{"id":"minerl-diamond-challenge--minerl-io","name":"MineRL Diamond Challenge","url":"https://minerl.io/","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/minerl-diamond-challenge--minerl-io","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":2,"last_verified_at":"2026-05-14","lifecycle":{"status":"active","severity":0,"note":null},"taxonomy":{"storage":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"retrieval":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"persistence":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"update":[{"value":"read-only","primary":true,"reason":null}],"unit":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"governance":[{"value":"n/a","primary":true,"reason":"not applicable — eval dataset, not a system"}],"conflict":[{"value":"n/a","primary":true,"reason":"not applicable — read-only evaluation dataset"}]},"cells":{"type":{"value":"Minecraft RL benchmark — obtain a diamond","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"MineRL is a research project / competition series using Minecraft as a long-horizon RL environment. The flagship Diamond Challenge tasks an agent with obtaining a diamond from raw world — requires deep tech-tree planning across thousands of steps. DreamerV3 (DeepMind, 2023-12) famously became the first to solve it from scratch without human data.","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"claims":{"value":"NeurIPS 2019/2020/2021 competitions; DreamerV3 first to solve from scratch (2023-12); remains a canonical world-model benchmark","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"modalities":{"value":"visual (Minecraft screen) + inventory state","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"created":{"value":"2019 (Guss et al. IJCAI 2019)","citation":"https://minerl.io/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"latest-release":{"value":"not applicable — not OSS","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"license":{"value":"MIT","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"gh":{"value":"~700★ Python","citation":"https://minerl.io/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"mindshare":{"value":"Foundational Minecraft RL benchmark cited by DreamerV3, VPT, Voyager, MineDojo papers","citation":"https://minerl.io/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"citations":{"value":"500+ cites — MineRL paper + Diamond Challenge papers","citation":"https://minerl.io/","status":"real-data","tier":"T2","last_verified_at":"2026-05-14","source_class":"vendor"},"funding":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"customers":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"pricing":{"value":"not applicable — open benchmark; free to use","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"compliance":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"data-handling":{"value":"not applicable — not commercial","citation":null,"status":"not-applicable","tier":"T3"},"deployment":{"value":"not applicable — run locally","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"William H. Guss et al. (CMU); MineRL Labs / OpenAI / Microsoft Research collaborators","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"volume":{"value":"not applicable — not a memory product","citation":null,"status":"not-applicable","tier":"T3"},"perf":{"value":"not applicable — does not compete on benchmarks","citation":null,"status":"not-applicable","tier":"T3"},"repro":{"value":"Independently reproduced — DreamerV3 (DeepMind 2023), VPT (OpenAI 2022)","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"code-release":{"value":"Code public + Minecraft proprietary","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"api-surface":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"latency":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"throughput":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"backend-storage":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"multi-tenancy":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"encryption":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"sso-rbac":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"embedding-model":{"value":"not applicable — eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"consistency":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"versioning":{"value":"not applicable — static benchmark","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"not applicable — static benchmark","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"schema-evolution":{"value":"not applicable — fixed evaluation dataset","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"namespace":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"contradiction":{"value":"not applicable","citation":null,"status":"not-applicable","tier":"T3"},"forgetting":{"value":"not applicable — static benchmark","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"mcp-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"a2a-support":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"otel":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"webhooks":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"import-export":{"value":"not applicable — benchmark / evaluation harness","citation":null,"status":"not-applicable","tier":"T3"},"integration-count":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"orchestration":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"programmatic-control":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"vendor-benchmarks":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"pricing-specifics":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"agent-abstraction":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"memory-primitives":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"llm-lock":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"runtimes":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"session-handling":{"value":"not applicable — wrong section","citation":null,"status":"not-applicable","tier":"T3"},"validated-verticals":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"time-to-running":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"anti-fit":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"optimised-for":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"adjacent-infrastructure":{"value":"not applicable - eval dataset, not a system","citation":null,"status":"not-applicable","tier":"T3"},"pros":{"value":"Real, complex, long-horizon environment; competition history with public leaderboards; visual modality forces realistic perception.","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"cons":{"value":"Minecraft proprietary licensing complicates redistribution; rewards extremely sparse (~24k steps to first diamond); legacy versions of MC mod required.","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"links":{"value":"minerl.io GitHub minerllabs/minerl","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"obs-langsmith":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-opentelemetry":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-datadog":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-helicone":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-weave":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-langfuse":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-arize":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"obs-custom":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-token-budget":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-prompt-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-semantic-caching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-batching":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-model-routing":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-streaming-only":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"cost-observability-cost-attribution":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-langsmith-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-braintrust":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-weights-and-biases-agent":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-helicone-evals":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-custom-test-harness":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-human-loop":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"eval-production-traffic-replay":{"value":"","citation":null,"status":"no-data","tier":"T3","last_verified_at":"2026-05-14"},"commit-trajectory":{"value":"not applicable — no GitHub repo","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"download-trajectory":{"value":"not applicable — not published as a package","citation":null,"status":"not-applicable","tier":"T3","last_verified_at":"2026-05-14"},"cost-input-usd-per-mtok":{"value":"0","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"cost-tier":{"value":"free","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"cost-pricing-model":{"value":"free-tier","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"cost-last-verified":{"value":"2026-06-29","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"capability-composite-score":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-band":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-benchmark-sources":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"capability-last-verified":{"value":"not applicable — benchmark / evaluation tool, not a capable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-tags":{"value":"not applicable — benchmark / competition, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — benchmark / competition, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"adoption-accelerator":{"value":"","citation":null,"status":"no-data","tier":"T3"},"architecture-deployment-locus":{"value":"","citation":null,"status":"no-data","tier":"T3"},"licensing-bucket":{"value":"open-source","citation":"https://minerl.io/","status":"real-data","tier":"T2","source_class":"vendor"},"positioning-platform-vs-product":{"value":"","citation":null,"status":"no-data","tier":"T3"},"taxonomy-three-layer-rollup":{"value":"agent-infra","citation":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/docs/schema/section-to-three-layer-rollup.json","status":"real-data","tier":"T1","source_class":"repo"},"developer-activity-opendigger":{"value":"","citation":null,"status":"no-data","tier":"T3"},"freshness-date":{"value":"2026-05-14","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/minerl-diamond-challenge--minerl-io","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"","citation":null,"status":"no-data","tier":"T3"},"sdk-languages":{"value":"","citation":null,"status":"no-data","tier":"T3"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":28,"third_party_cells":0},"edges":{"outgoing":[],"incoming":[]},"history":[],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}