{"jtbd":{"id":"evals","slug":"evals","name":"Prompt/agent eval harness","shortName":"Prompt/agent eval harness","problemStatement":"Regression-test agent quality in CI before ship."},"pick":{"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":8.28,"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":8.28,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","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":8.28,"kind":"curated_estimate","confidence":"high","asOf":"2026-10-19"}},"runnersUp":[{"id":"langfuse","slug":"langfuse","name":"Langfuse","tagline":"Depot default observability for most agent teams: open, affordable, good enough to serious.","website":"https://langfuse.com","overall":8.65,"scoreBand":{"low":8.1,"mid":8.7,"high":9.3,"halfWidth":0.6,"basis":"editorial_prior","display":"8.1–9.3 (editorial prior)"},"scoreLayers":{"editorialPrior":8.65,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Open-source + cloud; generous self-host; cloud from ~$29–59/mo tiers; EU-friendly.","scores":{"capabilityFit":8.8,"pricePerformance":9.2,"latencyReliability":8.4,"developerDx":8.8,"privacyPosture":8.8,"lockInRisk":2.5,"maturity":8.2,"overall":8.65,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"langsmith","slug":"langsmith","name":"LangSmith","tagline":"If you live in LangGraph, LangSmith is the obvious observatory. Otherwise compare Langfuse/Helicone first.","website":"https://www.langchain.com/langsmith","overall":8.14,"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":8.14,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Seat + trace volume pricing; deep LangChain/LangGraph integration; Plus tiers from tens of $/mo.","scores":{"capabilityFit":9,"pricePerformance":7,"latencyReliability":8.8,"developerDx":9,"privacyPosture":7.8,"lockInRisk":6.5,"maturity":8.8,"overall":8.14,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"arize-phoenix","slug":"arize-phoenix","name":"Arize Phoenix","tagline":"Choose Phoenix when you want open-source observability you can own. Cloud Arize when enterprise wants a…","website":"https://phoenix.arize.com","overall":8.37,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.37,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"Open-source Phoenix free to self-host; Arize AX cloud paid; OpenTelemetry-friendly.","scores":{"capabilityFit":8.6,"pricePerformance":9,"latencyReliability":8.2,"developerDx":8,"privacyPosture":8.5,"lockInRisk":2.5,"maturity":8.6,"overall":8.37,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"confident-ai","slug":"confident-ai","name":"Confident AI","tagline":"Best when your team already thinks in pytest/DeepEval. Braintrust remains Depot hosted-evals default…","website":"https://www.confident-ai.com","overall":8.06,"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":8.06,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (confident-ai.com/pricing): Free forever (2 seats, 1 project, 5 test runs/week, 1 GB-mo traces). Starter $200/mo (5 projects, 5 GB-mo then $1/GB-mo). Team $2,000/mo (unlimited projects, 75 GB-mo). Enterprise custom (on-prem, HIPAA, residency). Online eval tokens ~$0.05/$0.40 per 1M in/out.","scores":{"capabilityFit":8.6,"pricePerformance":7.8,"latencyReliability":8,"developerDx":9,"privacyPosture":7.8,"lockInRisk":4.5,"maturity":7.2,"overall":8.06,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"langwatch","slug":"langwatch","name":"LangWatch","tagline":"Strong when you need multi-turn/voice agent simulations with EU self-host. Langfuse default tracing…","website":"https://langwatch.ai","overall":8.11,"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":8.11,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (langwatch.ai/pricing): Developer free (50k events/mo, 14-day access, 2 users). Growth €29/core-seat/mo + 200k events then €5/100k; 30-day retention then €3/GB. Enterprise hybrid/self-host/on-prem + marketplace billing. Scenario SDK OSS (Python+TS); voice agent simulation supported.","scores":{"capabilityFit":8.4,"pricePerformance":8,"latencyReliability":8,"developerDx":8.6,"privacyPosture":8.5,"lockInRisk":3.5,"maturity":7.2,"overall":8.11,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"comet-opik","slug":"comet-opik","name":"Comet Opik","tagline":"Pick when you already live in