{"jtbd":{"id":"coding-agent","slug":"coding-agent","name":"Coding agent / code generation","shortName":"Coding agent / code generation","problemStatement":"Agent must edit repos, call tools, and produce correct code with high reliability."},"pick":{"id":"anthropic","slug":"anthropic","name":"Anthropic","tagline":"Depot default for serious coding and production agents. Prefer Sonnet for cost/quality; reserve Opus for hard…","website":"https://www.anthropic.com","overall":8.42,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.42,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","pricingNotes":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","scores":{"capabilityFit":9.7,"pricePerformance":6.8,"latencyReliability":8.7,"developerDx":9.2,"privacyPosture":9,"lockInRisk":6.5,"maturity":9.4,"overall":8.42,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},"runnersUp":[{"id":"openai","slug":"openai","name":"OpenAI","tagline":"Default when you want maximum capability and ecosystem glue. Multi-home critical paths behind OpenAI-compat…","website":"https://openai.com","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":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"GPT-5.6 tiers (Sol/Terra/Luna) roughly $5/$30 to $1/$6 per 1M tokens; prompt caching with explicit breakpoints; batch discounts. Media (images/audio) billed separately.","scores":{"capabilityFit":9.6,"pricePerformance":6.2,"latencyReliability":8.8,"developerDx":9.5,"privacyPosture":7.8,"lockInRisk":7.2,"maturity":9.8,"overall":8.22,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"deepseek","slug":"deepseek","name":"DeepSeek","tagline":"Unbeatable $/quality for many workloads — if your compliance team allows it. Otherwise host similar open…","website":"https://www.deepseek.com","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":"2026-10-03","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Official API at api-docs.deepseek.com with very aggressive Flash/Pro token pricing (often cents per MTok on Flash tiers). Strong coding/reasoning open releases also hostable elsewhere. Geopolitical/compliance caveats for some orgs — host weights on Fireworks/Together/DeepInfra if direct API is blocked.","scores":{"capabilityFit":8.8,"pricePerformance":9.8,"latencyReliability":7.8,"developerDx":8,"privacyPosture":4.5,"lockInRisk":4,"maturity":7.5,"overall":7.95,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"mistral","slug":"mistral","name":"Mistral AI","tagline":"Default EU-friendly LLM vendor. Pair with Mistral-hosted or self-host open weights when sovereignty matters.","website":"https://mistral.ai","overall":8.05,"scoreBand":{"low":7.5,"mid":8.1,"high":8.7,"halfWidth":0.6,"basis":"editorial_prior","display":"7.5–8.7 (editorial prior)"},"scoreLayers":{"editorialPrior":8.05,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"La Plateforme API; mix of open and commercial models; EU-friendly positioning; competitive mid-tier pricing.","scores":{"capabilityFit":8.2,"pricePerformance":8.4,"latencyReliability":8,"developerDx":8,"privacyPosture":8.5,"lockInRisk":4,"maturity":8.2,"overall":8.05,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"zai","slug":"zai","name":"Z.AI (Zhipu GLM)","tagline":"International GLM via z.ai — catalog zai, not a second Zhipu mainland-only SKU. Strong cheap/coding runner…","website":"https://z.ai","overall":7.79,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.79,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (docs.z.ai/guides/overview/pricing): International OpenAI-compat api.z.ai. GLM-5.3 / 5.2 / 5.1 $1.40 in / $0.26 cached / $4.40 out per 1M; GLM-5 input $1, cached $0.20, output $3.20; GLM-4.7 input $0.60, cached $0.11, output $2.20; GLM-4.7-FlashX input $0.07, cached $0.01, output $0.40 (all per 1M, matching stored rows; re-checked on docs.z.ai/guides/overview/pricing 2026-10-21); GLM-4.7-Flash and GLM-4.5-Flash free. Vision GLM-4.6V $0.30/$0.90; GLM-OCR $0.03; GLM-Image $0.015/img; CogVideoX-3 $0.20/video; GLM-ASR-2512 $0.03/MTok (~$0.0024/min). Web Search tool $0.01/use. Cached-input storage limited-time free.","scores":{"capabilityFit":8.2,"pricePerformance":9,"latencyReliability":7.6,"developerDx":8,"privacyPosture":6,"lockInRisk":4.6,"maturity":8,"overall":7.79,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"minimax","slug":"minimax","name":"MiniMax","tagline":"Primary