{"evidenceStatus":{"decisionRole":"independent_prior_and_candidate_generator","positioning":"The independent, agent-readable prior for choosing AI infrastructure — not a universal router, generic marketplace, or synthetic leaderboard.","freshnessThresholdDays":30,"freshness_policy":{"policy_version":"agentdepot.freshness_policy.v1","threshold_days":30},"freshness_state":"fresh","editorial_freshness_state":"fresh","unqualified_current_pick_allowed":true,"pick_qualification":"qualified_current_pick","promotionClass":"deterministic_source_reverified","evidenceClass":"editorial_prior","staleDowngraded":false,"effectiveConfidence":"high","confidenceHalfWidth":0.5,"pickScoreAgeDays":3,"editorialJudgmentAgeDays":9,"pricingAgeDays":3,"isPickScoreStale":false,"isPricingStale":false,"editorialJudgmentAsOf":"2026-10-19","pricingVerifiedAt":"2026-10-25","outcomeVerifiedAt":null,"effectiveVerifiedAsOf":"2026-10-25","downgradeReasons":[],"stalenessWarning":"Editorial judgment and deterministic pricing verification are both within the 30-day freshness threshold.","promotionGate":{"deterministicPricingCheck":true,"approvedScoreReaffirm":true,"pendingHumanReviewBlock":false,"zeroUnverifiedSkus":true,"costEfficiencyConsistent":true,"lockInAndReliabilityConsistent":true,"secondModelOrRuleAudit":true,"countersignReceiptIds":[],"otsAttestationHead":"b32634d5784cbfe663be0a16cce4f60a3ff1c3d4490437be00361cb4ae5d5d59","sourceCheckDate":"2026-10-27","activePricingRowsCount":0,"freeResourcesCount":1,"runnerUpPricingRowsCount":1},"claimProvenance":{"claim_id":"claim:public-agent-benchmarks:promptfoo:depot-pick","provider_id":"promptfoo","jtbd_id":"public-agent-benchmarks","primary_url":"https://www.promptfoo.dev/pricing","source_type":"primary_pricing","source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28","claim_support_state":"claim_specific_supported","max_allowed_evidence_class":"replicated_outcome","defect_codes":[],"sources":[{"original_url":"https://www.promptfoo.dev/pricing","final_url":"https://www.promptfoo.dev/pricing","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_pricing","is_claim_specific":true,"source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.promptfoo.dev","final_url":"https://www.promptfoo.dev","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:0f3e1cf49c5b44e0","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","final_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_benchmark_or_status","is_claim_specific":true,"source_revision":"sha256:0f488916f20c16b9","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"verifiedOutcomeSummary":{"totalVerifiedReceipts":0,"byEvidenceTier":{"E0_ASSERTION":0,"E1_SOURCE_BOUND":0,"E2_DELIVERY":0,"E3_INDEPENDENT_OUTCOME":0,"E4_REPLICATED_OUTCOME":0},"bySubjectLayer":{"provider":0,"product":0,"model_version":0,"runtime_route":0}}},"freshness_state":"fresh","freshness_policy":{"policy_version":"agentdepot.freshness_policy.v1","threshold_days":30},"runtimeRoutes":[{"routeId":"public-agent-benchmarks:promptfoo:primary","roleForJob":"depot_pick","provider":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","website":"https://www.promptfoo.dev","status":"active"},"model":{"representativeModelId":"Promptfoo Primary Runtime","skuId":null,"unit":null,"amountUsd":null,"sourceUrl":"https://www.promptfoo.dev","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"self_hosted_or_oss_compatible","endpointPattern":"https://www.promptfoo.dev (self hosted or oss compatible)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Promptfoo Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":true,"freeTierSummary":"Promptfoo (oss, asOf 2026-10-25)","rateLimitsSummary":"See /api/limits?provider=promptfoo","subscriptionFirstEligible":true,"documentedPlansCount":0},"regions":{"supportedRegions":["global","us"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":7.8,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":9,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":true,"selfHostable":true},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":0,"unverifiedSkus":0,"liveFailoverTargetId":"braintrust"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:promptfoo:promptfoo-primary:self_hosted_or_oss_compatible:global","provider_id":"promptfoo","product_id":"promptfoo-core","model_id":"promptfoo-primary","version":"2026-10-28","route_class":"self_hosted_or_oss_compatible","region":"global","score_status":"unknown","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}},{"routeId":"public-agent-benchmarks:braintrust:primary","roleForJob":"runner_up","provider":{"id":"braintrust","slug":"braintrust","name":"Braintrust","website":"https://www.braintrust.dev","status":"active"},"model":{"representativeModelId":"Braintrust Primary Runtime","skuId":null,"unit":null,"amountUsd":null,"sourceUrl":"https://www.braintrust.dev","asOf":"2026-10-28"},"servingRoute":{"primaryRouteType":"managed_cloud_service","endpointPattern":"https://www.braintrust.dev (managed cloud service)","aggregatorAlternatives":[{"aggregatorId":"direct-only","name":"Braintrust Direct API","routeType":"first_party","tradeoff":"Direct vendor SDK/REST contract; pair with runner-up for multi-vendor failover."