Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.
A dataset holds tasks your organization publishes to Valkyrie, with no benchmark service to run.
Each push makes an immutable version.
Lay out the task folders
Put each task in its own folder, named by its task ID, under one parent folder.
A task folder holds task.toml, instruction.md, and tests/test.sh. It can also hold
environment/ and solution/.
A metric.py in the parent folder computes the dataset’s score from the task rewards.
A dataset.toml in the parent folder pins the exact tasks and their digests, and its version
becomes a tag.
Read secrets in task environments
In task.toml, use a whole-value ${NAME} to read a secret available to the run.
For JSON secrets, this reads the field named NAME.
Use ${SECRET#FIELD} to select a different JSON field, or
${SECRET#FIELD:-fallback} to use a default when the secret or field is unavailable.
These references work in agent, verifier, verifier sandbox, and solution environment
values, including step verifiers. A field reference requires a JSON object secret.
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Valkyrie","description":"Run scalable, reproducible evaluations for AI agents.","colors":{"primary":"#386B46","light":"#6FD09F","dark":"#488959"},"logo":{"light":"https://mintcdn.com/valkyrie-vals/tCK_p9H_q6ml7cFr/images/valkyrie-logo-light.png?fit=max\u0026auto=format\u0026n=tCK_p9H_q6ml7cFr\u0026q=85\u0026s=defbf7b76eebf8e90b1beede16a4f7a3","dark":"https://mintcdn.com/valkyrie-vals/tCK_p9H_q6ml7cFr/images/valkyrie-logo-dark.png?fit=max\u0026auto=format\u0026n=tCK_p9H_q6ml7cFr\u0026q=85\u0026s=becaf91c5603e90328e67792fdd01b21","href":"https://www.vals.ai"},"favicon":{"light":"https://mintcdn.com/valkyrie-vals/GoPJBu1n3ZBfKc19/images/vals-icon-light.svg?fit=max\u0026auto=format\u0026n=GoPJBu1n3ZBfKc19\u0026q=85\u0026s=4db5ac875225c809eef2c0052e8f345b","dark":"https://mintcdn.com/valkyrie-vals/GoPJBu1n3ZBfKc19/images/vals-icon-dark.svg?fit=max\u0026auto=format\u0026n=GoPJBu1n3ZBfKc19\u0026q=85\u0026s=5319ff142c46a52e4f36531e260707c9"},"appearance":{"default":"system"},"background":{"color":{"light":"#F3F2F2","dark":"#171717"}},"navbar":{"links":[{"href":"https://github.com/vals-ai/Valkyrie","type":"github"}],"primary":{"type":"button","label":"vals.ai","href":"https://www.vals.ai"}},"footer":{"socials":{"website":"https://www.vals.ai","github":"https://github.com/vals-ai/Valkyrie"}},"fonts":{"family":"Söhne","source":"https://www.vals.ai/fonts/Soehne/soehne-buch.woff2","format":"woff2"},"icons":{"library":"lucide"},"banner":{"content":"Benchmark services are legacy. The recommended way to run your own benchmark through Valkyrie is to publish its tasks as a [dataset](/benchmarks/datasets).","type":"warning"},"contextual":{"options":["copy","view","chatgpt","claude","cursor","vscode"],"display":"header"},"styling":{"latex":false},"navigation":{"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"valkyrie-vals","hasAudioNarration":false,"actualSubdomain":"valkyrie-vals","customDomains":["docs.valkyrie.vals.ai"],"gitSource":{"type":"github","owner":"vals-ai","repo":"valkyrie-internal","deployBranch":"dev","contentDirectory":"docs","isPrivate":true,"mountPath":"","label":""},"entitlements":{},"buildId":"6af79ab8d8f22d3b7c20eb29","clientVersion":"0.0.4131","searchFilterCounts":[{"language":"default","tag":"Python SDK","count":39},{"language":"default","tag":"Python SDK reference","count":33},{"language":"default","tag":"CLI","count":29},{"language":"default","tag":"Types","count":15},{"language":"default","tag":"CLI reference","count":13},{"language":"default","tag":"Benchmark services","count":6},{"language":"default","tag":"Runs","count":5},{"language":"default","tag":"Get