indie-usable Chinese multimodal API alongside Moonshot. Prefer Anthropic/OpenAI for coding agents…","website":"https://www.minimax.io","overall":7.83,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (platform.minimax.io/docs/guides/pricing-paygo): International api.minimax.io (OpenAI + Anthropic-compat). MiniMax-M3 ≤512k: list $0.60/$2.40 → permanent 50% off $0.30/$1.20 per 1M (cache read $0.06); >512k $0.60/$2.40 after promo. Priority tier 1.5×. M2.7 $0.30/$1.20 (highspeed $0.60/$2.40). TTS speech-2.8-turbo $60/M chars, hd $100/M. ASR $0.38/hr. Video H3 768P $0.08/s / 2K $0.13/s. image-01 $0.0035. Token Plan (Plus/Max/Ultra) is closed to new purchases; its figure was removed. It is replaced by M Plan, listed at platform.minimax.io/docs/m-plan/monthly-offer as of 2026-10-21 at regular prices of Go $22/month, Explore $55/month and Build $132/month (first month 50% off; not stored as rows). Mainland keys use api.minimaxi.com — not interchangeable.","scores":{"capabilityFit":8.4,"pricePerformance":8.8,"latencyReliability":7.8,"developerDx":8.2,"privacyPosture":6.2,"lockInRisk":4.8,"maturity":7.6,"overall":7.83,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"dashscope","slug":"dashscope","name":"Alibaba Cloud Model Studio (DashScope)","tagline":"Catalog dashscope for Alibaba Model Studio / DashScope international Qwen. Complements Moonshot/MiniMax/Z.AI…","website":"https://www.alibabacloud.com/help/en/model-studio/","overall":7.86,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.86,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (alibabacloud.com/help/en/model-studio/model-pricing International): Qwen3.8-Max $2/$6 per 1M; Qwen3.7-Max $2.5/$7.5 (limited-time 50% off on some SKUs); Qwen3-Max $1.2/$6 (≤32k) tiering up at longer contexts; Qwen-Plus class ~$0.40/$1.20–$1.60. Batch often 50% off. Singapore free quotas (~1M tokens/90d) on many models. Intl endpoint dashscope-intl.aliyuncs.com; regional MaaS hosts for CN/EU/US/JP. Coding/Token Plans available in Singapore.","scores":{"capabilityFit":8.6,"pricePerformance":8.2,"latencyReliability":8.4,"developerDx":7.2,"privacyPosture":7,"lockInRisk":5.5,"maturity":8.8,"overall":7.86,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.42,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"anthropic","pickName":"Anthropic","pickScore":8.42,"highestScoredCandidateId":"anthropic","highestScoredCandidateName":"Anthropic","highestScore":8.42,"pickHasLowerCompositeScore":false,"delta":0,"pickLeadsOnDimensions":[],"explanation":"Anthropic (8.42) holds both the highest composite score among ranked candidates and the editorial pick for Coding agent / code generation: Capability and reliability dominate. PricePerf secondary for interactive coding; primary for bulk codegen."},"cheapest":{"providerId":"zai","providerName":"Z.AI (Zhipu GLM)","skuId":"zai-glm-4-6v-flashx-in","item":"GLM-4.6V-FlashX","plan":"GLM-4.6V-FlashX — Prices per 1M tokens","unit":"usd_per_million_input_tokens","amountUsd":0.04,"isFloorPrice":true,"floorWarning":"Provider-wide floor SKU; may not be the flagship model scored for this JTBD.","skuCountInUnit":18,"isDepotPick":false,"sourceUrl":"https://docs.z.ai/guides/overview/pricing","asOf":"2026-10-03","verifiedAsOf":"2026-10-27"},"recommendedWorkloadQuote":{"providerId":"anthropic","providerName":"Anthropic","skuId":"anthropic-sonnet-55-input","item":"Sonnet 5.5","plan":"Sonnet 5.5 — standard input; cache read/write on the same card were not folded in","unit":"usd_per_million_input_tokens","amountUsd":2,"outputSkuId":"anthropic-sonnet-55-output","outputItem":"Sonnet 5.5","outputAmountUsd":10,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","pricingLastVerifiedAt":"2026-10-27","isFlagshipForJob":true,"differsFromFloorCheapest":true,"representativeQuote":{"skuId":"anthropic-sonnet-55-input","item":"Sonnet 5.5","plan":"Sonnet 5.5 — standard input; cache read/write on the same card were not folded in","amountUsd":2,"inputOrUnitUsd":2,"unit":"usd_per_million_input_tokens","outputUsd":10,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":18,"totalUsd":20.7,"estimatedTotalUsd":20.7,"perTaskUsd":0.0207,"estimatedCostPerTaskUsd":0.0207,"formula":"((4,000 in * $2/1M + 1,000 out * $10/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."