","owner":{"type":"user","name":"marii"},"created_at":"2026-03-18T08:22:43.685000","updated_at":"2026-03-18T08:26:59.790000","tags":["placeholder-tag","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"obm0ilr120j4dtopy5x8wgjf","name":"medphysbench-dvh","description":"DVH Treatment Plan Evaluation — clinical treatment planning assessment for radiation therapy","visibility":"PUBLIC","owner":{"type":"user","name":"omar"},"created_at":"2026-03-18T04:37:31.867000","updated_at":"2026-03-18T18:44:28.717000","tags":["medical-physics","treatment-planning","dvh","single-turn","think","clinical"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.4"},{"id":"hbz0902b7pg8se354w0rl2g5","name":"codenames","description":"PrimeIntellect Codenames environment for evaluation and RL training","visibility":"PUBLIC","owner":{"type":"user","name":"maxbittker"},"created_at":"2026-03-17T22:27:26.405000","updated_at":"2026-04-12T15:47:36.822000","tags":["games","rl","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.5.2"},{"id":"r1jhw14mxyqsnra14hjuq5tg","name":"gpt-world","description":"Multi-turn hex-grid pathfinding environment based on GPT-World","visibility":"PUBLIC","owner":{"type":"user","name":"alex-maraval"},"created_at":"2026-03-17T16:44:06.191000","updated_at":"2026-03-18T13:43:31.787000","tags":["games","planning","tool-use","multiturn","pathfinding"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"m7lmmvvk3lbhqona8gckcgnl","name":"fitness-meal-planner","description":"Fitness meal planning with tool-use: model searches recipes and composes macro-matched daily plans","visibility":"PUBLIC","owner":{"type":"user","name":"socaitcy"},"created_at":"2026-03-17T14:03:33.359000","updated_at":"2026-03-17T14:51:03.806000","tags":["tool-use","multi-turn","fitness","nutrition","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.6"},{"id":"ecr78ljevfcvr3ezo178zmyk","name":"opencode-deepdive","description":"OpenCode DeepDive QA environment with web research tools","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-17T01:00:46.456000","updated_at":"2026-04-10T18:28:39.982000","tags":["rl","search","qa","multi-turn","sandbox"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"j6p3bjn5czagyza4z6qswqn1","name":"bb-demo","description":"BrowserEnv demo for web browsing tasks using Browserbase","visibility":"PUBLIC","owner":{"type":"team","name":"prime"},"created_at":"2026-03-16T23:46:51.016000","updated_at":"2026-03-17T01:27:00.100000","tags":["browser","browserbase","eval"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"sbb344ptgqnuto7ljjblsoa0","name":"impact-agent-bt-v2","description":"ImpactAgent Bradley-Terry v2 environment with correctness-only reward","visibility":"PUBLIC","owner":{"type":"team","name":"shiels-ai"},"created_at":"2026-03-16T12:22:12.109000","updated_at":"2026-03-18T18:24:29.299000","tags":["tool-use","scientific-papers","pairwise-ranking","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.7"},{"id":"o9zgk3f354s3p8hhwgmr6eso","name":"impact-agent-gaussian-v2","description":"ImpactAgent Gaussian v2 environment with baseline-subtracted task reward","visibility":"PUBLIC","owner":{"type":"team","name":"shiels-ai"},"created_at":"2026-03-16T12:21:50.048000","updated_at":"2026-03-18T18:25:05.125000","tags":["tool-use","scientific-papers","impact-prediction","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.5"},{"id":"od0wpuibcpwocd4qqltsjia5","name":"barterbench","description":"BarterBench: competitive multi-agent marketplace RL environment","visibility":"PUBLIC","owner":{"type":"user","name":"mead0w1ark"},"created_at":"2026-03-15T22:55:15.517000","updated_at":"2026-03-15T23:05:19.709000","tags":["multi-agent","economics","competition","barter","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"n0ywaguroagtn4uossrai0n1","name":"ClinEval-safety","description":"A deterministic safety evaluation framework for clinical AI agents. Tests 5 failure categories (omission, hallucination, contradiction, contaminati...","visibility":"PUBLIC","owner":{"type":"user","name":"kinzakhan"},"created_at":"2026-03-15T22:51:34.146000","updated_at":"2026-04-07T16:57:57.513000","tags":["safety","healthcare","ehr","eval","clinical","mimic-iv","tool-use","multi-turn"],"stars":0,"latest_ci_status":null,"latest_version":"0.2.3"},{"id":"jvloauv4nwpwxoancccbbk5m","name":"unslop-dpo-reward","description":"Prime Intellect Verifiers environment for qfennessy/unslop-dpo Bradley-Terry preference