started","count":4},{"language":"default","tag":"Agents","count":3},{"language":"default","tag":"Integrations","count":2}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableContextualStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-rbac-roles","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[{"filePath":"style.css","content":"@font-face{font-family:\"Söhne\";src:url(\"https://www.vals.ai/fonts/Soehne/soehne-leicht.woff2\") format(\"woff2\");font-weight:300;font-style:normal;font-display:swap}@font-face{font-family:\"Söhne\";src:url(\"https://www.vals.ai/fonts/Soehne/soehne-buch.woff2\") format(\"woff2\");font-weight:400;font-style:normal;font-display:swap}@font-face{font-family:\"Söhne\";src:url(\"https://www.vals.ai/fonts/Soehne/soehne-kraftig.woff2\") format(\"woff2\");font-weight:500;font-style:normal;font-display:swap}@font-face{font-family:\"Söhne\";src:url(\"https://www.vals.ai/fonts/Soehne/soehne-halbfett.woff2\") format(\"woff2\");font-weight:600;font-style:normal;font-display:swap}@font-face{font-family:\"Söhne\";src:url(\"https://www.vals.ai/fonts/Soehne/soehne-dreiviertelfett.woff2\") format(\"woff2\");font-weight:700;font-style:normal;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-light.woff2\") format(\"woff2\");font-weight:300;font-style:normal;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-light-italic.woff2\") format(\"woff2\");font-weight:300;font-style:italic;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-regular.woff2\") format(\"woff2\");font-weight:400;font-style:normal;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-italic.woff2\") format(\"woff2\");font-weight:400;font-style:italic;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-medium.woff2\") format(\"woff2\");font-weight:500;font-style:normal;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-medium-italic.woff2\") format(\"woff2\");font-weight:500;font-style:italic;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-bold.woff2\") format(\"woff2\");font-weight:700;font-style:normal;font-display:swap}@font-face{font-family:\"Martina Plantijn\";src:url(\"https://www.vals.ai/fonts/MartinaPlantijn/martina-plantijn-bold-italic.woff2\") format(\"woff2\");font-weight:700;font-style:italic;font-display:swap}@font-face{font-family:\"Berkeley Mono\";src:url(\"https://www.vals.ai/fonts/BerkeleyMono/BerkeleyMono-Regular.woff2\") format(\"woff2\");font-weight:400;font-style:normal;font-display:swap}@font-face{font-family:\"Berkeley Mono\";src:url(\"https://www.vals.ai/fonts/BerkeleyMono/BerkeleyMono-Oblique.woff2\") format(\"woff2\");font-weight:400;font-style:italic;font-display:swap}@font-face{font-family:\"Berkeley Mono\";src:url(\"https://www.vals.ai/fonts/BerkeleyMono/BerkeleyMono-Bold.woff2\") format(\"woff2\");font-weight:700;font-style:normal;font-display:swap}@font-face{font-family:\"Berkeley Mono\";src:url(\"https://www.vals.ai/fonts/BerkeleyMono/BerkeleyMono-Bold-Oblique.woff2\") format(\"woff2\");font-weight:700;font-style:italic;font-display:swap}html,body,#navbar,#sidebar,#footer,#content-area{font-family:\"Söhne\", -apple-system, BlinkMacSystemFont, \"Segoe UI\", sans-serif}#page-title,h1,h2,h3,h4,h5,h6{font-family:\"Martina Plantijn\", Georgia, serif;font-weight:400;letter-spacing:-0.01em}#page-title,#content-area h1,.mdx-content h1{font-size:36px;line-height:40px}#content-area h2,.mdx-content h2{font-size:24px;line-height:32px}#content-area h3,.mdx-content h3{font-size:20px;line-height:32px;letter-spacing:normal}#content-area h4,#content-area h5,#content-area h6,.mdx-content h4,.mdx-content h5,.mdx-content h6{font-size:16px;line-height:24px}#content-area p,#content-area li,.mdx-content p,.mdx-content li{font-size:16px;line-height:24px}#header p{font-size:18px;line-height:28px}[data-component-part=\"card-title\"]{font-size:16px!important;line-height:24px!important}[data-component-part=\"card-content\"]{font-size:14px;line-height:20px}.callout,.callout [data-component-part=\"callout-content\"],[data-component-part=\"callout-content\"]{font-size:14px;line-height:20px}#navbar a,#topbar-cta-button,#topbar-cta-button a,navbar-link{font-size:16px!important;line-height:24px!important}#navbar a[href*=\"github.com\"],#navbar