}},"representativeQuote":{"skuId":"anthropic-sonnet-55-input","item":"Sonnet 5.5","plan":"Sonnet 5.5 — standard input; cache read/write on the same card were not folded in","amountUsd":2,"inputOrUnitUsd":2,"unit":"usd_per_million_input_tokens","outputUsd":10,"outputUnit":"usd_per_million_output_tokens","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27"},"estimatedTaskCost":{"tasks":1000,"retryAndToolOverheadMultiplier":1.15,"retryToolOverheadMultiplier":1.15,"inputTokensPerTask":4000,"outputTokensPerTask":1000,"baseCostPer1kTasksUsd":18,"totalUsd":20.7,"estimatedTotalUsd":20.7,"perTaskUsd":0.0207,"estimatedCostPerTaskUsd":0.0207,"formula":"((4,000 in * $2/1M + 1,000 out * $10/1M) * 1,000 tasks) * 1.15 overhead","assumptions":"1,000 agent tasks @ 4k input + 1k output tokens/task with 1.15x retry/tool-call overhead."},"freeAlternatives":[{"id":"gemini-api-free-tier-standard","name":"Gemini API free tier, standard token price","kind":"free_inference","providerId":"google-ai","jtbdIds":["cheap-volume-llm","coding-agent","frontier-chat"],"whatYouGet":"Standard input and output marked Free of charge for models whose free-tier cell says that. Includes gemini-3.8-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, and gemini-2.5-flash-lite.","cost":"free_tier_unspecified","sourceUrl":"https://ai.google.dev/gemini-api/docs/pricing","notes":"Pricing page fetched twice 2026-10-24 (identical text; page footer 'Last updated 2026-10-22 UTC'): the Free tier card lists 'Limited access to certain models' and 'Free input & output tokens'; each listed model's Standard Free Tier input and output cells read 'Free of charge'. gemini-3.7-flash and gemini-3.5-flash, listed in this row before 0.12.96, no longer appear on the page, so they were removed rather than kept unsourced. 'Gemini 4 Argon is not available on the Free tier.' and gemini-3.1-pro-preview standard free-tier cells read 'Not available'. Batch free-tier cells read 'Not available' for several of these models (gemini-3.8-flash, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash). Image-generation free-tier cells fetched were Not available. The Free tier card says 'Content used to improve our products'. https://ai.google.dev/gemini-api/docs/rate-limits (fetched twice 2026-10-24, identical text, 'Last updated 2026-10-15 UTC') publishes no free-tier RPM, TPM or RPD and says 'View your active rate limits in AI Studio', so limits stay null. Not a $0 price-sort row. The page describes gemini-3.8-flash as 'engineered for long-horizon software engineering' and gemini-2.5-pro as 'A Pro model which excels at coding and complex reasoning tasks.' Re-checked 2026-10-26 (v0.12.131): stored quotes still match. https://ai.google.dev/gemini-api/docs/pricing and https://ai.google.dev/gemini-api/docs/rate-limits were each fetched twice (~10 s apart, plain curl, no login, following redirects): HTTP 200, no redirect, HTML differs only inside inline scripts, tag-stripped text identical; both footers now read 'Last updated 2026-10-26 UTC'. Every quote above string-matched the whitespace-normalized text except the older footer stamps, which are fetch-date stamps, not row values; the eight listed models' Standard free-tier input cells still read 'Free of charge', and gemini-3.7-flash and gemini-3.5-flash are still absent; values unchanged (Depot data decision to re-date only, approvalRef 'Ethan delegation 2026-10-21 19:41 ET t55u', decidedBy Agent Depo).","limits":null,"license":null,"asOf":"2026-10-26","freeType":"free_inference","substitutable":true},{"id":"humaneval","name":"HumanEval","kind":"free_data","jtbdIds":["evals","coding-agent"],"whatYouGet":"Public OpenAI HumanEval code-generation dataset.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/datasets/openai/openai_humaneval/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: mit. openai/human-eval GitHub LICENSE fetched the same day is also MIT. Dataset card re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license:' / '- mit'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"multi-swe-bench","name":"Multi-SWE-bench","kind":"free_data","jtbdIds":["evals","coding-agent"],"whatYouGet":"Public multi-language SWE-bench style issue-resolution benchmark.