}]},"accountAndQuota":{"freeTierAvailable":false,"freeTierSummary":null,"rateLimitsSummary":"Starter: Starter For everyone $0 / month - $10 credits + tok rates - 1 GB processed data + $4/GB - ","subscriptionFirstEligible":true,"documentedPlansCount":2},"regions":{"supportedRegions":["us","global"],"multiRegionFailover":true,"euResidencyAvailable":true},"toolSchemaSupport":{"strictJsonSchema":true,"parallelToolCalls":false,"mcpServerAvailable":true,"streamingSupported":true},"latencyTier":{"tier":"standard_1s_to_5s","latencyReliabilityScore":8.6,"coldStartNotes":"Standard warm pool; check provider SLA for burst concurrency"},"privacyConfig":{"privacyPostureScore":8,"zeroDataRetentionAvailable":true,"trainsOnApiDataByDefault":false,"hipaaEligible":false,"selfHostable":false},"availabilityStatus":{"providerStatus":"active","verifiedActiveSkus":0,"unverifiedSkus":0,"liveFailoverTargetId":"promptfoo"},"subject_ref":{"layer":"runtime_route","subject_id":"runtime_route:braintrust:braintrust-primary:managed_cloud_service:us","provider_id":"braintrust","product_id":"braintrust-core","model_id":"braintrust-primary","version":"2026-10-28","route_class":"managed_cloud_service","region":"us","score_status":"layer_evidenced","layer_score":"unknown","inherited_from_parent_layer":false,"inheritance_policy":"no_cross_layer_inheritance"}}],"verifiedOutcomes":[],"jtbd":{"id":"public-agent-benchmarks","slug":"public-agent-benchmarks","name":"Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench)","shortName":"Public agent capability benchmarks","problemStatement":"Select and run standardized, contamination-checked public agent benchmarks matched to your agent's task taxonomy (coding, tool-policy dialogue, web/GUI actions, shell/CLI, function-calling, ML engineering) so capability claims are reproducible outside your private test set."},"pick":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","tagline":"Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…","website":"https://www.promptfoo.dev","overall":8.44,"scoreBand":{"low":7.9,"mid":8.4,"high":8.9,"halfWidth":0.5,"basis":"editorial_prior","display":"7.9–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.94,8.94],"formattedScore":"8.4 ± 0.5 (7.9–8.9 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.94,"mid":8.44,"high":8.94,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","dissentingEvidence":["Less polished product UI than Braintrust","Enterprise features gated","You bring judge costs","When not to use top pick: Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust.","Runner-up Braintrust (braintrust) is the primary alternative when constraints disqualify Promptfoo."],"whatWouldChangePick":["Caller constraint matching: Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust.","Live quota or rate-limit exhaustion on promptfoo (pass ?exhausted=promptfoo or liveQuota.exhaustedProviders=[\"promptfoo\"] to promote braintrust).","Active subscription or enterprise commit on braintrust combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://www.promptfoo.dev or unverified SKU drift detected by npm run check:sources."],"claimProvenance":{"claim_id":"claim:public-agent-benchmarks:promptfoo:depot-pick","provider_id":"promptfoo","jtbd_id":"public-agent-benchmarks","primary_url":"https://www.promptfoo.dev/pricing","source_type":"primary_pricing","source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28","claim_support_state":"claim_specific_supported","max_allowed_evidence_class":"replicated_outcome","defect_codes":[],"sources":[{"original_url":"https://www.promptfoo.dev/pricing","final_url":"https://www.promptfoo.dev/pricing","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_pricing","is_claim_specific":true,"source_revision":"sha256:1ae69609cf01d1ca","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://www.promptfoo.dev","final_url":"https://www.promptfoo.dev","redirected":false,"http_status":200,"reachable":true,"source_type":"generic_homepage","is_claim_specific":