{"id":"procgen-benchmark-suite--gh-openai-procgen","name":"PROCGEN benchmark suite","url":"https://github.com/openai/procgen","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/procgen-benchmark-suite--gh-openai-procgen","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":3,"last_verified_at":"2026-10-28","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":"Procedurally-generated RL game suite — generalisation eval","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"desc":{"value":"OpenAI's 16-game procedurally-generated benchmark for evaluating RL generalisation. Unlike Atari (fixed levels memorisable), every PROCGEN episode uses a different procedural seed → test-set generalisation is the headline metric. Released at ICML 2020. Standard benchmark for studying generalisation, exploration, transfer.","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"ICML 2020; 16 procedurally-generated games; standard for RL generalisation research; used by IMPALA, PPG, DAAC, IDAAC follow-ups","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"modalities":{"value":"visual (procedural 2D game frames, 64x64)","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"created":{"value":"2019-12 (Cobbe et al. arXiv 1912.01588)","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"980★ Python/C","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"mindshare":{"value":"Standard RL generalisation benchmark cited by hundreds of follow-up papers","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citations":{"value":"700+ cites — Cobbe et al. ICML 2020","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"Karl Cobbe, Christopher Hesse, Jacob Hilton, John Schulman (OpenAI)","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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 — multiple SOTA papers","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"code-release":{"value":"Code public","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"tombstoning":{"value":"not applicable — static benchmark","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"schema-evolution":{"value":"not applicable — fixed evaluation dataset","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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":"Procedural seed-train / seed-test split rigorously isolates generalisation from memorisation; lightweight (16 fast games).","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"cons":{"value":"2D platformer style limits transfer to richer 3D / embodied; PROCGEN-shaped overfitting is a known critique.","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"links":{"value":"github.com/openai/procgen arxiv 1912.01588","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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":"[{\"ym\":\"2019-11\",\"cum\":1},{\"ym\":\"2019-12\",\"cum\":39},{\"ym\":\"2020-01\",\"cum\":41},{\"ym\":\"2020-02\",\"cum\":43},{\"ym\":\"2020-03\",\"cum\":44},{\"ym\":\"2020-06\",\"cum\":53},{\"ym\":\"2020-07\",\"cum\":56},{\"ym\":\"2020-12\",\"cum\":59},{\"ym\":\"2021-05\",\"cum\":60},{\"ym\":\"2022-01\",\"cum\":75},{\"ym\":\"2026-03\",\"cum\":77}]","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"cost-tier":{"value":"free","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"cost-pricing-model":{"value":"free-tier","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"cost-last-verified":{"value":"2026-06-29","citation":"https://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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, not a deployable system","citation":null,"status":"not-applicable","tier":"T3"},"use-case-anti-tags":{"value":"not applicable — benchmark, 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://github.com/openai/procgen","status":"real-data","tier":"T1","source_class":"repo"},"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":"{\"activity\":0.72,\"as_of\":\"2024-08\",\"openrank_12mo\":1.01,\"openrank_current\":0.32,\"participants\":1}","citation":"https://oss.open-digger.cn/github/openai/procgen/openrank.json","status":"real-data","tier":"T2","last_verified_at":"2026-10-28","source_class":"third-party"},"freshness-date":{"value":"2026-10-28","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/procgen-benchmark-suite--gh-openai-procgen","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":30,"third_party_cells":1},"edges":{"outgoing":[],"incoming":[]},"history":[],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}