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/multi-swe-bench/multi-swe-bench/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder-7B-Instruct","kind":"open_weights","jtbdIds":["coding-agent","open-model-inference"],"whatYouGet":"Downloadable Qwen2.5-Coder 7B Instruct weights. This checkpoint only.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/raw/main/LICENSE","notes":"LICENSE file fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"open_weights","substitutable":true},{"id":"swe-bench","name":"SWE-bench","kind":"free_data","jtbdIds":["oss-evals","coding-agent"],"whatYouGet":"Public software-engineering benchmark instances. Download from the GitHub repo or the Hugging Face dataset princeton-nlp/SWE-bench.","cost":"oss","license":"MIT","sourceUrl":"https://github.com/SWE-bench/SWE-bench/blob/main/LICENSE","notes":"Dataset card: https://huggingface.co/datasets/princeton-nlp/SWE-bench. Instance text can include upstream repository code under other licenses. Re-fetched twice 2026-10-25: https://github.com/princeton-nlp/SWE-bench/blob/main/LICENSE now answers HTTP 301 to https://github.com/SWE-bench/SWE-bench/blob/main/LICENSE (HTTP 200; the GitHub blob page changes between fetches, page chrome), so sourceUrl moved to the redirect target; the raw file https://raw.githubusercontent.com/SWE-bench/SWE-bench/main/LICENSE was also fetched twice (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) 2023 Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, Karthik R Narasimhan'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"swe-bench-verified","name":"SWE-bench Verified","kind":"free_data","jtbdIds":["evals","oss-evals","coding-agent"],"whatYouGet":"Public SWE-bench Verified subset. The dataset card fetched here does not state a license.","cost":"free","license":null,"sourceUrl":"https://huggingface.co/api/datasets/SWE-bench/SWE-bench_Verified","notes":"Hugging Face dataset API fetched 2026-10-03. cardData.license is null and gated is false. The existing swe-bench row is the MIT code license, not this subset card. License left null. Dataset API re-fetched twice 2026-10-25 (HTTP 200, byte-identical): cardData.license still null and gated false, so license stays null.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"terminal-bench","name":"Terminal-Bench","kind":"free_data","jtbdIds":["evals","oss-evals","coding-agent"],"whatYouGet":"Public terminal-bench tasks for agents that use a shell.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/laude-institute/terminal-bench/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true}],"referenceDocs":[{"id":"agent-skills-spec","name":"Agent Skills specification","kind":"free_docs","jtbdIds":["coding-agent","mcp-discovery"],"whatYouGet":"Public Agent Skills docs index, including the specification links.","cost":"free","license":null,"sourceUrl":"https://agentskills.io/llms.txt","notes":"llms.txt fetched 2026-10-03 lists the Agent Skills docs. No license line was in that file. The HTML specification page also returned 200. License left null. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical; the file still starts '# Agent Skills' and links [Specification](https://agentskills.io/specification.md), and still has no license line, so license stays null.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_docs","substitutable":false,"note":"Public API documentation or specification only; not free inference or execution."},{"id":"agents-md","name":"AGENTS.md","kind":"free_docs","jtbdIds":["coding-agent"],"whatYouGet":"AGENTS.md convention for telling coding agents how a repo works.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/agentsmd/agents.md/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is MIT, copyright 2025 OpenAI. https://agents.md/ returned 200 the same day. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, byte-identical: 'MIT License' / 'Copyright (c) 2025 OpenAI'. License unchanged. https://agents.md/ re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): HTTP 200, no redirect, byte-identical; page title 'AGENTS.md', text 'AGENTS.md is a simple, open format for guiding coding agents'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_docs","substitutable":false,"note":"Public API documentation or specification only; not free inference or execution."