false,"source_revision":"sha256:0f3e1cf49c5b44e0","observed_at":"2026-10-28","checked_at":"2026-10-28"},{"original_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","final_url":"https://qaskills.sh/blog/llm-evals-comparison-openai-promptfoo-ragas","redirected":false,"http_status":200,"reachable":true,"source_type":"primary_benchmark_or_status","is_claim_specific":true,"source_revision":"sha256:0f488916f20c16b9","observed_at":"2026-10-28","checked_at":"2026-10-28"}]},"calibratedScore":{"point":8.44,"band":[7.94,8.94],"interval":{"lower":7.94,"upper":8.94,"half_width":0.5},"score_kind":"source_bound_prior_band","evidence_class":"source_bound","confidence":"medium","confidence_ceiling":"medium","age_days":3,"dissent":["Less polished product UI than Braintrust","Enterprise features gated","You bring judge costs","When not to use top pick: Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust.","Runner-up Braintrust (braintrust) is the primary alternative when constraints disqualify Promptfoo."],"what_would_change_this":["Caller constraint matching: Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust.","Live quota or rate-limit exhaustion on promptfoo (pass ?exhausted=promptfoo or liveQuota.exhaustedProviders=[\"promptfoo\"] to promote braintrust).","Active subscription or enterprise commit on braintrust combined with low switching-cost tolerance (existingSubscriptions + switchingCost.maxMigrationEffort=\"low\").","Sourced price increase >20% on https://www.promptfoo.dev or unverified SKU drift detected by npm run check:sources."],"subject_layer":"provider"},"subject_ref":{"layer":"provider","provider_id":"promptfoo","product_id":"promptfoo-core","model_id":null,"version":null,"route_class":null,"inheritance_policy":"no_cross_layer_inheritance"},"pricingNotes":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a single request made to your target system during red team testing.' Enterprise 'Custom' ('Contact us for a personalized quote.'; 'Enterprise customers can purchase additional probes for larger scale testing.'; 'Managed cloud deployment'). On-Premise 'Custom' ('Deployment on your own infrastructure'). No list price is published, so Enterprise price stays null.","scores":{"capabilityFit":8.2,"pricePerformance":9.2,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":9,"lockInRisk":2.5,"maturity":8,"overall":8.44,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},"liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"selectedPick":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","tagline":"Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…","website":"https://www.promptfoo.dev","overall":8.44,"scoreBand":{"low":7.9,"mid":8.4,"high":8.9,"halfWidth":0.5,"basis":"editorial_prior","display":"7.9–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.94,8.94],"formattedScore":"8.4 ± 0.5 (7.9–8.9 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.94,"mid":8.44,"high":8.94,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a single request made to your target system during red team testing.' Enterprise 'Custom' ('Contact us for a personalized quote.'; 'Enterprise customers can purchase additional probes for larger scale testing.'; 'Managed cloud deployment'). On-Premise 'Custom' ('Deployment on your own infrastructure'). No list price is published, so Enterprise price stays null.","scores":{"capabilityFit":8.2,"pricePerformance":9.2,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":9,"lockInRisk":2.5,"maturity":8,"overall":8.44,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},"editorialPick":{"id":"promptfoo","slug":"promptfoo","name":"Promptfoo","tagline":"Default OSS eval harness. Braintrust when you want hosted collaboration; Promptfoo when you want local/CI…","website":"https://www.promptfoo.dev","overall":8.44,"scoreBand":{"low":7.9,"mid":8.4,"high":8.9,"halfWidth":0.5,"basis":"editorial_prior","display":"7.9–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://www.promptfoo.dev","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.94,8.94],"formattedScore":"8.4 ± 0.5 (7.9–8.9 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.94,"mid":8.44,"high":8.94,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a single request made to your target system during red team testing.' Enterprise 'Custom' ('Contact us for a personalized quote.'; 'Enterprise customers can purchase additional probes for larger scale testing.'; 'Managed cloud deployment'). On-Premise 'Custom' ('Deployment on your own infrastructure'). No list price is published, so Enterprise price stays