a[href*=\"github.com\"] span{font-size:14px!important;font-weight:400!important;line-height:20px!important}#navbar a[href*=\"github.com\"]{gap:6px}#navbar a[href*=\"github.com\"]>span:last-of-type{margin-inline-start:12px!important}#pagination,#pagination a,[data-component-part=\"pagination-prev\"],[data-component-part=\"pagination-next\"]{font-size:14px;line-height:20px}#sidebar,#sidebar-content,#sidebar-content a{font-size:14px;line-height:20px}#sidebar-content h3,sidebar-group-header{font-family:\"Söhne\", -apple-system, BlinkMacSystemFont, \"Segoe UI\", sans-serif;font-size:13px;line-height:16px;letter-spacing:0.13px;font-weight:500}#table-of-contents,toc-item{font-size:13px;line-height:16px}eyebrow,breadcrumb-item{font-size:13px;line-height:16px;letter-spacing:0.13px}code,kbd,samp,pre,pre code{font-family:\"Berkeley Mono\", ui-monospace, \"SFMono-Regular\", Menlo, monospace}pre,pre code,code-block{font-size:13px;line-height:20px}:root{--vals-ink: #191917;--vals-paper: #f3f2f2;--vals-border: #c7c4c1;--vals-border-subtle: rgb(62 59 56 / 0.15);--vals-radius: 4px;--rounded-xl: 4px;--rounded-2xl: 4px}#navbar,#sidebar,#content-area{color:var(--vals-ink)}#navbar{border-bottom:1px solid var(--vals-border)}#search-bar-entry,#search-bar-entry-mobile,#search-bar-entry *,#search-bar-entry-mobile *,#search-input,#topbar-cta-button,#topbar-cta-button *,#page-context-menu,#panel,#mobile-nav,#mobile-nav-content,#chat-assistant-sheet,#chat-assistant-textarea,tooltip,tile,step,steps,update,#sidebar-content a,#sidebar-content button,#sidebar-content li,toc-item[data-active],toc-item[data-active-deepest],[data-component-name=\"theme-toggle\"],[data-component-name=\"theme-preference-menu\"],[data-component-part=\"theme-preference-menu-trigger\"],[data-component-part=\"card-icon\"],[data-badge],.code-block,.code-block button,[data-component-part=\"code-block-root\"],[data-component-part=\"code-block-header\"],.code-block-fade-overlay,.code-block-copy-button,code-block,.code-group,.code-group [data-component-part=\"code-block-root\"],.code-group [data-component-part=\"scroll-area\"],.code-group [data-component-part=\"scroll-area-viewport\"],.code-group button,code-group,.card,card,card-group,columns,.callout,callout,accordion,accordion-group,tabs,expandable,frame,#pagination,#pagination a,[data-component-part=\"pagination-prev\"],[data-component-part=\"pagination-next\"],[role=\"menu\"],[role=\"menu\"] *,[role=\"menuitem\"],nav-dropdown-content,nav-dropdown-item,nav-dropdown-item-icon{border-radius:var(--vals-radius)!important}#content-area .code-group [data-component-part=\"code-block-root\"],#content-area .code-group [data-component-part=\"scroll-area-viewport\"]{border-radius:var(--vals-radius)!important}#page-context-menu-button{border-radius:var(--vals-radius) 0 0 var(--vals-radius)!important}#page-context-menu button:not(#page-context-menu-button){border-radius:0 var(--vals-radius) var(--vals-radius) 0!important}#search-bar-entry,#search-bar-entry-mobile,card,.card,callout,.callout,accordion,accordion-group,code-block,.code-block,code-group,.code-group,tabs,frame,expandable{border-color:var(--vals-border)!important;box-shadow:none!important}#search-bar-entry,#search-bar-entry-mobile{border:1px solid var(--vals-border)!important}#sidebar-content li[data-active]{background:rgb(72 137 89 / 0.1)!important}.dark #navbar,.dark #sidebar,.dark #content-area{color:#f3f2f2}.dark #navbar{border-bottom-color:rgb(255 255 255 / 0.14)}.dark #search-bar-entry,.dark #search-bar-entry-mobile,.dark card,.dark .card,.dark callout,.dark .callout,.dark accordion,.dark accordion-group,.dark code-block,.dark .code-block,.dark code-group,.dark .code-group,.dark tabs,.dark frame,.dark expandable{border-color:rgb(255 255 255 / 0.14)!important}.dark #sidebar-content li[data-active]{background:rgb(72 137 89 / 0.22)!important}:not(pre)>code{font-size:12px!important;line-height:16px!important;padding-block:2px!important;padding-inline:4px!important;background-color:#ffffff!important;border:1px