}],"falsification":{"jtbdId":"coding-agent","jtbdName":"Coding agent / code generation","currentPickId":"anthropic","currentPickScore":8.42,"challengerId":"openai","challengerScore":8.22,"currentScoreGap":0.2,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.35,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["OpenAI (openai) outperforms Anthropic (anthropic) by >= 0.35 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Anthropic's representative SKU for coding-agent without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=anthropic) 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":"openai","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.35,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"anthropic","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"anthropic","immediateOverrideUrl":"/api/decide?jtbd=coding-agent&exhausted=anthropic"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=coding-agent","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"coding-agent","providerId":"openai","outcome":"worked","detail":"Comparative production evaluation on coding-agent (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":["OpenAI (openai) outperforms Anthropic (anthropic) by >= 0.35 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Anthropic's representative SKU for coding-agent without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=anthropic) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"coding-agent","primary":{"providerId":"anthropic","name":"Anthropic","overall":8.42,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.42,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"primary","reason":"Editorial Depot Pick for Coding agent / code generation; healthy/eligible under caller constraints."},"fallback":[{"providerId":"openai","name":"OpenAI","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":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Coding agent / code generation."},{"providerId":"deepseek","name":"DeepSeek","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":"2026-10-03","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Coding agent / code generation."},{"providerId":"mistral","name":"Mistral AI","overall":8.05,"scoreBand":{"low":7.5,"mid":8.1,"high":8.7,"halfWidth":0.6,"basis":"editorial_prior","display":"7.5–8.7 (editorial prior)"},"scoreLayers":{"editorialPrior":8.05,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Coding agent / code generation."},{"providerId":"zai","name":"Z.AI (Zhipu GLM)","overall":7.79,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.79,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Coding agent / code generation."},{"providerId":"minimax","name":"MiniMax","overall":7.83,"scoreBand":{"low":7.2,"mid":7.8,"high":8.4,"halfWidth":0.6,"basis":"editorial_prior","display":"7.2–8.4 (editorial prior)"},"scoreLayers":{"editorialPrior":7.83,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Coding agent / code generation."},{"providerId":"dashscope","name":"Alibaba Cloud Model Studio (DashScope)","overall":7.86,"scoreBand":{"low":7.3,"mid":7.9,"high":8.5,"halfWidth":0.6,"basis":"editorial_prior","display":"7.3–8.5 (editorial prior)"},"scoreLayers":{"editorialPrior":7.86,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Coding agent / code generation."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"anthropic","activePrimaryId":"anthropic","summary":"0.00 score regret: unconstrained editorial pick satisfies all caller constraints."},"evidenceAgeDays":{"editorialScoreAgeDays":8,"pricingVerifiedAgeDays":0,"editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27"},"confidenceBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"coding-agent","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","tie":false,"scoreGap":0.2,"decidingFactor":null,"tieNote":null,"rationale":"Capability and reliability dominate. PricePerf secondary for interactive coding; primary for bulk codegen.","whenNotTopPick":"Compliance blocks Anthropic; or you need cheapest high-volume codegen (DeepSeek/open hosts) with human review.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","cite":"Depot Pick for coding-agent: anthropic (asOf 2026-10-19). See GET /api/jtbds/coding-agent + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/coding-agent?