{"id":"terminal-bench--tbench-ai","name":"Terminal-Bench","url":"https://www.tbench.ai/","page":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/terminal-bench--tbench-ai","family":"memory-research","section":"Memory benchmarks & evaluation","sections":["Memory benchmarks & evaluation"],"tier":3,"last_verified_at":"2026-10-29","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":"Benchmark","citation":"https://www.tbench.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"desc":{"value":"Benchmark of agents completing hard tasks in a terminal environment, now at version 4.0, with a public leaderboard of model and agent pairs. It is hosted by Stanford, Harbor and the Laude Institute.","citation":"https://www.tbench.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"claims":{"value":"A benchmark to measure and evolve with the frontier of agent work","citation":"https://www.tbench.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"modalities":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"created":{"value":"2025-01-17","citation":"https://github.com/harbor-framework/terminal-bench-1","status":"real-data","tier":"T1","source_class":"repo"},"latest-release":{"value":"last commit 2026-07-11","citation":"https://github.com/harbor-framework/terminal-bench-1","status":"real-data","tier":"T1","source_class":"repo"},"license":{"value":"Apache-2.0","citation":"https://www.tbench.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"gh":{"value":"https://github.com/harbor-framework/terminal-bench-1 (2613★)","citation":"https://github.com/harbor-framework/terminal-bench-1","status":"real-data","tier":"T1","source_class":"repo"},"mindshare":{"value":"2613 GitHub stars","citation":"https://github.com/harbor-framework/terminal-bench-1","status":"real-data","tier":"T1","source_class":"repo"},"citations":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"funding":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"customers":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"pricing":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"compliance":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"data-handling":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"deployment":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"hq":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"founders":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"volume":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"perf":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"repro":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"code-release":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"api-surface":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"latency":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"throughput":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"backend-storage":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"multi-tenancy":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"encryption":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"sso-rbac":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"embedding-model":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"consistency":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"versioning":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"tombstoning":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"schema-evolution":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"namespace":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"contradiction":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"forgetting":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"mcp-support":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"a2a-support":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"otel":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"webhooks":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"import-export":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"integration-count":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"orchestration":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"programmatic-control":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"vendor-benchmarks":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"pricing-specifics":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"agent-abstraction":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"memory-primitives":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"llm-lock":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"runtimes":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"session-handling":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"validated-verticals":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"time-to-running":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"anti-fit":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"optimised-for":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"adjacent-infrastructure":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"pros":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cons":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"links":{"value":"https://www.tbench.ai/ ; https://github.com/harbor-framework/terminal-bench-1","citation":"https://www.tbench.ai/","status":"real-data","tier":"T2","source_class":"vendor"},"obs-langsmith":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-opentelemetry":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-datadog":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-helicone":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-weave":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-langfuse":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-arize":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"obs-custom":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-token-budget":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-prompt-caching":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-semantic-caching":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-batching":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-model-routing":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-streaming-only":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-observability-cost-attribution":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-langsmith-evals":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-braintrust":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-weights-and-biases-agent":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-helicone-evals":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-custom-test-harness":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-human-loop":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"eval-production-traffic-replay":{"value":"no","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"commit-trajectory":{"value":"searched not found","citation":"https://github.com/harbor-framework/terminal-bench-1","status":"depth-floor-reached","tier":"T1","source_class":"repo"},"citation-trajectory":{"value":"not applicable — non-paper row","citation":null,"status":"not-applicable","tier":"T3"},"download-trajectory":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-input-usd-per-mtok":{"value":"not applicable — non-hosted pricing model","citation":null,"status":"not-applicable","tier":"T3"},"cost-output-usd-per-mtok":{"value":"not applicable — non-hosted pricing model","citation":null,"status":"not-applicable","tier":"T3"},"cost-tier":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"cost-pricing-model":{"value":"unknown","citation":null,"status":"estimate","tier":"T3"},"cost-last-verified":{"value":"searched not found","citation":"https://www.tbench.ai/","status":"depth-floor-reached","tier":"T2","source_class":"vendor"},"capability-composite-score":{"value":"(LLM unverified)","citation":null,"status":"estimate","tier":"T3"},"capability-band":{"value":"(LLM unverified)","citation":null,"status":"estimate","tier":"T3"},"capability-benchmark-sources":{"value":"(LLM unverified)","citation":null,"status":"estimate","tier":"T3"},"capability-last-verified":{"value":"(LLM unverified)","citation":null,"status":"estimate","tier":"T3"},"use-case-tags":{"value":"(LLM unverified)","citation":null,"status":"estimate","tier":"T3"},"use-case-anti-tags":{"value":"(LLM unverified)","citation":null,"status":"estimate","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://www.tbench.ai/","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":"2026-10-29","citation":"https://mrpeppersdev.github.io/agent-infrastructure-landscape/systems/terminal-bench--tbench-ai","status":"real-data","tier":"T2","source_class":"catalog"},"compliance-certifications":{"value":"not applicable — no hosted service","citation":"https://github.com/laude-institute/terminal-bench","status":"not-applicable","tier":"T1","source_class":"repo"},"sdk-languages":{"value":"python","citation":"https://raw.githubusercontent.com/laude-institute/terminal-bench/main/README.md","status":"real-data","tier":"T2","source_class":"repo"},"protocol-support":{"value":"","citation":null,"status":"no-data","tier":"T3"},"maturity":{"value":"","citation":null,"status":"no-data","tier":"T3"}},"corroboration":{"cited_cells":12,"third_party_cells":0},"edges":{"outgoing":[],"incoming":[]},"history":[{"date":"2026-10-30","commit":"98ac84a5b9","pr":347,"kind":"added","changes":[]}],"license":"CC-BY-4.0","source":"https://github.com/MrPeppersDev/agent-infrastructure-landscape/blob/main/data/landscape.json"}