solid var(--vals-border)!important;border-radius:var(--vals-radius)!important}.dark :not(pre)>code{background-color:#262626!important;border-color:rgb(255 255 255 / 0.14)!important}a:has(>code){border-bottom:none!important}a>code{color:#386b46!important}.dark a>code{color:#6fd09f!important}img.nav-logo{height:1.75rem!important;width:auto!important}#table-of-contents{max-height:calc(100vh - 8rem);overflow-y:auto;overscroll-behavior:contain}#table-of-contents-content,#table-of-contents-content ul,#table-of-contents-content li{display:flex;flex-direction:column;gap:2px}#table-of-contents-content{margin-top:12px}:is(h1,h2,h3,h4) code,.dark :is(h1,h2,h3,h4) code{font-size:inherit!important;line-height:inherit!important;padding:0!important;background-color:transparent!important;border:none!important}td>code:only-child{white-space:nowrap}@layer base{html:not(:has(.nav-tabs-item[data-active][href=\"/benchmarks/convert-a-benchmark\"])) #banner{display:none!important}}html:not(:has(.nav-tabs-item[data-active][href=\"/benchmarks/convert-a-benchmark\"])){--banner-height: 0px !important}"}],"page":{"pagePath":"benchmarks/datasets","slug":"/benchmarks/datasets","pageMetadata":{"title":"Publish a dataset","description":"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.","href":"/benchmarks/datasets"},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsx(_components.p, {\n children: \"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.\"\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx,jsxs:_jsxs}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){const _components={a:`a`,code:`code`,li:`li`,p:`p`,pre:`pre`,span:`span`,ul:`ul`,..._provideComponents(),...props.components},{CodeBlock,Heading,Note}=_components;if(!CodeBlock)_missingMdxReference(`CodeBlock`,true);if(!Heading)_missingMdxReference(`Heading`,true);if(!Note)_missingMdxReference(`Note`,true);return _jsxs(_Fragment,{children:[_jsx(_components.p,{children:`A dataset holds tasks your organization publishes to Valkyrie, with no benchmark service to run.\nEach push makes an immutable version.`}),`\n`,_jsx(Heading,{level:`2`,id:`lay-out-the-task-folders`,children:`Lay out the task folders`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`Put each task in its own folder, named by its task ID, under one parent folder.`}),`\n`,_jsxs(_components.li,{children:[`A task folder holds `,_jsx(_components.code,{children:`task.toml`}),`, `,_jsx(_components.code,{children:`instruction.md`}),`, and `,_jsx(_components.code,{children:`tests/test.sh`}),`. It can also hold\n`,_jsx(_components.code,{children:`environment/`}),` and `,_jsx(_components.code,{children:`solution/`}),`.`]}),`\n`,_jsxs(_components.li,{children:[`A `,_jsx(_components.code,{children:`metric.py`}),` in the parent folder computes the dataset’s score from the task rewards.`]}),`\n`,_jsxs(_components.li,{children:[`A `,_jsx(_components.code,{children:`dataset.toml`}),` in the parent folder pins the exact tasks and their digests, and its version\nbecomes a tag.`]}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`read-secrets-in-task-environments`,children:`Read secrets in task environments`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[`In `,_jsx(_components.code,{children:`task.toml`}),`, use a whole-value `,_jsx(_components.code,{children:\"${NAME}\"}),` to read a secret available to the run.\nFor JSON secrets, this reads the field named `,_jsx(_components.code,{children:`NAME`}),`.`]}),`\n`,_jsxs(_components.li,{children:[`Use `,_jsx(_components.code,{children:\"${SECRET#FIELD}\"}),` to select a different JSON field, or\n`,_jsx(_components.code,{children:\"${SECRET#FIELD:-fallback}\"}),` to use a default when the secret or field is unavailable.`]}),`\n`,_jsx(_components.li,{children:`These references work in agent, verifier, verifier sandbox, and solution environment\nvalues, including step verifiers. A field reference requires a JSON object secret.