Comet or want OSS Opik + optional cloud. Langfuse remains cheaper OSS default…","website":"https://www.comet.com/site/products/opik/","overall":8.02,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.02,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14: Opik OSS self-host free. Comet Cloud free tier + Pro Cloud ~$19/mo class with ~100k spans / 60-day retention (confirm live comet.com/site/pricing). Fits teams already on Comet ML experiment tracking.","scores":{"capabilityFit":8.2,"pricePerformance":8.5,"latencyReliability":8,"developerDx":8.4,"privacyPosture":7.8,"lockInRisk":4,"maturity":8,"overall":8.02,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"honeyhive","slug":"honeyhive","name":"HoneyHive","tagline":"Use the free Developer tier to stand up agent evals/traces in a day; Enterprise when you need self-host…","website":"https://www.honeyhive.ai","overall":8.08,"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":8.08,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (honeyhive.ai/pricing): Developer free (no card) — 10k events/mo, 5 users, 1 workspace, 30-day retention, 1k RPM, evals + prompt versioning + CI. Enterprise custom (unlimited users/workspaces, SAML, custom retention, SLA, DPA/BAA, multi-tenant / single-tenant / hybrid / self-host). Data residency default AWS us-west-2. SOC2 Type II / GDPR / HIPAA. Startup discount < $5M raised.","scores":{"capabilityFit":8.4,"pricePerformance":7.8,"latencyReliability":8,"developerDx":8.6,"privacyPosture":8.8,"lockInRisk":4.2,"maturity":7.4,"overall":8.08,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}},{"id":"logfire","slug":"logfire","name":"Pydantic Logfire","tagline":"Best when the agent is already PydanticAI/Python and you want app+LLM traces together. Langfuse stays Depot…","website":"https://pydantic.dev/logfire","overall":8.37,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.37,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","pricingNotes":"As of 2026-09-14 (pydantic.dev/pricing): Personal free — 10M records/mo hard-capped, 1 seat, 3 projects, 30d. Team $49/mo (5 seats, $25 extra, 10M then $2/M, spend cap). Growth $249/mo unlimited seats/projects, up to 90d, BAA boilerplate. Enterprise cloud/dedicated/self-host. $0/1000 eval scores on Team+. AI Gateway BYOK (0% markup) / built-in 5% (3% on Growth).","scores":{"capabilityFit":8.4,"pricePerformance":8.6,"latencyReliability":8.2,"developerDx":9.2,"privacyPosture":8.4,"lockInRisk":3.8,"maturity":8,"overall":8.37,"kind":"curated_estimate","confidence":"high","asOf":"2026-09-14"}}],"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":8.28,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"whyPickOverHigherScore":{"pickId":"braintrust","pickName":"Braintrust","pickScore":8.28,"highestScoredCandidateId":"langfuse","highestScoredCandidateName":"Langfuse","highestScore":8.65,"pickHasLowerCompositeScore":true,"delta":-0.37,"pickLeadsOnDimensions":["capabilityFit (9.2 vs 8.8)","latencyReliability (8.6 vs 8.4)"],"explanation":"Braintrust (8.28) is the editorial pick for Prompt/agent eval harness over higher-composite Langfuse (8.65) because composite scores are provider-wide priors while Braintrust wins on capabilityFit (9.2 vs 8.8), latencyReliability (8.6 vs 8.4): capability eval workflows + dx."},"cheapest":null,"recommendedWorkloadQuote":null,"representativeQuote":null,"estimatedTaskCost":null,"freeAlternatives":[{"id":"agentbench","name":"AgentBench","kind":"free_data","jtbdIds":["evals","oss-evals"],"whatYouGet":"Public AgentBench multi-environment agent evaluation repository.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/THUDM/AgentBench/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical), no redirect from the THUDM path: 'Apache License Version 2.0, January 2004'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"bfcl","name":"Berkeley Function Calling Leaderboard","kind":"free_data","jtbdIds":["evals","oss-evals","agent-tools"],"whatYouGet":"Public function-calling eval dataset used by the Berkeley leaderboard.