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=coding-agent","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/anthropic","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=coding-agent","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":"2026-10-19","depth":{"whenNotToUse":{"text":"Compliance blocks Anthropic; or you need cheapest high-volume codegen (DeepSeek/open hosts) with human review.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"openai","name":"OpenAI","overallForJob":8.22,"pickOverallForJob":8.42,"beatsPickOn":["latencyReliability","developerDx","maturity"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":6.5,"runnerUpLockInRisk":7.2,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":[],"pickNotes":[],"selfHostFallback":[{"id":"swe-bench","name":"SWE-bench","license":"MIT","sourceUrl":"https://github.com/SWE-bench/SWE-bench/blob/main/LICENSE"},{"id":"qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder-7B-Instruct","license":"Apache-2.0","sourceUrl":"https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct/raw/main/LICENSE"},{"id":"terminal-bench","name":"Terminal-Bench","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/laude-institute/terminal-bench/main/LICENSE"}],"migration":"The pick has lower stored lock-in risk than runner-up OpenAI (6.5 vs 7.2). Self-host fallback listed for this job: SWE-bench, Qwen2.5-Coder-7B-Instruct, Terminal-Bench.","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 (v0.12.148), Depot Pick for coding-agent: anthropic, scores as of 2026-10-19, retrieved 2026-10-27. https://getagentdepot.com/jtbds/coding-agent","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/coding-agent) (v0.12.148) — Depot Pick for `coding-agent`: **anthropic** (scores as of 2026-10-19, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.148","role":"depot_pick","jtbdId":"coding-agent","providerId":"anthropic","scoreAsOf":"2026-10-19","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/coding-agent","api":"https://getagentdepot.com/api/decide?jtbd=coding-agent"},"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":"2026-10-19","ageDays":8,"stale":false,"staleAfterDays":30,"reason":null},"lastReviewed":{"asOf":"2026-10-19","ageDays":8,"stale":false,"staleAfterDays":30,"reason":null},"sourceCheck":{"checkedAt":"2026-10-27","sourceUrls":2,"sourcesReachable":2,"pricingRows":14,"pricingRowsReconfirmed":14,"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":"2026-10-19","editorialPriorAsOf":"2026-10-19","pricingLastVerifiedAt":"2026-10-27","pickLastReviewed":"2026-10-19","runnersUpScoreAsOf":["2026-09-14","2026-09-14","2026-09-14","2026-09-14","2026-09-14","2026-09-14"],"contractAsOf":"2026-10-03","pricingShape":"sourced_rows","normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate"},"pricingContract":{"normalizedUsdPerMillionTokens":null,"normalizationStatus":"ambiguous","normalizationReason":"input_output_split_not_a_single_rate","shape":"sourced_rows","filterable":false,"priceSortEligible":true,"priceSortKeyUsdPerMillionInputTokens":0.1,"rows":[{"id":"anthropic-fable-51-input","providerId":"anthropic","sku":"Fable 5.1","unit":"usd_per_million_input_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-fable-51-output","providerId":"anthropic","sku":"Fable 5.1","unit":"usd_per_million_output_tokens","amountUsd":50,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":50,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-opus-55-input","providerId":"anthropic","sku":"Opus 5.5","unit":"usd_per_million_input_tokens","amountUsd":4,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":4,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-opus-55-output","providerId":"anthropic","sku":"Opus 5.5","unit":"usd_per_million_output_tokens","amountUsd":20,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":20,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-sonnet-55-input","providerId":"anthropic","sku":"Sonnet 5.5","unit":"usd_per_million_input_tokens","amountUsd":2,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in"},{"id":"anthropic-sonnet-55-output","providerId":"anthropic","sku":"Sonnet 5.5","unit":"usd_per_million_output_tokens","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":10,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output"},{"id":"anthropic-haiku-45-input","providerId":"anthropic","sku":"Haiku 4.5","unit":"usd_per_million_input_tokens","amountUsd":1,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"standard input; cache