rewards.","visibility":"PUBLIC","owner":{"type":"user","name":"andrewmead"},"created_at":"2026-03-15T19:48:27.555000","updated_at":"2026-03-15T21:35:33.738000","tags":["single-turn","preference","dpo","train","eval"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"fktu7a4oicbaylo2rarbw1ui","name":"medconcepts_train","description":"Your environment description here","visibility":"PUBLIC","owner":{"type":"user","name":"marii"},"created_at":"2026-03-15T12:35:47.045000","updated_at":"2026-03-15T14:34:44.666000","tags":["placeholder-tag","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"o6baxzqqmj4160mpgvly5127","name":"impact-agent-bt","description":"Bradley-Terry pairwise environment for comparing blinded research papers","visibility":"PUBLIC","owner":{"type":"team","name":"shiels-ai"},"created_at":"2026-03-15T07:43:19.552000","updated_at":"2026-03-15T07:48:14.004000","tags":["tool-use","scientific-papers","pairwise-ranking","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.7"},{"id":"aantxydz47kocf2wipnaytzf","name":"arabic-math","description":"Arabic math problems environment for RL training","visibility":"PUBLIC","owner":{"type":"user","name":"mohad"},"created_at":"2026-03-15T00:13:20.754000","updated_at":"2026-03-15T00:24:33.200000","tags":[],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"b3zkp6rwcap7yeqrkt2tqht0","name":"autoresearch","description":"Autonomous LLM training research environment for Verifiers and prime-rl","visibility":"PUBLIC","owner":{"type":"user","name":"stochi0"},"created_at":"2026-03-14T22:45:17.529000","updated_at":"2026-03-15T19:55:54.209000","tags":["multi-turn","tool-use","rlm","autoresearch","training"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"haxrs4oy2s0lsiayvjvu5yho","name":"medconcepts-train-sample","description":"Your environment description here","visibility":"PUBLIC","owner":{"type":"user","name":"marii"},"created_at":"2026-03-14T22:26:04.498000","updated_at":"2026-03-14T22:26:11.803000","tags":["placeholder-tag","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"hycs3bpn03c1amwcr1ypfyow","name":"mijabench","description":"A bilingual adversarial benchmark for auditing demographic safety alignment and jailbreak vulnerabilities in LLMs.","visibility":"PUBLIC","owner":{"type":"user","name":"ob1"},"created_at":"2026-03-14T18:05:51.642000","updated_at":"2026-03-14T23:55:36.592000","tags":["safety","red-teaming","jailbreak","bias","single-turn","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"cm0v9170dh7no3bk60s6eg2a","name":"kv-cache-rl","description":"RL environment for KV-cache eviction policy optimization in LLM serving","visibility":"PUBLIC","owner":{"type":"user","name":"semih"},"created_at":"2026-03-14T15:03:42.414000","updated_at":"2026-03-14T15:17:13.548000","tags":["multi-turn","tool-use","rl","inference","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"ed46w13n33p08gu741gj319o","name":"tic-tac-toe","description":"Multi-turn tic-tac-toe against a GTO (minimax) opponent. Model plays as X or O randomly, first mover randomized. Win=1.0, Draw=0.5, Loss/Illegal=0.0.","visibility":"PUBLIC","owner":{"type":"user","name":"tars90percent"},"created_at":"2026-03-14T03:05:57.490000","updated_at":"2026-03-14T07:22:07.366000","tags":["game","reasoning","multi-turn","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.2"},{"id":"k5ch761yjwl7ovfm1rjk2zex","name":"brfauna","description":"Verifiers port of BRFauna eval suite.","visibility":"PUBLIC","owner":{"type":"user","name":"ob1"},"created_at":"2026-03-14T01:52:33.443000","updated_at":"2026-03-14T02:47:29.612000","tags":["portuguese","qa","text-simplification","text-summarization","brfauna","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"aj50jmvvqd4cenpx54m0es7k","name":"emr-colorectal-env","description":"Prime Intellect RLVR environment for colorectal surgical clinic pathway navigation","visibility":"PUBLIC","owner":{"type":"team","name":"standard-data"},"created_at":"2026-03-13T17:58:11.423000","updated_at":"2026-03-28T01:13:45.893000","tags":[],"stars":0,"latest_ci_status":null,"latest_version":"5.3.0"},{"id":"xg8f0maf8mh2zgduzit8rq1q","name":"medpt-gqa","description":"Generative question-answering environment based on MedPT dataset - Portuguese medical questions","visibility":"PUBLIC","owner":{"type":"user","name":"ob1"},"created_at":"2026-03-13T17:36:19.599000","updated_at":"2026-03-14T02:53:15.776000","tags":["medical","qa","portuguese","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"jelusby6mmar5l6ssd0gqpyo","name":"chart-extraction","description":"Environment for