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://huggingface.co/datasets/gorilla-llm/Berkeley-Function-Calling-Leaderboard/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: apache-2.0. The gorilla GitHub LICENSE fetched the same day is also Apache-2.0. Dataset card re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: apache-2.0'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"browsergym","name":"BrowserGym","kind":"free_data","jtbdIds":["evals","web-agent","self-host-browser"],"whatYouGet":"Public BrowserGym environment for web agents.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/ServiceNow/BrowserGym/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0, copyright 2024 ServiceNow. README fetched 2026-10-19 says it is a framework to implement, test, and evaluate web agents on BrowserGym benchmarks. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Copyright 2024 ServiceNow' / 'Licensed under the Apache License, Version 2.0'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"gaia","name":"GAIA","kind":"free_data","jtbdIds":["evals","oss-evals","deep-research-agents"],"whatYouGet":"Gated public benchmark of tool-using assistant questions. Files require accepting a no-reshare condition. No license field was on the fetched card.","cost":"free","license":null,"sourceUrl":"https://huggingface.co/datasets/gaia-benchmark/GAIA/resolve/main/README.md","notes":"README fetched 2026-10-03. extra_gated_prompt says not to reshare outside a gated or private HF repo. No license key in the fetched card. Anonymous file download returned 401 earlier on the raw README path before this resolve URL. README re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter still has extra_gated_prompt 'To avoid contamination and data leakage, you agree to not reshare this dataset outside of a gated or private repository on the HF hub.' and still no license key, so license stays null.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"gsm8k","name":"GSM8K","kind":"free_data","jtbdIds":["evals"],"whatYouGet":"Public GSM8K grade-school math word problems.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/datasets/openai/gsm8k/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: mit. openai/grade-school-math GitHub LICENSE fetched the same day is also MIT. Dataset card fetched 2026-10-19 says it has been used for many benchmarks, including the Open LLM Leaderboard. 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":"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":"inspect-ai","name":"Inspect AI","kind":"dev_tool","jtbdIds":["oss-evals","evals"],"whatYouGet":"UK AISI eval framework. Model provider calls are billed by those providers.","cost":"oss","license":"MIT","sourceUrl":"https://github.com/UKGovernmentBEIS/inspect_ai/blob/main/LICENSE","notes":"Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): GitHub blob page HTTP 200, no redirect (page chrome differs between fetches); raw LICENSE fetched twice too, HTTP 200, byte-identical: 'MIT License' / 'Copyright (c) 2024 UK AI Security Institute'. License unchanged.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"dev_tool","substitutable":true},{"id":"mind2web","name":"Mind2Web","kind":"free_data","jtbdIds":["evals","web-agent","form-filling-rpa"],"whatYouGet":"Public Mind2Web web-agent demonstration dataset.","cost":"oss","license":"CC-BY-4.0","sourceUrl":"https://huggingface.co/datasets/osunlp/Mind2Web/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: cc-by-4.0. A GitHub LICENSE path returned 404. Dataset card fetched 2026-10-19 says Mind2Web is a dataset for developing and evaluating generalist agents for the web. Dataset card re-fetched twice 2026-10-25 (HTTP 200, byte-identical): front matter 'license: cc-by-4.0'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"mmlu","name":"MMLU","kind":"free_data","jtbdIds":["evals","oss-evals"],"whatYouGet":"Public cais/mmlu multiple-choice eval dataset.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/datasets/cais/mmlu/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: mit. The hendrycks/test 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":"mmlu-pro","name":"MMLU-Pro","kind":"free_data","jtbdIds":["evals","oss-evals"],"whatYouGet":"Public MMLU-Pro eval dataset, a harder multiple-choice successor set.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: mit. The TIGER-AI-Lab/MMLU-Pro GitHub LICENSE fetched the same day is Apache-2.0 for the code repo; this row follows the dataset card, not the code license. 