`}),`\n`]}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`2`,language:`toml`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`toml`,children:_jsxs(_components.code,{language:`toml`,numberOfLines:`2`,children:[_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`[`}),_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#D4D4D4`},children:`verifier`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`.`}),_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#D4D4D4`},children:`env`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:`]`})]}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#9CDCFE`},children:`API_KEY`}),_jsx(_components.span,{style:{color:`#1F2328`,\"--shiki-dark\":`#D4D4D4`},children:` = `}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:'\"${ClientConfig#API_KEY}\"'})]}),`\n`]})})}),`\n`,_jsx(Heading,{level:`2`,id:`push-a-folder`,children:`Push a folder`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`1`,language:`shellscript`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`shellscript`,children:_jsxs(_components.code,{language:`shellscript`,numberOfLines:`1`,children:[_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` push`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` ./tasks`}),_jsx(_components.span,{style:{color:`#0550AE`,\"--shiki-dark\":`#569CD6`},children:` --tag`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` v1`})]}),`\n`]})})}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:`The benchmark and the dataset are created when they don’t exist yet.`}),`\n`,_jsx(_components.li,{children:`Only tasks the dataset doesn’t store yet are uploaded. Pushing an unchanged folder makes no\nnew version.`}),`\n`,_jsxs(_components.li,{children:[`Every version gets the `,_jsx(_components.code,{children:`latest`}),` tag, plus each `,_jsx(_components.code,{children:`--tag`}),`.`]}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`install-from-harbor-github-or-hugging-face`,children:`Install from Harbor, GitHub, or Hugging Face`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`1`,language:`shellscript`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`shellscript`,children:_jsxs(_components.code,{language:`shellscript`,numberOfLines:`1`,children:[_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` install`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` tb/tb2`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` terminal-bench/terminal-bench-2`}),_jsx(_components.span,{style:{color:`#0550AE`,\"--shiki-dark\":`#569CD6`},children:` --location`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` harbor`})]}),`\n`]})})}),`\n`,_jsxs(_components.p,{children:[_jsx(_components.code,{children:`--location github`}),` and `,_jsx(_components.code,{children:`--location hugging_face`}),` take a repository as `,_jsx(_components.code,{children:`owner/name`}),` or its URL.`]}),`\n`,_jsx(Note,{children:_jsxs(_components.p,{children:[_jsx(_components.code,{children:`--location harbor`}),` needs `,_jsx(_components.code,{children:`uv`}),` or the `,_jsx(_components.code,{children:`harbor`}),` CLI on your `,_jsx(_components.code,{children:`PATH`}),`.`]})}),`\n`,_jsx(Heading,{level:`2`,id:`tag-versions`,children:`Tag versions`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`5`,language:`shellscript`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`shellscript`,children:_jsxs(_components.code,{language:`shellscript`,numberOfLines:`5`,children:[_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` versions`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset`})]}),`\n`,_jsx(_components.span,{className:`line`}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` tag`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset@2`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` stable`})]}),`\n`,_jsx(_components.span,{className:`line`}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` untag`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` v1`})]}),`\n`]})})}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[_jsx(_components.code,{children:`latest`}),` always moves. Another tag on a different version moves only with `,_jsx(_components.code,{children:`--force`}),`.