extracting structured data from line chart images","visibility":"PUBLIC","owner":{"type":"user","name":"13point5"},"created_at":"2026-03-13T13:56:41.405000","updated_at":"2026-04-03T00:33:28.014000","tags":["single-turn","multimodal","vision","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.9"},{"id":"p0ljo5h31szxetddqa37sfj6","name":"medpt","description":"Verifiers port for MedPT dataset","visibility":"PUBLIC","owner":{"type":"user","name":"ob1"},"created_at":"2026-03-12T20:28:46.247000","updated_at":"2026-03-12T20:33:06.709000","tags":["medical","classification","portuguese","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"sttprvcsywy60m2yr2ca685v","name":"compression-rl","description":"Compress text faithfully: deterministic fact-preservation scoring via downstream QA","visibility":"PUBLIC","owner":{"type":"user","name":"nrghosh"},"created_at":"2026-03-12T05:12:42.562000","updated_at":"2026-03-12T16:44:24.037000","tags":["single-turn","compression","nlp","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"pafvmbwn3bzelchogzwtr2y7","name":"regex-golf","description":"Regex golf: generate the shortest regex separating positive and negative string sets","visibility":"PUBLIC","owner":{"type":"user","name":"nrghosh"},"created_at":"2026-03-12T05:12:33.656000","updated_at":"2026-03-12T05:44:46.059000","tags":["single-turn","code","regex","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"jx2i4c2ssgie9kd25txewtv5","name":"longbenchv2","description":"LongBench v2: multiple-choice QA over long documents","visibility":"PUBLIC","owner":{"type":"user","name":"alz"},"created_at":"2026-03-12T04:46:49.171000","updated_at":"2026-03-12T04:58:02.767000","tags":["single-turn","long-context","mcqa","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"lf8tvzhiq88nxad26ex1qqr2","name":"opencode-cp","description":"Solve competitive programming problems using OpenCode agent via ComposableEnv.","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-11T22:19:07.361000","updated_at":"2026-04-10T18:28:23.203000","tags":["coding","opencode","multi-turn"],"stars":1,"latest_ci_status":null,"latest_version":"0.2.2"},{"id":"aaj72iiv8oy4n825w3n38ltd","name":"opencode-science","description":"Solve science problems using OpenCode agent via ComposableEnv.","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-11T15:47:23.470000","updated_at":"2026-04-10T18:28:34.495000","tags":["science","opencode","multi-turn"],"stars":1,"latest_ci_status":null,"latest_version":"0.2.2"},{"id":"c6g6hgr4t4srxfu078j7h5ou","name":"hangman_agent","description":"A dense-reward multi-turn Hangman environment for Prime/Verifiers.","visibility":"PUBLIC","owner":{"type":"user","name":"alex-maraval"},"created_at":"2026-03-11T09:57:47.911000","updated_at":"2026-03-16T08:42:25.123000","tags":["multi-turn","game","hangman","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.2.11"},{"id":"mxi7h5i12binmtgozp1frhrr","name":"indic-ifeval","description":"IndicIFEval: Instruction-following eval for 14 Indic languages","visibility":"PUBLIC","owner":{"type":"user","name":"adityapuranik"},"created_at":"2026-03-11T05:06:07.288000","updated_at":"2026-04-01T22:44:31.857000","tags":["indic","ifeval","instruction-following","single-turn","train","eval"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.4"},{"id":"uhpvq8hxckq4eneknezlrxae","name":"contract-clause-review","description":"This environment tests an agent's ability to review legal contracts, identify specific clauses, and assess their compliance with predefined legal s...","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T19:10:46.478000","updated_at":"2026-03-09T19:10:50.026000","tags":["law"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"v54qgimhjgvm8oc9iboy6ww7","name":"clinical-diagnosis-differential","description":"This environment tests an agent's ability to perform differential diagnosis by iteratively gathering patient information and consulting medical kno...","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T19:10:38.229000","updated_at":"2026-03-09T19:15:04.425000","tags":["medicine"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"eeceo8ws2knwz51e7v5j5x1b","name":"discover-gsm8k","description":"GSM8K rubric-discovery environment: learn rubric_fn from (input, response, score) examples","visibility":"PUBLIC","owner":{"type":"user","name":"stochi0"},"created_at":"2026-03-09T19:05:57.963000","updated_at":"2026-03-14T05:20:34.635000","tags":["multi-turn","tool-use","rlm","gsm8k","rubric"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.4"},{"id":"skd6ofm2gvnqegtpkfka5t29","name":"sudoku-solver","description":"Generated