read/write on the same card were not folded in","lifecycle":"legacy","lifecycleSourceUrl":"https://platform.claude.com/docs/en/about-claude/models/overview","lifecycleAsOf":"2026-10-21"},{"id":"anthropic-haiku-45-output","providerId":"anthropic","sku":"Haiku 4.5","unit":"usd_per_million_output_tokens","amountUsd":5,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":5,"normalizationReason":"output_token_price_not_a_single_blended_rate","priceSortEligible":false,"qualifier":"standard output","lifecycle":"legacy","lifecycleSourceUrl":"https://platform.claude.com/docs/en/about-claude/models/overview","lifecycleAsOf":"2026-10-21"},{"id":"anthropic-web-search","providerId":"anthropic","sku":"Web search","unit":"usd_per_1k_searches","amountUsd":10,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_1k_searches","priceSortEligible":false,"qualifier":"page says does not include input and output tokens"},{"id":"anthropic-code-exec-hour","providerId":"anthropic","sku":"Code execution additional hours","unit":"usd_per_hour","amountUsd":0.05,"currency":"USD","sourceUrl":"https://claude.com/pricing","asOf":"2026-10-27","normalizationStatus":"unit_mismatch","normalizedUsdPerMillionTokens":null,"normalizationReason":"unit_mismatch_per_hour","priceSortEligible":false,"qualifier":"per hour per container"},{"id":"anthropic-haiku-55-input-le-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts up to 100K tokens)","unit":"usd_per_million_input_tokens","amountUsd":0.1,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.1,"normalizationReason":null,"priceSortEligible":true,"qualifier":"Base input, prompts up to 100,000 tokens (docs pricing table). Cache write 5m $0.125, cache hit $0.01 not folded in. The claude.com/pricing card agrees as of 2026-10-27 (the 2026-10-21 card/docs mismatch is resolved)."},{"id":"anthropic-haiku-55-output-le-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts up to 100K tokens)","unit":"usd_per_million_output_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output, prompts up to 100,000 tokens (docs pricing table)."},{"id":"anthropic-haiku-55-input-gt-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts over 100K tokens)","unit":"usd_per_million_input_tokens","amountUsd":0.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":0.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Base input, prompts over 100,000 tokens (whole request priced at this rate, including cache reads/writes in the count). Cache write 5m $0.625, cache hit $0.05 not folded in."},{"id":"anthropic-haiku-55-output-gt-100k","providerId":"anthropic","sku":"Haiku 5.5 (prompts over 100K tokens)","unit":"usd_per_million_output_tokens","amountUsd":2.5,"currency":"USD","sourceUrl":"https://platform.claude.com/docs/en/about-claude/pricing","asOf":"2026-10-27","normalizationStatus":"sourced_token_price","normalizedUsdPerMillionTokens":2.5,"normalizationReason":null,"priceSortEligible":false,"qualifier":"Output, prompts over 100,000 tokens."}],"notesExcerpt":"Sonnet 5 ~$2/$10 per 1M; Opus ~$5/$25; Haiku 4.5 ~$1/$5; Fable higher. Prompt caching + batch. Managed Agents session-hour fees. US-only inference ~1.1x.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://www.anthropic.com","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":"Partial coverage. Providers without a fetched SKU are omitted. See GET /api/pricing."},"links":{"jtbd":"/jtbds/coding-agent","jtbdApi":"/api/jtbds/coding-agent","leaderboard":"/api/leaderboards?jtbd=coding-agent","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=coding-agent","decide":"/api/decide?jtbd=coding-agent","humanPage":"/jtbds/coding-agent","alternatives":"/api/alternatives?provider=anthropic","canonical":"/api/canonical","quote":"/api/quote?jtbd=coding-agent","falsify":"/api/falsify?jtbd=coding-agent"},"constraintBundle":{"task":null,"jtbd":"coding-agent","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]},"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":1,"withVerifiedReceipt":0,"failureModes":{},"latestAt":"2026-09-10T12:00:00.000Z","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":1,"test":0,"notFeedback":0},"reason":"no_submitted_outcome_reports_yet"},"pick":{"providerId":"anthropic","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=coding-agent"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}