{"uid":"cap_lJ_nAEsnlN4Bkfn1LyjMV","slug":"agents-forwardlane-com-list-benchmark-tasks-0bb18889","name":"List Benchmark Tasks","description":"Catalog of SWE-bench-format benchmark tasks (metadata only).\n\nEach item carries ``instance_id``, ``repo``, ``difficulty``, ``domain``,\n``complexity`` (when scored), ``fail_to_pass_count``,\n``pass_to_pass_count``, ``created_at``, ``version`` and ``solve_rate``.\nThe problem statement, gold patch and test lists are not included; fetch\none task by ``instance_id`` for the full record. ``total`` is the number\nof tasks matching the filters before ``limit`` is applied; items are\nnewest first.","url":"https://agents.forwardlane.com/api/benchmark/tasks?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","properties":{"repo":{"type":"string","anyOf":[{"type":"string"},{"type":"null"}],"title":"Repo","description":"Filter by repository name"},"limit":{"type":"integer","title":"Limit","default":20,"maximum":500,"minimum":1,"description":"Maximum tasks to return"},"domain":{"type":"string","anyOf":[{"type":"string"},{"type":"null"}],"title":"Domain","description":"Filter by domain"},"difficulty":{"type":"string","anyOf":[{"type":"string"},{"type":"null"}],"title":"Difficulty","description":"Filter by difficulty (easy/medium/hard)"}}},"responseSchema":{"type":"object","additionalProperties":true},"example":null,"exampleRequest":null,"tags":[],"displayCostAmount":"0.000000","displayCostAsset":"USD","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"1.00","reviews":0,"stars":null,"state":"rated"},"availabilityStatus":"healthy","priceObserved":{"p10Cents":"2.0000","medianCents":"2.0000","p90Cents":"2.0000","minCents":"2.0000","maxCents":"2.0000","p95Cents":"2.0000","sampleCount":1,"varies":false,"failureChargeRate":null},"sessionDeposit":null,"pricing":{"kind":"unknown","summary":"~$0.02/call (observed)","primary":{"kind":"unknown","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"},"accepted":[{"kind":"unknown","protocol":"mpp","network":"tempo","amountUsd":null,"per":"call","confidence":"unknown"}]},"paymentMethods":[{"uid":"pm_Par00jfWo4WvmUPoO3lxb","protocol":"mpp","methodType":"crypto","chain":"tempo","mode":"charge","costAmount":"0.000000","costPer":"request","priority":0,"asset":"0x20C000000000000000000000b9537d11c60E8b50","unit":"request","depositMicros":null,"planRef":null}],"brandName":"agents.forwardlane.com","brandSlug":"agents-forwardlane-com-x402","brandBaseUrl":"https://agents.forwardlane.com","brandDocsUrl":null,"whatItDoes":"Lists SWE-bench style benchmark task instances from ForwardLane's financial-services code repositories, with optional filtering by repo, domain, and difficulty.","exampleAgentPrompt":"Show me up to 50 hard SWE-bench benchmark tasks from ForwardLane's financial-services repos, filtered to the risk-management domain.","exampleUseCases":[{"title":"Browsing tasks by difficulty tier","prompt":"Pull me a list of easy benchmark tasks from ForwardLane's financial repo intelligence platform so I can start with simpler coding challenges first."},{"title":"Filtering benchmark tasks by repository","prompt":"Get me benchmark tasks specifically from the 'portfolio-analytics' repo on ForwardLane — up to 30 of them please."},{"title":"Finding domain-specific evaluation tasks","prompt":"List all available medium-difficulty benchmark tasks in the compliance domain from ForwardLane's SWE-bench evaluation set."}],"resultDescription":"A JSON object containing a list of SWE-bench benchmark task instances matching the specified filters. Each task includes details such as instance ID, repository name, domain, and difficulty. Returns up to the specified limit (default 20, max 500).","failureModes":["Invalid difficulty value (not easy/medium/hard) returns an error or empty results","Specifying a non-existent repo name returns empty task list","Limit below 1 or above 500 triggers a validation error","Network or server error returns a 5xx response","No tasks match the combined filters, resulting in an empty list"],"whenToPreferThis":"Use this endpoint when you need to discover or browse the available SWE-bench benchmark tasks across ForwardLane's 151 private financial-services repositories — especially when you want to filter by repo name, domain, or difficulty before retrieving a specific task with Get Benchmark Task. Prefer this over Get Benchmark Task when you don't yet know the instance_id and need to explore what tasks exist.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":2,"lastUsedAt":"2026-10-23T01:51:03.691Z","lastSuccessfullyRanAt":"2026-10-23T01:51:03.691Z","lastHealthCheckAt":"2026-10-26T07:05:14.723Z","isFirstParty":false,"canonicalSlug":"agents-forwardlane-com-list-benchmark-tasks-0bb18889"}