environment","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T18:00:18.139000","updated_at":"2026-03-09T18:00:21.273000","tags":["general"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"pxor2vr51qi9n0adpg5obz9x","name":"scientific-literature-review","description":"Generated environment","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T18:00:14.241000","updated_at":"2026-03-09T18:00:16.864000","tags":["general"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"ta07bwcax3n6wh2oxrcgc5xh","name":"financial-risk-assessment","description":"This environment assesses a model's ability to identify and quantify financial risks based on provided company data. It evaluates understanding of ...","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T18:00:10.216000","updated_at":"2026-03-09T18:02:21.350000","tags":["finance"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"xtpylfy92flffjdrfjx29d0k","name":"drug-interaction-checker","description":"This environment tests an agent's ability to identify potential drug-drug interactions given a patient's current medications and a newly prescribed...","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T18:00:05.526000","updated_at":"2026-03-09T19:16:44.891000","tags":["medicine"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"u0iaxcbxb0mcoi0m4lbjmp93","name":"contract-review-clause-identification","description":"This environment tests an agent's ability to review legal contracts, identify specific clauses based on given criteria, and extract relevant inform...","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T18:00:01.620000","updated_at":"2026-03-09T19:15:29.630000","tags":["law"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"lm5itwsdvek9htzgx81c0olx","name":"clinical-diagnosis-assistant","description":"Generated environment","visibility":"PUBLIC","owner":{"type":"team","name":"primeintellect"},"created_at":"2026-03-09T17:59:57.221000","updated_at":"2026-03-09T17:59:59.935000","tags":["general"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"u9lhlma6ds4t7v1tv81abijq","name":"MATH500","description":"MATH-500 competition math environment with symbolic verification via math-verify","visibility":"PUBLIC","owner":{"type":"user","name":"maziyar"},"created_at":"2026-03-09T15:10:06.117000","updated_at":"2026-03-27T20:26:33.610000","tags":["math","competition-math","reasoning","symbolic-verification","single-turn","train","eval"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"b4aur43vxemjxi4fjghl6cdv","name":"kuhn-poker","description":"Kuhn Poker environment with TextArena game engine","visibility":"PUBLIC","owner":{"type":"user","name":"nph4rd"},"created_at":"2026-03-09T03:20:18.609000","updated_at":"2026-03-09T07:31:33.416000","tags":["multi-agent","game-theory","kuhn-poker"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"yvz596lq1cots6aa7fuibqui","name":"chastitybench","description":"Verifiers environment for the ChastityBench multimodal benchmark","visibility":"PUBLIC","owner":{"type":"user","name":"carsten"},"created_at":"2026-03-08T05:47:15.238000","updated_at":"2026-03-18T14:49:35.200000","tags":["multimodal","vision","eval"],"stars":1,"latest_ci_status":null,"latest_version":"0.1.0"},{"id":"qacmm9gz0406jc7ffpfepyqj","name":"stepfun-prover","description":"A multi-turn RL environment for formal theorem proving in Lean 4, where models alternate between reasoning, sketching proof code, and receiving ver...","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-08T03:19:13.011000","updated_at":"2026-03-08T03:19:16.506000","tags":["math","theorem-proving","lean4","rl","multi-turn","train"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.3"},{"id":"o5paw7at0781ubmg6bwbv57b","name":"wiki-race","description":"Environment for the game Wiki Race","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-08T03:15:13.091000","updated_at":"2026-03-08T03:15:15.905000","tags":["game","multi-turn","navigation"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"},{"id":"sebuqpuviytepss68gjr9x6b","name":"vision-sr1","description":"Vision-SR1 environment (train+eval) using original graders","visibility":"PUBLIC","owner":{"type":"team","name":"prime-community"},"created_at":"2026-03-08T03:15:08.595000","updated_at":"2026-03-08T03:15:11.519000","tags":["vision-sr1","multi-pass","vlm","rl"],"stars":0,"latest_ci_status":null,"latest_version":"0.1.1"}],"status":null}