{"id":26571948,"url":"https://github.com/paradite/eval-data","last_synced_at":"2026-02-21T03:30:58.396Z","repository":{"id":225128691,"uuid":"765141103","full_name":"paradite/eval-data","owner":"paradite","description":"Prompts and evaluation data for LLMs on real world coding and writing tasks","archived":false,"fork":false,"pushed_at":"2025-09-13T06:27:37.000Z","size":1984,"stargazers_count":16,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-09-13T08:32:07.595Z","etag":null,"topics":["ai","benchmark","eval","evaluation","llm","prompt","prompt-engineering"],"latest_commit_sha":null,"homepage":"https://eval.16x.engineer/","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/paradite.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-02-29T11:05:03.000Z","updated_at":"2025-09-13T06:27:41.000Z","dependencies_parsed_at":"2025-08-20T09:19:37.134Z","dependency_job_id":"b4cbb2fd-aa63-4900-a085-77821051bfce","html_url":"https://github.com/paradite/eval-data","commit_stats":null,"previous_names":["paradite/prompt-sample","paradite/16x-eval","paradite/eval-data"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/paradite/eval-data","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paradite%2Feval-data","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paradite%2Feval-data/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paradite%2Feval-data/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paradite%2Feval-data/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/paradite","download_url":"https://codeload.github.com/paradite/eval-data/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/paradite%2Feval-data/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29672704,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-21T03:11:15.450Z","status":"ssl_error","status_checked_at":"2026-02-21T03:10:34.920Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","benchmark","eval","evaluation","llm","prompt","prompt-engineering"],"created_at":"2025-03-22T23:18:14.822Z","updated_at":"2026-02-21T03:30:58.377Z","avatar_url":"https://github.com/paradite.png","language":"TypeScript","readme":"# Eval data\n\nEvaluation data for LLMs and prompts on real world coding tasks and writing tasks.\n\nBuilt by [16x Prompt](https://prompt.16x.engineer/) and [16x Eval](https://eval.16x.engineer/). \n\n## Coding Projects\n\n### Next.js\n\n[emoji-todo](/projects/emoji-todo/) - A simple Next.js TODO app with emojis.\n\n### SQL\n\n[sql](/projects/sql/) - SQL code snippets.\n\n### Python\n\n[python-script](/projects/python-script/) - Python script code snippets.\n\n### Benchmark Visualization\n\n[visualization](/projects/visualization/) - Coding a visualization of benchmark results.\n\n### TypeScript Narrowing\n\n[typescript-narrowing](/projects/typescript-narrowing/) - Coding TypeScript narrowing tests.\n\n### Clean Markdown\n\n[clean-markdown](/projects/clean-markdown/) - Clean markdown into plain text.\n\n### Clean MDX\n\n[clean-mdx](/projects/clean-mdx/) - Clean MDX into plain text.\n\n### Tailwind CSS Z-Index\n\n[tailwindcss-v3-z-index](/projects/tailwindcss-v3-z-index/) - Fix invalid z-index classes in Tailwind CSS v3.\n\n## Writing Projects\n\n### AI Timeline\n\n[ai-timeline](/projects/ai-timeline/) - Writing an AI Timeline.\n\n## Image Analysis Projects\n\n### Kanji\n\n[kanji](/projects/kanji/) - Image analysis and explanation related to kanji and Chinese characters.\n\n### Water bottle\n\n[water-bottle](/projects/water-bottle/) - Image analysis and explanation related to water bottle and physics.\n\n## Model Evaluation Results\n\n[model-eval-results](/model-eval-results/) - Raw results exported from [16x Eval](https://eval.16x.engineer/) for models evaluations.\n\n## 16x Eval\n\nI am building a local desktop app to evaluate models and prompts.\n\nSee [16x Eval website](https://eval.16x.engineer/) for more information.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fparadite%2Feval-data","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fparadite%2Feval-data","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fparadite%2Feval-data/lists"}