{"jtbd":{"id":"computer-use-browser-agent-evals","slug":"computer-use-browser-agent-evals","name":"Browser, WebArena & Desktop Computer-Use Agent Evaluation","shortName":"Computer-use & browser agent evals"},"recommended":{"role":"depot_pick","id":"browserbase","slug":"browserbase","name":"Browserbase","website":"https://www.browserbase.com","editorialOverall":8.39,"scoreKind":"curated_estimate","scoreAsOf":"2026-10-28","price":{"available":true,"unavailableReason":null,"skus":[{"id":"browserbase-developer-browser-hour","providerId":"browserbase","sku":"Developer browser hour overage","unit":"usd_per_browser_hour","amountUsd":0.12,"currency":"USD","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_browser_hour","priceSortEligible":false,"qualifier":"After included browser hours on the Developer plan. Not a subscription and not a token price.","verifiedAsOf":"2026-10-28","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"browserbase-developer-plan","providerId":"browserbase","sku":"Developer plan","unit":"usd_per_month","amountUsd":20,"currency":"USD","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_month","priceSortEligible":false,"qualifier":"Monthly plan fee. Included hours are not converted into this fee.","verifiedAsOf":"2026-10-28","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"browserbase-fetch-calls","providerId":"browserbase","sku":"Fetch calls","unit":"usd_per_1k_calls","amountUsd":1,"currency":"USD","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_calls","priceSortEligible":false,"qualifier":"Developer plan Fetch overage without proxies. With proxies is a separate row.","verifiedAsOf":"2026-10-28","sourceCheck":"reconfirmed","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"browserbase-fetch-calls-proxy","providerId":"browserbase","sku":"Fetch calls with proxies","unit":"usd_per_1k_calls","amountUsd":4,"currency":"USD","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_calls","priceSortEligible":false,"qualifier":"Developer plan Fetch overage with proxies.","verifiedAsOf":"2026-10-28","sourceCheck":"reconfirmed_manual","ageDays":1,"stale":false,"firstSeen":"2026-10-03","lastChanged":null,"frequentlyChanging":false},{"id":"browserbase-search-calls","providerId":"browserbase","sku":"Search calls (default: Parallel Advanced)","unit":"usd_per_1k_searches","amountUsd":5,"currency":"USD","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-21","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_searches","priceSortEligible":false,"qualifier":"Developer and Startup overage after the 1,000 included Search calls, default search provider (Parallel, mode advanced). Pricing page 2026-10-21: '1,000 Search calls then $5/1k searches by default with more options' and '$5/1k for Parallel Advanced'; docs https://docs.browserbase.com/platform/search/overview.md (2026-10-21): '| `parallel` | `advanced` (default) | $5 |'. Other providers are separate rows in the same unit: browserbase-search-calls-parallel-fast ($1/1k) and browserbase-search-calls-exa ($7/1k). Included searches are shared across providers and modes. Note: the docs plans table https://docs.browserbase.com/account/billing/plans.md (fetched 2026-10-21) still shows a single '| *Search overage* | N/A | $7/1k calls | $7/1k calls | Custom |', which matches only the Exa price; the pricing page (commercial source) and the docs Search page give $5 as the default.","verifiedAsOf":null,"sourceCheck":"amount_only","ageDays":8,"stale":false,"firstSeen":"2026-10-03","lastChanged":"2026-10-21","frequentlyChanging":false},{"id":"browserbase-search-calls-exa","providerId":"browserbase","sku":"Search calls (Exa)","unit":"usd_per_1k_searches","amountUsd":7,"currency":"USD","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-21","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_searches","priceSortEligible":false,"qualifier":"Developer and Startup overage after the 1,000 included Search calls when the request sets provider=exa. Pricing page 2026-10-21: '$7/1k for Exa'; docs https://docs.browserbase.com/platform/search/overview.md (2026-10-21): '| `exa` | None | $7 |'. This is the $7 the docs plans table (https://docs.browserbase.com/account/billing/plans.md) shows as the single Search overage. Not the default; included searches are shared across providers and