null.","scores":{"capabilityFit":8.2,"pricePerformance":9.2,"latencyReliability":7.8,"developerDx":8.8,"privacyPosture":9,"lockInRisk":2.5,"maturity":8,"overall":8.44,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},"disqualifiedCandidates":[],"runnersUp":[{"id":"braintrust","slug":"braintrust","name":"Braintrust","tagline":"Depot pick when evals are the product quality gate. Pair with Helicone/Langfuse for cheap request logs if…","website":"https://www.braintrust.dev","overall":8.22,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.22,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"operational","checkedAt":"2026-10-28T15:04:27.127Z","statusPageUrl":"https://status.braintrust.dev","latencyMs":1315,"indicator":"none","description":"Public status/endpoint reachable (HTTP 200)"},"scoreRange":[7.72,8.72],"formattedScore":"8.2 ± 0.5 (7.7–8.7 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.72,"mid":8.22,"high":8.72,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"Eval-first platform; data-based pricing with unlimited seats on many plans; strong CI eval story.","scores":{"capabilityFit":9.2,"pricePerformance":7.5,"latencyReliability":8.6,"developerDx":8.8,"privacyPosture":8,"lockInRisk":5,"maturity":8.2,"overall":8.22,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},{"id":"e2b","slug":"e2b","name":"E2B","tagline":"Depot default code sandbox for agents. Use for untrusted code; Daytona when you need persistent…","website":"https://e2b.dev","overall":8.59,"scoreBand":{"low":8,"mid":8.6,"high":9.2,"halfWidth":0.6,"basis":"editorial_prior","display":"8.0–9.2 (editorial prior)"},"scoreLayers":{"editorialPrior":8.59,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"operational","checkedAt":"2026-10-28T15:04:27.121Z","statusPageUrl":"https://status.e2b.dev","latencyMs":516,"indicator":"none","description":"Public status/endpoint reachable (HTTP 200)"},"scoreRange":[8.09,9.09],"formattedScore":"8.6 ± 0.5 (8.1–9.1 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":8.09,"mid":8.59,"high":9.09,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"Firecracker microVM sandboxes billed per second; templates; code interpreter for agents.","scores":{"capabilityFit":9.4,"pricePerformance":8,"latencyReliability":8.6,"developerDx":9.4,"privacyPosture":8.5,"lockInRisk":4,"maturity":8,"overall":8.59,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},{"id":"modal","slug":"modal","name":"Modal","tagline":"Depot darling for Python agent backends and bursty GPU jobs. If you think in functions not VMs, start here.","website":"https://modal.com","overall":8.46,"scoreBand":{"low":7.9,"mid":8.5,"high":9.1,"halfWidth":0.6,"basis":"editorial_prior","display":"7.9–9.1 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"operational","checkedAt":"2026-10-28T15:04:27.120Z","statusPageUrl":"https://status.modal.com","latencyMs":638,"indicator":"none","description":"Public status/endpoint reachable (HTTP 200)"},"scoreRange":[7.96,8.96],"formattedScore":"8.5 ± 0.5 (8.0–9.0 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.96,"mid":8.46,"high":8.96,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"As of 2026-10-24 (modal.com/pricing, fetched 2026-10-24): Python-native serverless GPU/CPU billed per second of compute ('You never pay for idle resources'). GPU list rates per second: H100 SXM5 '$0.001097', H200 SXM '$0.001261', B200 '$0.001736', A100 80 GB '$0.000694', L40S '$0.000542', A10 '$0.000306', L4 '$0.000222', T4 '$0.000164'; CPU '$0.0000131' per core per second (physical core, 2 vCPU equivalent); memory '$0.00000222' per GiB per second. Region selection '1.15 - 1.75x base prices'; non-preemptible execution '3x base prices' ('Sandboxes are billed at non-preemptible rates of 3x list price.'). Containers are kept alive '60 seconds after the last inputs', which is billed (configurable). Plans: Starter '$0 + compute / month' with '$30 / month free credits' ('100 containers + 10 GPU concurrency'); Team '$250 + compute / month' with '$100 / month free credits' ('5000 containers + 50 GPU concurrency'); Enterprise custom. Shared Endpoints are 'billed per token rather than per second' and not covered by included compute ('This took effect September 1, 2026.'). Excellent DX for jobs and endpoints; cold starts matter for interactive agents.","scores":{"capabilityFit":9,"pricePerformance":8.2,"latencyReliability":8.6,"developerDx":9.6,"privacyPosture":7.8,"lockInRisk":4.5,"maturity":8.2,"overall":8.46,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}},{"id":"weights-biases","slug":"weights-biases","name":"Weights & Biases","tagline":"Use for training/fine-tune discipline. For pure agent request tracing, Langfuse/Helicone are leaner.","website":"https://wandb.ai","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","pricingVerifiedAsOf":"2026-10-28","scoreVerifiedAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","liveHealth":{"status":"unknown","checkedAt":"2026-10-28T15:04:28.744Z","statusPageUrl":"https://wandb.ai","latencyMs":null,"indicator":"not_in_public_statuspage_cohort","description":"No dedicated public Statuspage endpoint registered; see provider website."