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":"openai-mrcr","name":"OpenAI MRCR","kind":"free_data","jtbdIds":["evals","long-context-agents"],"whatYouGet":"Public OpenAI MRCR long-context multi-needle benchmark dataset.","cost":"oss","license":"MIT","sourceUrl":"https://huggingface.co/datasets/openai/mrcr/raw/main/README.md","notes":"Dataset card fetched 2026-10-03 says license: 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":"osworld","name":"OSWorld","kind":"free_data","jtbdIds":["evals","desktop-computer-use"],"whatYouGet":"Public OSWorld desktop computer-use benchmark.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/xlang-ai/OSWorld/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":"promptfoo","name":"Promptfoo","kind":"dev_tool","providerId":"promptfoo","jtbdIds":["oss-evals","evals","adversarial-red-team-evals","continuous-eval-ci"],"whatYouGet":"Local eval CLI and library. No hosted quota is included.","cost":"oss","license":"MIT","sourceUrl":"https://github.com/promptfoo/promptfoo/blob/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is MIT. Copyright line says Promptfoo 2025. README fetched 2026-10-03 says to automate checks in CI/CD. It does not say the check blocks a merge, and it does not name GitHub or GitLab. README fetched 2026-10-19 says promptfoo is a CLI and library for evaluating and red-teaming LLM-based apps, with red teaming and vulnerability scanning. Re-fetched twice 2026-10-25 (~10 s apart, plain curl, no login): GitHub blob page HTTP 200, no redirect (page chrome differs between fetches); raw LICENSE fetched twice too, HTTP 200, byte-identical: 'Copyright (c) Promptfoo 2025' / 'Permission is hereby granted, free of charge'. The file is the MIT permission text without an 'MIT License' heading. License unchanged.","limits":null,"asOf":"2026-10-25","freeType":"dev_tool","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":"tau-bench","name":"τ-bench","kind":"free_data","jtbdIds":["evals","oss-evals","agent-tools"],"whatYouGet":"Public tau-bench agent tool-use benchmark repository.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/sierra-research/tau-bench/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is MIT, copyright 2024 Sierra. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) 2024 Sierra'.","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},{"id":"the-agent-company","name":"TheAgentCompany","kind":"free_data","jtbdIds":["evals","oss-evals"],"whatYouGet":"Public TheAgentCompany simulated-workplace agent benchmark.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is MIT, copyright 2024 TheAgentCompany. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'MIT License' / 'Copyright (c) 2024 TheAgentCompany'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"visualwebarena","name":"VisualWebArena","kind":"free_data","jtbdIds":["evals","web-agent","multimodal"],"whatYouGet":"Public VisualWebArena benchmark, a multimodal successor to WebArena.","cost":"oss","license":"MIT","sourceUrl":"https://raw.githubusercontent.com/web-arena-x/visualwebarena/main/LICENSE","notes":"LICENSE fetched 2026-10-03 begins with a free-of-charge permission grant (MIT). Copyright 2024 Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, and Po-Yu Huang. LICENSE re-fetched twice 2026-10-25 (HTTP 200, byte-identical): 'Copyright (c) 2024 Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Chong Lim, and Po-Yu Huang' / 'Permission is hereby granted, free of charge'.","providerId":null,"limits":null,"asOf":"2026-10-25","freeType":"free_data","substitutable":true},{"id":"webarena","name":"WebArena","kind":"free_data","jtbdIds":["evals","web-agent","browser-agent-loop"],"whatYouGet":"Public WebArena web-agent benchmark code and task definitions.","cost":"oss","license":"Apache-2.0","sourceUrl":"https://raw.githubusercontent.com/web-arena-x/webarena/main/LICENSE","notes":"LICENSE fetched 2026-10-03 is Apache License 2.0. Self-hosted websites in the benchmark are a separate setup, not priced here. 