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.code,{children:`untag`}),` removes a tag. `,_jsx(_components.code,{children:`latest`}),` can’t be removed.`]}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`run-an-agent-on-a-dataset`,children:`Run an agent on a dataset`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`1`,language:`shellscript`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`shellscript`,children:_jsxs(_components.code,{language:`shellscript`,numberOfLines:`1`,children:[_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` run`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` start`}),_jsx(_components.span,{style:{color:`#0550AE`,\"--shiki-dark\":`#569CD6`},children:` --agent`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-agent`}),_jsx(_components.span,{style:{color:`#0550AE`,\"--shiki-dark\":`#569CD6`},children:` --dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset@stable`})]}),`\n`]})})}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsxs(_components.li,{children:[`After `,_jsx(_components.code,{children:`@`}),`, pass a revision number, a tag, or a digest. Without it, the run uses `,_jsx(_components.code,{children:`latest`}),`.`]}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.code,{children:`--slice`}),`, `,_jsx(_components.code,{children:`--task-ids`}),`, and `,_jsx(_components.code,{children:`--concurrency`}),` work as in `,_jsx(_components.a,{href:`/runs/start`,children:`Start a run`}),`.`]}),`\n`]}),`\n`,_jsx(Heading,{level:`2`,id:`inspect-tasks`,children:`Inspect tasks`}),`\n`,_jsx(CodeBlock,{filename:``,numberOfLines:`3`,language:`shellscript`,children:_jsx(_components.pre,{className:`shiki shiki-themes github-light-default dark-plus`,style:{backgroundColor:`#ffffff`,\"--shiki-dark-bg\":`#0B0C0E`,color:`#1f2328`,\"--shiki-dark\":`#D4D4D4`},language:`shellscript`,children:_jsxs(_components.code,{language:`shellscript`,numberOfLines:`3`,children:[_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` task`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` list`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset@2`})]}),`\n`,_jsx(_components.span,{className:`line`}),`\n`,_jsxs(_components.span,{className:`line`,children:[_jsx(_components.span,{style:{color:`#953800`,\"--shiki-dark\":`#DCDCAA`},children:`valkyrie`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` dataset`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` task`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` download`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` my-benchmark/my-dataset@2`}),_jsx(_components.span,{style:{color:`#0A3069`,\"--shiki-dark\":`#CE9178`},children:` hello`})]}),`\n`]})})}),`\n`,_jsxs(_components.p,{children:[`The download is saved as `,_jsx(_components.code,{children:`TASK_ID.zip`}),` unless you pass `,_jsx(_components.code,{children:`--output`}),`.`]}),`\n`,_jsx(Heading,{level:`2`,id:`reference`,children:`Reference`}),`\n`,_jsxs(_components.ul,{children:[`\n`,_jsx(_components.li,{children:_jsx(_components.a,{href:`/reference/cli/dataset`,children:_jsx(_components.code,{children:`valkyrie dataset`})})}),`\n`,_jsxs(_components.li,{children:[_jsx(_components.a,{href:`/reference/sdk/datasets`,children:_jsx(_components.code,{children:`client.datasets`})}),` and `,_jsx(_components.a,{href:`/reference/sdk/datasets-versions`,children:_jsx(_components.code,{children:`client.datasets.versions`})})]}),`\n`]})]})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent};function _missingMdxReference(id,component){throw new Error(`Expected `+(component?`component`:`object`)+\" `\"+id+\"` to be defined: you likely forgot to import, pass, or provide it.