},"scoreRange":[7.45,8.45],"formattedScore":"8.0 ± 0.5 (7.5–8.4 · editorial_prior)","evidenceClass":"editorial_prior","promotionClass":"deterministic_source_reverified","staleDowngraded":false,"effectiveConfidence":"high","confidenceInterval":{"low":7.45,"mid":7.95,"high":8.45,"halfWidth":0.5,"confidenceLevel":0.8,"basis":"deterministic_source_reverified_interval_0.5"},"sourceAgeDays":9,"pricingAgeDays":3,"freshness_state":"fresh","pricingNotes":"Experiment tracking + W&B Weave/LLM tools; seat and usage based; free tiers for individuals.","scores":{"capabilityFit":8.8,"pricePerformance":6.8,"latencyReliability":9,"developerDx":8.2,"privacyPosture":7.8,"lockInRisk":5.5,"maturity":9.4,"overall":7.95,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-28"}}],"scoreBand":{"low":7.9,"mid":8.4,"high":8.9,"halfWidth":0.5,"basis":"editorial_prior","display":"7.9–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"promptfoo","pickName":"Promptfoo","pickScore":8.44,"highestScoredCandidateId":"e2b","highestScoredCandidateName":"E2B","highestScore":8.59,"pickHasLowerCompositeScore":true,"delta":-0.15,"pickLeadsOnDimensions":["pricePerformance (9.2 vs 8)","privacyPosture (9 vs 8.5)","lower lockInRisk (2.5 vs 4)"],"explanation":"Promptfoo (8.44) is the editorial pick for Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench) over higher-composite E2B (8.59) because composite scores are provider-wide priors while Promptfoo wins on pricePerformance (9.2 vs 8), privacyPosture (9 vs 8.5), lower lockInRisk (2.5 vs 4): Promptfoo runs local, declarative YAML/CLI evaluation matrices across providers and models (Apache-2.0, $0 OSS CLI) with custom Python/JS graders and Docker/sandbox hooks — ideal for wrapping public benchmark subsets (BFCL, GAIA, τ-bench, SWE-bench Verified slices) in repeatable runs without SaaS lock-in."},"cheapest":null,"recommendedWorkloadQuote":null,"representativeQuote":null,"estimatedTaskCost":null,"freeAlternatives":[],"referenceDocs":[],"falsification":{"jtbdId":"public-agent-benchmarks","jtbdName":"Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench)","currentPickId":"promptfoo","currentPickScore":8.44,"challengerId":"braintrust","challengerScore":8.22,"currentScoreGap":0.22,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.37,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Braintrust (braintrust) outperforms Promptfoo (promptfoo) by >= 0.37 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Promptfoo's representative SKU for public-agent-benchmarks without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=promptfoo) or sustained >= 30% degraded/failed rate in verified production outcomes."],"frozenHoldoutPolicy":{"holdoutSplit":"20% frozen benchmark holdout tasks + 80% live production outcome receipts","requireCountersignReceipt":true,"requiredEvidenceTiers":["outcome_verified","reference_checked"],"minDistinctContributors":2,"antiGamingRule":"Unverified self-reports and seed/editorial rows never mutate picks or scores."},"triggers":[{"kind":"verified_outcomes_outperformance","challengerId":"braintrust","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.37,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"promptfoo","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"promptfoo","immediateOverrideUrl":"/api/decide?jtbd=public-agent-benchmarks&exhausted=promptfoo"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=public-agent-benchmarks","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"public-agent-benchmarks","providerId":"braintrust","outcome":"worked","detail":"Comparative production evaluation on public-agent-benchmarks (n>=10 tasks) with Countersign receipt.","confidence":"high","receipt":{"countersign":{"claim_id":"cs-00000000","status":"verified","evidence_tier":"outcome_verified","counts_as_verified":true}}}}},"whatWouldChangePick":["Braintrust (braintrust) outperforms Promptfoo (promptfoo) by >= 0.37 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Promptfoo's representative SKU for public-agent-benchmarks without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=promptfoo) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"public-agent-benchmarks","primary":{"providerId":"promptfoo","name":"Promptfoo","overall":8.44,"scoreBand":{"low":7.9,"mid":8.4,"high":8.9,"halfWidth":0.5,"basis":"editorial_prior","display":"7.9–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"primary","reason":"Editorial Depot Pick for Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench); healthy/eligible under caller constraints."