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":[],"falsification":{"jtbdId":"evals","jtbdName":"Prompt/agent eval harness","currentPickId":"braintrust","currentPickScore":8.28,"challengerId":"langfuse","challengerScore":8.65,"currentScoreGap":0.37,"minVerifiedOutcomes":10,"requiredOutcomeMargin":0.52,"requiredSuccessRateDelta":0.15,"maxPickPriceIncreasePct":25,"whatWouldChangePick":["Langfuse (langfuse) outperforms Braintrust (braintrust) by >= 0.52 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Braintrust's representative SKU for evals without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=braintrust) 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":"langfuse","minVerifiedOutcomes":10,"requiredOutcomeMargin":0.52,"requiredWorkedRateDelta":0.15},{"kind":"verified_price_increase","providerId":"braintrust","maxPriceIncreasePct":25},{"kind":"live_rail_exhaustion_or_degradation","providerId":"braintrust","immediateOverrideUrl":"/api/decide?jtbd=evals&exhausted=braintrust"}],"submissionSpec":{"falsifyEndpoint":"/api/falsify?jtbd=evals","outcomesEndpoint":"POST /api/feedback","correctionsEndpoint":"POST /api/corrections","payloadTemplate":{"agentIdentity":"agent:<your-agent-id>","jtbdId":"evals","providerId":"langfuse","outcome":"worked","detail":"Comparative production evaluation on evals (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":["Langfuse (langfuse) outperforms Braintrust (braintrust) by >= 0.52 outcome points (or >= 15% worked-rate delta) across >= 10 Countersign-verified production outcomes.","A verified price increase > 25% on Braintrust's representative SKU for evals without a corresponding capability gain.","Live caller rail exhaustion (?exhausted=braintrust) or sustained >= 30% degraded/failed rate in verified production outcomes."],"routePlan":{"jtbdId":"evals","primary":{"providerId":"braintrust","name":"Braintrust","overall":8.28,"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":8.28,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","role":"primary","reason":"Editorial Depot Pick for Prompt/agent eval harness; healthy/eligible under caller constraints."},"fallback":[{"providerId":"langfuse","name":"Langfuse","overall":8.65,"scoreBand":{"low":8.1,"mid":8.7,"high":9.3,"halfWidth":0.6,"basis":"editorial_prior","display":"8.1–9.3 (editorial prior)"},"scoreLayers":{"editorialPrior":8.65,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"langsmith","name":"LangSmith","overall":8.14,"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":8.14,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"arize-phoenix","name":"Arize Phoenix","overall":8.37,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.37,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"confident-ai","name":"Confident AI","overall":8.06,"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":8.06,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"langwatch","name":"LangWatch","overall":8.11,"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":8.11,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"comet-opik","name":"Comet Opik","overall":8.02,"scoreBand":{"low":7.4,"mid":8,"high":8.6,"halfWidth":0.6,"basis":"editorial_prior","display":"7.4–8.6 (editorial prior)"},"scoreLayers":{"editorialPrior":8.02,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"honeyhive","name":"HoneyHive","overall":8.08,"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":8.08,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."},{"providerId":"logfire","name":"Pydantic Logfire","overall":8.37,"scoreBand":{"low":7.8,"mid":8.4,"high":9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.8–9.0 (editorial prior)"},"scoreLayers":{"editorialPrior":8.37,"measuredBenchmark":null,"verifiedOutcomeScore":null,"verifiedOutcomeCount":0,"accountRuntimeState":"unprobed"},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-09-14","role":"fallback","reason":"Ranked fallback route for Prompt/agent eval harness."