modes.","verifiedAsOf":null,"sourceCheck":"amount_only","ageDays":8,"stale":false,"firstSeen":"2026-10-21","lastChanged":null,"frequentlyChanging":false}],"normalizedUsdPerMillionTokens":null,"normalizationStatus":"unit_mismatch","normalizationReason":"unit_mismatch"}},"priceComparison":{"skuKind":"none","unit":null,"comparison":"no comparable sourced unit for this job; chat input $/1M and other units were not borrowed","amountLabel":"Matching price","reportsUsdPerMillion":false,"matchedCandidates":0},"cheapestInput":null,"cheapest":null,"recommendedWorkloadQuote":{"providerId":"browserbase","providerName":"Browserbase","skuId":"browserbase-startup-browser-hour","item":"Startup browser hour overage","plan":"Startup browser hour overage — After included browser hours on the Startup plan","unit":"usd_per_browser_hour","amountUsd":0.1,"outputSkuId":null,"outputItem":null,"outputAmountUsd":null,"outputUnit":null,"sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28","pricingLastVerifiedAt":"2026-10-28","isFlagshipForJob":false,"differsFromFloorCheapest":false,"representativeQuote":{"skuId":"browserbase-startup-browser-hour","item":"Startup browser hour overage","plan":"Startup browser hour overage — After included browser hours on the Startup plan","amountUsd":0.1,"inputOrUnitUsd":0.1,"unit":"usd_per_browser_hour","outputUsd":null,"outputUnit":null,"sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"unitsPerTask":0.05,"baseCostPer1kTasksUsd":5,"totalUsd":5.75,"estimatedTotalUsd":5.75,"perTaskUsd":0.00575,"estimatedCostPerTaskUsd":0.00575,"formula":"(1,000 tasks * 0.05 hr/task * 0.1/browser_hour) * 1.15 overhead","assumptions":"1,000 tasks @ 3 min (0.05 hr) runtime per task with 1.15x retry overhead."}},"representativeQuote":{"skuId":"browserbase-startup-browser-hour","item":"Startup browser hour overage","plan":"Startup browser hour overage — After included browser hours on the Startup plan","amountUsd":0.1,"inputOrUnitUsd":0.1,"unit":"usd_per_browser_hour","outputUsd":null,"outputUnit":null,"sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-28"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"unitsPerTask":0.05,"baseCostPer1kTasksUsd":5,"totalUsd":5.75,"estimatedTotalUsd":5.75,"perTaskUsd":0.00575,"estimatedCostPerTaskUsd":0.00575,"formula":"(1,000 tasks * 0.05 hr/task * 0.1/browser_hour) * 1.15 overhead","assumptions":"1,000 tasks @ 3 min (0.05 hr) runtime per task with 1.15x retry overhead."},"cheapestGoodEnough":{"band":{"rule":"editorial overall >= Depot Pick overall - 0.5","minOverall":7.89,"pickOverall":8.39,"points":0.5},"pick":null,"reason":"no_matching_sourced_price","cheaperButBelowBand":[]},"dates":{"scoreAsOf":"2026-10-28","scoreKind":"curated_estimate","priceVerifiedAsOf":"2026-10-28","note":"scoreAsOf is when the editorial score was last set; priceVerifiedAsOf is the newest fact-check of the pick's price rows. They are separate: a fresh price check does not re-score."},"sourcedInputs":[],"pickIsPriceWinner":null,"priceWinnerReason":"no_comparison_no_candidate_has_matching_sourced_price","priceWinnerNote":"Nothing was compared. no comparable sourced unit for this job; chat input $/1M and other units were not borrowed pickIsPriceWinner is null.","excluded":1,"coverage":{"candidates":5,"withAnySourcedRow":4,"withSourcedInputUsdPerMillion":0,"withMatchingPrice":0,"excludedNoSourcedPrice":1,"excludedFromCheapestInput":5},"normalizedUsdPerMillionTokens":null,"normalizationReason":"input_and_output_are_not_blended","seo":{"published":false,"reason":"Only 0 candidate(s) have a matching Matching price (none). Need 3 before a crawlable price section. Quote JSON is still returned."},"skipTopPick":false,"matchedConstraints":[],"unsupportedConstraints":[],"routePlan":{"jtbdId":"computer-use-browser-agent-evals","primary":{"providerId":"browserbase","name":"Browserbase","overall":8.39,"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":8.39,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"primary","reason":"Editorial Depot Pick for Browser, WebArena & Desktop Computer-Use Agent Evaluation; healthy/eligible under caller constraints."},"omittedReason":null,"fallback":[{"providerId":"e2b","name":"E2B","overall":8.63,"scoreBand":{"low":8,"mid":8.6,"high":9.2,"halfWidth":0.6,"basis":"editorial_prior","display":"8.0–9.2 (editorial prior)"},"scoreLayers":{"editorialPrior":8.63,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Browser, WebArena & Desktop Computer-Use Agent Evaluation."