},"omittedReason":null,"fallback":[{"providerId":"braintrust","name":"Braintrust","overall":8.22,"scoreBand":{"low":7.6,"mid":8.2,"high":8.8,"halfWidth":0.6,"basis":"editorial_prior","display":"7.6–8.8 (editorial prior)"},"scoreLayers":{"editorialPrior":8.22,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench)."},{"providerId":"e2b","name":"E2B","overall":8.59,"scoreBand":{"low":8,"mid":8.6,"high":9.2,"halfWidth":0.6,"basis":"editorial_prior","display":"8.0–9.2 (editorial prior)"},"scoreLayers":{"editorialPrior":8.59,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench)."},{"providerId":"modal","name":"Modal","overall":8.46,"scoreBand":{"low":7.9,"mid":8.5,"high":9.1,"halfWidth":0.6,"basis":"editorial_prior","display":"7.9–9.1 (editorial prior)"},"scoreLayers":{"editorialPrior":8.46,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench)."},{"providerId":"weights-biases","name":"Weights & Biases","overall":7.95,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":7.95,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Public Agent Capability Benchmarks (SWE-bench, τ-bench, GAIA, OSWorld, WebArena, Terminal-Bench, BFCL, MLE-bench)."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"promptfoo","activePrimaryId":"promptfoo","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":1,"pricingVerifiedAgeDays":1,"editorialPriorAsOf":"2026-10-28","pricingLastVerifiedAt":"2026-10-28"},"confidenceBand":{"low":7.9,"mid":8.4,"high":8.9,"halfWidth":0.5,"basis":"editorial_prior","display":"7.9–8.9 (editorial prior)"},"constraintsApplied":false,"matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","constraintBundle":{"schemaVersion":"agentdepot.constraints.v1","task":null,"jtbd":"public-agent-benchmarks","constraintsRaw":"","constraintTokens":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"typedConstraints":[],"quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[],"existingSubscriptions":[],"requiredCapabilities":[],"switchingCost":null}},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","tie":false,"scoreGap":0.22,"scoreMargin":0.22,"isNearTie":true,"pickConfidenceBand":"near_tie_co_pick","nearTie":{"isNearTie":true,"scoreMargin":0.22,"threshold":0.35,"pickConfidenceBand":"near_tie_co_pick","coPickProviderId":"braintrust","coPickProviderName":"Braintrust","coPickScore":8.22,"decidingFactor":"pricePerformance (9.2 vs 7.5)","methodologyWarning":"Top pick (8.44) and #2 runner-up (8.22) are separated by 0.22 points (<= 0.35 weight-sensitivity band). Treat them as co-picks and use the workload tie-breaker rule below rather than the raw composite decimal.","tieBreakerRule":"Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust."},"decidingFactor":"pricePerformance (9.2 vs 7.5)","tieNote":"Top pick (8.44) and #2 runner-up (8.22) are separated by 0.22 points (<= 0.35 weight-sensitivity band). Treat them as co-picks and use the workload tie-breaker rule below rather than the raw composite decimal.","rationale":"Promptfoo runs local, declarative YAML/CLI evaluation matrices across providers and models (Apache-2.0, $0 OSS CLI) with custom Python/JS graders and Docker/sandbox hooks — ideal for wrapping public benchmark subsets (BFCL, GAIA, τ-bench, SWE-bench Verified slices) in repeatable runs without SaaS lock-in.","whenNotTopPick":"Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust.","whenNotTopPickRules":[{"ifConstraint":"escape_hatch_clause_1","recommendedProviderId":"e2b","activeModelOrSku":"e2b-sandbox-1vcpu-per-s","reason":"Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards)"},{"ifConstraint":"exit:self_host_or_open_weights","recommendedProviderId":"weights-biases","activeModelOrSku":"wandb-teams","reason":"hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases"},{"ifConstraint":"escape_hatch_clause_3","recommendedProviderId":"braintrust","activeModelOrSku":"braintrust-pro","reason":"hosted dataset + scorer UI for team review — Braintrust."