\")}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Publish a dataset","description":"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.","href":"/benchmarks/datasets"}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[{"title":"Lay out the task folders","slug":"lay-out-the-task-folders","depth":2,"children":[]},{"title":"Read secrets in task environments","slug":"read-secrets-in-task-environments","depth":2,"children":[]},{"title":"Push a folder","slug":"push-a-folder","depth":2,"children":[]},{"title":"Install from Harbor, GitHub, or Hugging Face","slug":"install-from-harbor-github-or-hugging-face","depth":2,"children":[]},{"title":"Tag versions","slug":"tag-versions","depth":2,"children":[]},{"title":"Run an agent on a dataset","slug":"run-an-agent-on-a-dataset","depth":2,"children":[]},{"title":"Inspect tasks","slug":"inspect-tasks","depth":2,"children":[]},{"title":"Reference","slug":"reference","depth":2,"children":[]}],"codeExamples":{}},"jsLinks":[],"subdomain":"valkyrie-vals","siteName":"Valkyrie","title":"Publish a dataset - Valkyrie","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-11-13T19:29:58.212Z","originalFileLocation":"benchmarks/datasets.mdx"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.\">\u003cmeta data-mint-head name=\"application-name\" content=\"Valkyrie\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Publish a dataset - Valkyrie\">\u003cmeta data-mint-head property=\"og:description\" content=\"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Valkyrie\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.valkyrie.vals.ai/benchmarks/datasets\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://valkyrie-vals.mintlify.site/_mintlify/api/og/v2?division=Datasets\u0026amp;title=Publish+a+dataset\u0026amp;description=Publish+task+folders+as+a+versioned+dataset+in+your+benchmark%2C+tag+versions%2C+and+run+agents+on+them.\u0026amp;theme=f8b3606d0e8bb85b292ff87b\u0026amp;signature=43da87973f810b97a0a0a37896dfcde4314bd2101e9fd8e8edbe3d564dcbaa00\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Publish a dataset - Valkyrie\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://valkyrie-vals.mintlify.site/_mintlify/api/og/v2?division=Datasets\u0026amp;title=Publish+a+dataset\u0026amp;description=Publish+task+folders+as+a+versioned+dataset+in+your+benchmark%2C+tag+versions%2C+and+run+agents+on+them.\u0026amp;theme=f8b3606d0e8bb85b292ff87b\u0026amp;signature=43da87973f810b97a0a0a37896dfcde4314bd2101e9fd8e8edbe3d564dcbaa00\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/valkyrie-vals/oJhbVMD0h5yAk4Mv/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Valkyrie\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#386B46\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.valkyrie.vals.ai/benchmarks/datasets\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/benchmarks/datasets.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.valkyrie.vals.ai/#organization\",\"name\":\"Valkyrie\",\"url\":\"https://docs.valkyrie.vals.ai\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/valkyrie-vals/tCK_p9H_q6ml7cFr/images/valkyrie-logo-light.png?fit=max\u0026auto=format\u0026n=tCK_p9H_q6ml7cFr\u0026q=85\u0026s=defbf7b76eebf8e90b1beede16a4f7a3\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.valkyrie.vals.ai#website\",\"name\":\"Valkyrie\",\"url\":\"https://docs.valkyrie.vals.ai\",\"publisher\":{\"@id\":\"https://docs.valkyrie.vals.ai/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets#webpage\",\"url\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets\",\"name\":\"Publish a dataset\",\"description\":\"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.\",\"dateModified\":\"2026-11-13T19:29:58.212Z\",\"isPartOf\":{\"@id\":\"https://docs.valkyrie.vals.ai#website\"},\"breadcrumb\":{\"@id\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Valkyrie\",\"item\":\"https://docs.valkyrie.vals.ai\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Publish a dataset\",\"item\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets\"}]},{\"@type\":[\"Article\",\"TechArticle\"],\"@id\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets#article\",\"headline\":\"Publish a dataset\",\"name\":\"Publish a dataset\",\"description\":\"Publish task folders as a versioned dataset in your benchmark, tag versions, and run agents on them.