}],"disqualified":[],"expectedRegret":{"scoreDeltaVsUnconstrainedPick":0,"unconstrainedPickId":"braintrust","activePrimaryId":"braintrust","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":7.7,"mid":8.3,"high":8.9,"halfWidth":0.6,"basis":"editorial_prior","display":"7.7–8.9 (editorial prior)"},"constraintsApplied":false,"constraintBundle":{"task":null,"jtbd":"evals","quotaExhausted":[],"degraded":[],"healthy":[],"budgetUsd":null,"maxLatencyMs":null,"region":null,"privacy":null,"exit":[],"existing":[]}},"pricingLastVerifiedAt":"2026-10-27","editorialPriorAsOf":"2026-10-19","tie":false,"scoreGap":-0.37,"decidingFactor":null,"tieNote":null,"rationale":"capability eval workflows + dx.","whenNotTopPick":"Budget OSS-only — Langfuse/Phoenix. Already standardized on LangSmith datasets. Humanloop is sunset (Anthropic acquihire) — do not pick.","skipTopPick":false,"skipReason":null,"matchedConstraints":[],"pricingSummary":"Eval-first platform; data-based pricing with unlimited seats on many plans; strong CI eval story.","cite":"Depot Pick for evals: braintrust (asOf 2026-10-19). See GET /api/jtbds/evals + GET /api/methodology.","nextActions":[{"step":1,"title":"Inspect full JTBD + embeds","href":"/api/jtbds/evals?embed=providers","why":"Confirm pick, runners-up, and methodology notes."},{"step":2,"title":"Quote sourced SKUs","href":"/api/quote?jtbd=evals","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/braintrust","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=evals","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":"Budget OSS-only — Langfuse/Phoenix. Already standardized on LangSmith datasets. Humanloop is sunset (Anthropic acquihire) — do not pick.","source":"editorial `whenNotTopPick` (data/jtbds.json)"},"whenNotToUseReason":null,"runnerUp":{"providerId":"langfuse","name":"Langfuse","overallForJob":8.65,"pickOverallForJob":8.28,"beatsPickOn":["pricePerformance","privacyPosture","lockInRisk"],"source":"first resolvable entry of the job's editorially ranked `runnersUpIds`; scores are stored job-weighted scores"},"runnerUpReason":null,"lockIn":{"pickLockInRisk":5,"runnerUpLockInRisk":2.5,"scale":"0–10 stored curated estimate; higher = more lock-in (worse)","pickExitSignals":[],"runnerUpExitSignals":["open source (provider tag `oss`)"],"pickNotes":[],"selfHostFallback":[{"id":"promptfoo","name":"Promptfoo","license":"MIT","sourceUrl":"https://github.com/promptfoo/promptfoo/blob/main/LICENSE"},{"id":"inspect-ai","name":"Inspect AI","license":"MIT","sourceUrl":"https://github.com/UKGovernmentBEIS/inspect_ai/blob/main/LICENSE"},{"id":"mmlu","name":"MMLU","license":"MIT","sourceUrl":"https://huggingface.co/datasets/cais/mmlu/raw/main/README.md"}],"migration":"Runner-up Langfuse has lower stored lock-in risk (2.5 vs 5, 0–10, higher = more lock-in). Self-host fallback listed for this job: Promptfoo, Inspect AI, MMLU.","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 (v0.12.152), Depot Pick for evals: braintrust, scores as of 2026-10-19, retrieved 2026-10-27. https://getagentdepot.com/jtbds/evals","markdown":"[Agent Provider Depot](https://getagentdepot.com/jtbds/evals) (v0.12.152) — Depot Pick for `evals`: **braintrust** (scores as of 2026-10-19, retrieved 2026-10-27)","fields":{"publisher":"Agent Provider Depot","version":"0.12.152","role":"depot_pick","jtbdId":"evals","providerId":"braintrust","scoreAsOf":"2026-10-19","retrievedOn":"2026-10-27","page":"https://getagentdepot.com/jtbds/evals","api":"https://getagentdepot.com/api/decide?jtbd=evals"},"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":1,"sourcesReachable":1,"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":"2026-10-19","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","2026-09-14","2026-09-14"],"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":"Eval-first platform; data-based pricing with unlimited seats on many plans; strong CI eval story.","notesCheck":{"status":"no_known_contradiction","pairs":[],"review":null,"note":null},"lastReviewed":"2026-10-19","scoreAsOf":"2026-10-19","website":"https://www.braintrust.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/evals","jtbdApi":"/api/jtbds/evals","leaderboard":"/api/leaderboards?jtbd=evals","methodology":"/api/methodology","badge":"/api/badge?type=depot-pick&jtbd=evals","decide":"/api/decide?jtbd=evals","humanPage":"/jtbds/evals","alternatives":"/api/alternatives?provider=braintrust","canonical":"/api/canonical","quote":"/api/quote?jtbd=evals","falsify":"/api/falsify?jtbd=evals"},"constraintBundle":{"task":null,"jtbd":"evals","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":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":"braintrust","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=evals"},"report":"POST /api/feedback {agentIdentity, outcome: failed|degraded|worked, detail, providerId, jtbdId, failureModeId?, receipt?}"}}