}],"bootstrap":{"sdkInstall":{"npm":"npm install promptfoo","pip":null},"installCommand":"npx promptfoo@latest init","envVars":["OPENAI_API_KEY"],"activeModelOrSku":"promptfoo-oss","canonicalSnippet":"# Run red-team & eval suite via CLI\nnpx promptfoo@latest eval -c promptfooconfig.yaml","docsUrl":"https://www.promptfoo.dev/docs/intro/","bootstrapReason":"Node CLI & library (promptfoo on npm); no separate Python package required.","authType":"api_key","signupUrl":"https://www.promptfoo.dev","apiKeyUrl":"https://www.promptfoo.dev","mcpServer":null,"cliInit":"npx promptfoo@latest init","verifyCommand":"test -n \"$OPENAI_API_KEY\" && echo \"OPENAI_API_KEY configured\""},"quickstartSpec":{"installCommand":"npx promptfoo@latest init","envVars":["OPENAI_API_KEY"],"activeModelOrSku":"promptfoo-oss","canonicalSnippet":"# Run red-team & eval suite via CLI\nnpx promptfoo@latest eval -c promptfooconfig.yaml","sdkInstall":{"npm":"npm install promptfoo","pip":null},"verifyCommand":"test -n \"$OPENAI_API_KEY\" && echo \"OPENAI_API_KEY configured\"","apiKeyUrl":"https://www.promptfoo.dev","docsUrl":"https://www.promptfoo.dev/docs/intro/","mcpServer":null,"bootstrapReason":"Node CLI & library (promptfoo on npm); no separate Python package required."},"operationalGotchas":[{"code":"hidden_spend_tier_gates","severity":"warning","summary":"Less polished product UI than Braintrust","sourceDate":"2026-10-28"},{"code":"hidden_spend_tier_gates","severity":"warning","summary":"Enterprise features gated","sourceDate":"2026-10-28"}],"relatedPacks":[],"skipTopPick":false,"skipReason":null,"matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","constraintBundle":{"schemaVersion":"agentdepot.constraints.v1","task":null,"jtbd":"public-agent-benchmarks","constraintsRaw":"","constraintTokens":[],"constraintDigest":"sha256:eb9d397ca67bcf6889704910eeb3a58796ea2ef5e54fb6289c71f6114f2c67a7","matchedConstraints":[],"unsupportedConstraints":[],"malformedConstraints":[],"conflictingConstraints":[],"typedConstraints":[],"quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[],"existingSubscriptions":[],"requiredCapabilities":[],"switchingCost":null},"pricingSummary":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a singl…","cite":"Depot Pick for public-agent-benchmarks: promptfoo (asOf 2026-10-28). See GET /api/jtbds/public-agent-benchmarks + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/public-agent-benchmarks?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=public-agent-benchmarks","why":"Depot Pick SKUs plus the cheapest sourced SKU whose unit matches this job. Does not change the pick. Does not blend input and output or borrow a chat rate for a non-chat job."},{"step":3,"title":"Open provider detail","href":"/api/providers/promptfoo","why":"Scores, pricingNotes, strengths/weaknesses, communitySignals (claims only)."},{"step":4,"title":"Cite methodology","href":"/api/methodology","why":"Required when publishing a Depot Pick citation."},{"step":5,"title":"Grab badge SVG","href":"/api/badge?type=depot-pick&jtbd=public-agent-benchmarks","why":"Embed in README / agent passport."},{"step":6,"title":"Post production insight","method":"POST","href":"/api/insights","why":"Unverified until curated; never auto-mutates official scores."}],"honesty":["Do not invent scores or benches.","Insights are claims until curated/reviewed; they never silently mutate official scores.","lockInRisk higher = more lock-in (worse).","normalizedUsdPerMillionTokens is set only for a single sourced token row. Otherwise null, with a machine-readable reason. Do not coerce GPU, minute, or per-1k search units.","Runners-up are not Depot Picks.","Depot overall is editorial_weighted, not Arena Elo and not an Artificial Analysis index."],"asOf":"2026-10-28","depth":{"whenNotToUse":{"text":"Need isolated Docker/microVM sandboxes to execute SWE-bench Verified, Terminal-Bench, or MLE-bench container tasks — E2B (or Modal for bursty parallel container shards); hosted experiment & dataset artifact tracking across training/eval sweeps — Weights & Biases; hosted dataset + scorer UI for team review — Braintrust.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"braintrust","name":"Braintrust","overallForJob":8.22,"pickOverallForJob":8.44,"beatsPickOn":["capabilityFit","latencyReliability","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":2.5,"runnerUpLockInRisk":5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":["open source (provider tag `oss`)"],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[],"migration":"The pick has lower stored lock-in risk than runner-up Braintrust (2.5 vs 5). Pick exit signals: open source (provider tag `oss`).","migrationReason":null,"derivedFrom":"stored lockInRisk scores, provider tags (oss, self-host, openai-compat, open-models), free rows that list this job, and verbatim provider notes. No migration guide was invented."