\",\"url\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets\",\"mainEntityOfPage\":{\"@id\":\"https://docs.valkyrie.vals.ai/benchmarks/datasets#webpage\"},\"dateModified\":\"2026-11-13T19:29:58.212Z\",\"publisher\":{\"@id\":\"https://docs.valkyrie.vals.ai/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.valkyrie.vals.ai#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Valkyrie\",\"publisher\":{\"@type\":\"Organization\",\"name\":\"Valkyrie\"},\"provider\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","agentPointerHref":"/benchmarks/datasets.md","siteName":"Valkyrie","nav":{"global":null,"tabs":[{"tab":"CLI","icon":"terminal","groups":[{"group":"Get started","pages":[{"title":"What is Valkyrie?","sidebarTitle":"Introduction","href":"/introduction/what-is-valkyrie"},{"title":"Quickstart","href":"/get-started/quickstart"},{"title":"Configure the CLI and SDK","sidebarTitle":"Configuration","href":"/get-started/configuration"},{"title":"Configure sandbox providers","sidebarTitle":"Sandbox providers","href":"/get-started/sandbox-providers"}]},{"group":"Agents","pages":[{"title":"Package an agent","href":"/agents/package-an-agent"},{"title":"Manage agents","href":"/agents/manage-agents"},{"title":"Agent contract reference","sidebarTitle":"Contract reference","href":"/agents/agent-contract"}]},{"group":"Runs","pages":[{"title":"Start a run","href":"/runs/start"},{"title":"Monitor runs","href":"/runs/monitor"},{"title":"Manage a run","href":"/runs/manage"},{"title":"Download results and outputs","sidebarTitle":"Results and outputs","href":"/runs/results-and-outputs"},{"title":"Task time limits","sidebarTitle":"Time limits","description":"How long an agent can work on a task, what counts toward it, and what happens when time runs out.","href":"/runs/time-limits"}]},{"group":"Datasets","pages":[{"title":"Publish a dataset","href":"/benchmarks/datasets"}]},{"group":"Integrations","pages":[{"title":"Invoke a Lambda after a run","sidebarTitle":"Post-run Lambda","description":"Have Valkyrie call an AWS Lambda function with a run's details when the run finishes.","href":"/integrations/post-run-lambda"},{"title":"Analyze runs with Docent","sidebarTitle":"Docent","href":"/integrations/docent"}]},{"group":"CLI reference","pages":[{"title":"CLI reference","href":"/reference/cli/index"},{"title":"valkyrie run","href":"/reference/cli/run"},{"title":"valkyrie agent","href":"/reference/cli/agent"},{"title":"valkyrie benchmark","href":"/reference/cli/benchmark"},{"title":"valkyrie dataset","href":"/reference/cli/dataset"},{"title":"valkyrie queue","href":"/reference/cli/queue"},{"title":"valkyrie project","href":"/reference/cli/project"},{"title":"valkyrie secret","href":"/reference/cli/secret"},{"title":"valkyrie provider","href":"/reference/cli/provider"},{"title":"valkyrie login","href":"/reference/cli/login"},{"title":"valkyrie token","href":"/reference/cli/token"},{"title":"valkyrie org","href":"/reference/cli/org"},{"title":"valkyrie tui","href":"/reference/cli/tui"}]},{"group":"Self-hosting","pages":[{"title":"Run Tracker locally","href":"/self-hosting/local-tracker"}]}]},{"tab":"Python SDK","icon":"code","pages":[{"title":"Python SDK","href":"/sdk/quickstart"}]},{"tab":"Benchmark services","icon":"server","pages":[{"title":"Benchmark services","href":"/benchmarks/convert-a-benchmark"}]}]},"basePath":"","title":"Publish a dataset - Valkyrie","buildId":"dpl_5joLUXmnJgwqjrHAS4dxZrQTdxgh","deploymentId":"dpl_5joLUXmnJgwqjrHAS4dxZrQTdxgh","dynamics":["10e4515597"],"chunks":["BannerMarkdown-bDkRQgq9.js","dist-CUljsAY7.js","lib-DuNMoZ05.js","lib-B8HbPgcC.js","clsx-B2t_mZQG.js","html-void-elements-mCSPHezU.js","katex-YMM-FMeD.js","marked.esm-CZWythHk.js"]}