{"id":"pokemon-red-benchmark-speedrun-completion--gh-pwhiddy-pokemonredexperiments","name":"Pokemon Red benchmark (speedrun / completion)","url":"https://github.com/PWhiddy/PokemonRedExperiments","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/pokemon-red-benchmark-speedrun-completion--gh-pwhiddy-pokemonredexperiments","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":4,"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":"Pokemon Red completion benchmark — long-horizon JRPG agent task","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"desc":{"value":"Pokemon Red has emerged as a community + academic benchmark for long-horizon agentic AI. Notable instances: Peter Whiddy's PokemonRedExperiments (RL via PPO + curiosity, viral YouTube series 2023); Anthropic's ClaudePlaysPokemon Twitch stream (2025-02); Google's GeminiPlaysPokemon (2025); MorphLabs PokemonRedRL. The benchmark protocol varies: badge count, gym progression, full Elite-Four completion. Common across all: ~5k-20k+ step horizon, sparse rewards, deep partial-observability.","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"claims":{"value":"Anthropic ClaudePlaysPokemon: 2/8 badges over ~80hr (Claude 3.7 Sonnet, Feb 2025); Google Gemini 2.5 Pro reportedly completed full game; Whiddy's PPO+curiosity RL completed up to Pewter Gym; viral mindshare via Twitch livestreams","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"modalities":{"value":"visual (Game Boy emulator frames) + memory-state introspection","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"created":{"value":"2023-09 (Whiddy YouTube + GitHub release)","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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 (Whiddy repo)","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"gh":{"value":"7.6k★ Python (PokemonRedExperiments)","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"mindshare":{"value":"Anthropic ClaudePlaysPokemon Twitch viral 2025; ~7.6k stars on Whiddy repo; key public spectacle for long-horizon LLM-agent capability","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","last_verified_at":"2026-05-14","source_class":"repo"},"citations":{"value":"20+ cites — academic Pokemon-Red papers (Whiddy preprint, RL follow-ups)","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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/PWhiddy/PokemonRedExperiments","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/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"hq":{"value":"not applicable — not a company","citation":null,"status":"not-applicable","tier":"T3"},"founders":{"value":"Peter Whiddy (independent); Anthropic team (ClaudePlaysPokemon); Google DeepMind (GeminiPlaysPokemon)","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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 labs (Anthropic, Google, MorphLabs) running variants","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"code-release":{"value":"Code public (Whiddy repo) + ROM user-supplied","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"tombstoning":{"value":"not applicable — static benchmark","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"schema-evolution":{"value":"not applicable — fixed evaluation dataset","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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/PWhiddy/PokemonRedExperiments","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":"Most-watched public AI-agent benchmark via Twitch streams; ~hours-to-days horizon stresses long-horizon planning; deeply community-engaging; multiple frontier labs racing on it.","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"cons":{"value":"No standardized scoring protocol (badge-count vs completion vs speed); Game Boy ROM legality issues; Twitch streams not always reproducible at the playthrough level.","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"links":{"value":"github.com/PWhiddy/PokemonRedExperiments Anthropic ClaudePlaysPokemon Twitch GeminiPlaysPokemon","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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\":\"2019-12\",\"cum\":3},{\"ym\":\"2021-10\",\"cum\":11},{\"ym\":\"2021-11\",\"cum\":22},{\"ym\":\"2021-12\",\"cum\":57},{\"ym\":\"2022-01\",\"cum\":76},{\"ym\":\"2022-02\",\"cum\":78},{\"ym\":\"2022-03\",\"cum\":81},{\"ym\":\"2022-04\",\"cum\":113},{\"ym\":\"2022-06\",\"cum\":120},{\"ym\":\"2023-02\",\"cum\":127},{\"ym\":\"2023-05\",\"cum\":130},{\"ym\":\"2023-07\",\"cum\":132},{\"ym\":\"2023-08\",\"cum\":134},{\"ym\":\"2023-09\",\"cum\":141},{\"ym\":\"2023-10\",\"cum\":199},{\"ym\":\"2023-11\",\"cum\":203},{\"ym\":\"2023-12\",\"cum\":205},{\"ym\":\"2024-01\",\"cum\":211},{\"ym\":\"2024-02\",\"cum\":216},{\"ym\":\"2024-03\",\"cum\":218},{\"ym\":\"2024-05\",\"cum\":223},{\"ym\":\"2024-07\",\"cum\":225},{\"ym\":\"2024-08\",\"cum\":244},{\"ym\":\"2024-09\",\"cum\":245},{\"ym\":\"2024-10\",\"cum\":249},{\"ym\":\"2024-11\",\"cum\":253},{\"ym\":\"2024-12\",\"cum\":259},{\"ym\":\"2025-01\",\"cum\":261},{\"ym\":\"2025-02\",\"cum\":262},{\"ym\":\"2025-03\",\"cum\":264},{\"ym\":\"2025-04\",\"cum\":266},{\"ym\":\"2025-05\",\"cum\":271},{\"ym\":\"2025-08\",\"cum\":272}]","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"cost-output-usd-per-mtok":{"value":"0","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"cost-tier":{"value":"free","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"cost-pricing-model":{"value":"free-tier","citation":"https://github.com/PWhiddy/PokemonRedExperiments","status":"real-data","tier":"T1","source_class":"repo"},"cost-last-verified":{"value":"2026-06-29","citation":"https://github.com/PWhiddy/PokemonRedExperiments","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/PWhiddy/PokemonRedExperiments","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\":\"2026-09\",\"openrank_12mo\":1.98,\"openrank_current\":0.14,\"participants\":1}","citation":"https://oss.open-digger.cn/github/PWhiddy/PokemonRedExperiments/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/pokemon-red-benchmark-speedrun-completion--gh-pwhiddy-pokemonredexperiments","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"}