}},"citation":{"text":"Agent Provider Depot (v0.13.9), Depot Pick for public-agent-benchmarks: promptfoo, scores as of 2026-10-28, retrieved 2026-10-29. https://getagentdepot.com/jtbds/public-agent-benchmarks","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/public-agent-benchmarks) (v0.13.9) — Depot Pick for `public-agent-benchmarks`: **promptfoo** (scores as of 2026-10-28, retrieved 2026-10-29)","fields":{"publisher":"Agent Provider Depot","version":"0.13.9","role":"depot_pick","jtbdId":"public-agent-benchmarks","providerId":"promptfoo","scoreAsOf":"2026-10-28","retrievedOn":"2026-10-29","page":"https://getagentdepot.com/jtbds/public-agent-benchmarks","api":"https://getagentdepot.com/api/decide?jtbd=public-agent-benchmarks"},"howToCite":"Cite Depot as an editorial, dated recommendation, not a benchmark: name the job, the Depot Pick (or runner-up), the score asOf date and the day you retrieved it, and link the job page. Format: “Agent Provider Depot (v{version}), Depot Pick for {jobId}: {providerId}, scores as of {scoreAsOf}, retrieved {retrievedOn}. {baseUrl}/jtbds/{jobId}”. Quote prices only with their own sourceUrl and asOf. If the pick's score is stale (freshness.pick.score.stale), say so."},"freshness":{"pick":{"score":{"asOf":"2026-10-28","ageDays":1,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-28","ageDays":1,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-28","sourceUrls":3,"sourcesReachable":3,"pricingRows":0,"pricingRowsReconfirmed":0,"note":"A source re-check confirms the page is reachable and, for pricing rows, that the stored amount and SKU name appear on it. It does not re-derive or change the score.","reason":null}},"scoreAsOf":"2026-10-28","editorialPriorAsOf":"2026-10-28","pricingLastVerifiedAt":"2026-10-28","pickLastReviewed":"2026-10-28","runnersUpScoreAsOf":["2026-10-28","2026-10-28","2026-10-28","2026-10-28"],"contractAsOf":"2026-10-03","pricingShape":"prose_notes_only","normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unavailable","normalizationReason":"no_sourced_price","shape":"prose_notes_only","filterable":false,"priceSortEligible":false,"priceSortKeyUsdPerMillionInputTokens":null,"rows":[],"notesExcerpt":"As of 2026-10-24 (promptfoo.dev/pricing, fetched 2026-10-24): Community 'Free Forever' ('Our open-source tool, perfect for individual developers and small teams.') with 'Red teaming (10k probes/month)' and 'Run locally or self-host on your own infrastructure'; 'A probe is a singl…","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-28","scoreAsOf":"2026-10-28","website":"https://www.promptfoo.dev","doNotParse":"Do not parse pricingNotes. Use rows only. normalizedUsdPerMillionTokens is a single number only when this provider has exactly one sourced token row. Input/output, context tiers, and non-token units stay null at this level.","gap":"No sourced price row for this provider. pricingNotes stay prose. See research/gaps.md."},"links":{"jtbd":"/jtbds/public-agent-benchmarks","jtbdApi":"/api/jtbds/public-agent-benchmarks","leaderboard":"/api/leaderboards?jtbd=public-agent-benchmarks","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=public-agent-benchmarks","decide":"/api/decide?jtbd=public-agent-benchmarks","humanPage":"/jtbds/public-agent-benchmarks","alternatives":"/api/alternatives?provider=promptfoo","canonical":"/api/canonical","quote":"/api/quote?jtbd=public-agent-benchmarks","falsify":"/api/falsify?jtbd=public-agent-benchmarks"},"stackContext":{"host":null,"framework":null,"repo":null,"lang":null,"existing":[],"volume":null,"sender":null,"detectedFromTask":[]},"keep":null,"contextAdvice":null,"communityFeedback":{"pickOnThisJob":{"failed":0,"degraded":0,"worked":0,"insights":0,"withVerifiedReceipt":0,"failureModes":{},"latestAt":null,"note":"Agent-reported claims (unverified unless a receipt is verified by Depot's re-check). They never change scores or picks."},"outcomes":{"job":{"n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"verifiedReports":0,"contributors":0,"excluded":{"seed_editorial":0,"test":0,"notFeedback":0},"reason":"no_submitted_outcome_reports_yet"},"pick":{"providerId":"promptfoo","n":0,"worked":0,"degraded":0,"failed":0,"failureModes":{},"evidenceTiers":{"agent_claim":0,"self_declared":0,"reference_checked":0,"outcome_verified":0},"reason":"no_submitted_outcome_reports_yet"},"scoresMutated":false,"more":"/api/outcomes?jtbd=public-agent-benchmarks"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}