},{"providerId":"steel-dev","name":"Steel.dev","overall":8.29,"scoreBand":{"low":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"scoreLayers":{"editorialPrior":8.29,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Browser, WebArena & Desktop Computer-Use Agent Evaluation."},{"providerId":"browser-use","name":"Browser Use Cloud","overall":7.44,"scoreBand":{"low":6.8,"mid":7.4,"high":8,"halfWidth":0.6,"basis":"editorial_prior","display":"6.8–8.0 (editorial prior)"},"scoreLayers":{"editorialPrior":7.44,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Browser, WebArena & Desktop Computer-Use Agent Evaluation."},{"providerId":"browserstack","name":"BrowserStack","overall":8.03,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.03,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-28","editorialPriorAsOf":"2026-10-28","role":"fallback","reason":"Ranked fallback route for Browser, WebArena & Desktop Computer-Use Agent Evaluation."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"browserbase","activePrimaryId":"browserbase","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":"computer-use-browser-agent-evals","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}},"freshness_state":"fresh","cite":"Depot Pick for computer-use-browser-agent-evals: browserbase (asOf 2026-10-28). See GET /api/jtbds/computer-use-browser-agent-evals + GET /api/methodology.","asOf":"2026-10-28","honesty":["Recommended provider is the current Depot Pick from GET /api/decide. This quote does not change scores.","SKU rows come from data/pricing-rows.json via GET /api/pricing. Input and output stay on separate rows.","cheapestInput compares one native unit matching this job; non-token jobs never borrow chat $/1M rates.","pickIsPriceWinner is null when fewer than 2 candidates share a matching sourced unit price."],"links":{"decide":"/api/decide?jtbd=computer-use-browser-agent-evals","quote":"/api/quote?jtbd=computer-use-browser-agent-evals","pricing":"/api/pricing?provider=browserbase","leaderboardPrice":"/api/leaderboards?jtbd=computer-use-browser-agent-evals&sort=price","humanPage":"/jtbds/computer-use-browser-agent-evals#quote","methodology":"/api/methodology"},"sourceConflicts":[{"providerId":"browserbase","field":"Free plan overage","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-21","quotes":["Every plan scales past its included usage, so no caps or throttling as you build, billed at your plan’s rate.","| *Hours overage* | N/A | \\$0.12/hr | \\$0.10/hr | Custom | (docs.browserbase.com/account/billing/plans.md)"],"safeAssumption":"Free is not costed above 1 browser hour or any proxy use (no Free overage rate is published); budget on Developer."},{"providerId":"browserbase","field":"Search overage rate","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-21","quotes":["1,000 Search calls then $5/1k searches by default with more options","- $1/1k for Parallel Fast … - $5/1k for Parallel Advanced … - $7/1k for Exa","| *Search overage* | N/A | \\$7/1k calls | \\$7/1k calls | Custom | (docs.browserbase.com/account/billing/plans.md)","| `parallel` | `fast` | $1 | · | `parallel` | `advanced` (default) | $5 | · | `exa` | None | $7 | (docs.browserbase.com/platform/search/overview.md, 2026-10-21)"],"safeAssumption":"Search is not a meter here; budget $5/1k for the default provider (Parallel Advanced), $7/1k if you set provider=exa, $1/1k for provider=parallel mode=fast (see the three browserbase-search-calls* catalog rows).","resolution":"Resolved 2026-10-21: $5 and $7 are different search providers, not a conflict. $5/1k = default (Parallel Advanced), $7/1k = Exa, $1/1k = Parallel Fast, per the pricing page and the docs Search page. Only the docs plans table's single '$7/1k calls' line is out of step (it matches Exa). Catalog rows: browserbase-search-calls $5 (default), browserbase-search-calls-exa $7, browserbase-search-calls-parallel-fast $1, all usd_per_1k_searches. Approval: Ethan delegation 2026-10-21 19:41 ET (chat t55u): 'You make all decisions' -> decided by Agent Depo."},{"providerId":"browserbase","field":"Developer data retention","sourceUrl":"https://www.browserbase.com/pricing","asOf":"2026-10-21","quotes":["| Data Retention | 7 days | 30 days | 30 days | 30+ days | (pricing page)","| **Data Retention** | 7 days | 7 days | 30 days | 30+ days | (docs.browserbase.com/account/billing/plans.md)"],"safeAssumption":"Assume 7 days on Developer."}],"volumeEstimateHint":"Add &volume=<number> for a plan-level monthly cost (GET /api/estimate?jtbd=computer-use-browser-agent-evals&workload=...)"}