{"data":{"slug":"jinjieni-mixeval","name":"MixEval","tagline":"The official evaluation suite and dynamic data release for MixEval.","github_url":"https://github.com/JinjieNi/MixEval","owner":"JinjieNi","repo":"MixEval","owner_avatar_url":"https://avatars.githubusercontent.com/u/46987361?v=4","primary_language":"Python","stars":254,"forks":40,"topics":["benchmark","benchmark-mixture","benchmarking-framework","benchmarking-suite","evaluation","evaluation-framework","foundation-models","large-language-model","large-language-models","large-multimodal-models","llm-evaluation","llm-evaluation-framework","llm-inference","mixeval"],"archived":false,"github_pushed_at":"2024-11-10T02:23:50+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jinjieni-mixeval","markdown_url":"https://www.graphcanon.com/tools/jinjieni-mixeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jinjieni-mixeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jinjieni-mixeval","description":"The official evaluation suite and dynamic data release for MixEval.","homepage_url":"https://mixeval.github.io/","license":null,"open_issues":7,"watchers":1,"ai_summary":null,"readme_excerpt":"# Quick Start\n**(Step 1)** Clone repo and setup the environment:\n```\ngit clone https://github.com/Psycoy/MixEval.git\ncd MixEval\nconda create -n MixEval python=3.11 --yes\nconda activate MixEval\nbash setup.sh","github_created_at":"2024-06-01T10:50:50+00:00","created_at":"2026-07-11T10:34:59.538195+00:00","updated_at":"2026-07-12T03:26:44.836295+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"evaluation","name":"evaluation"},{"slug":"large-language-model","name":"large language model"},{"slug":"benchmarking-suite","name":"benchmarking-suite"},{"slug":"benchmark","name":"benchmark"},{"slug":"benchmark-mixture","name":"benchmark-mixture"},{"slug":"foundation-models","name":"foundation models"},{"slug":"benchmarking-framework","name":"benchmarking-framework"},{"slug":"evaluation-framework","name":"evaluation framework"}],"trust":{"provenance":{"is_fork":false,"github_id":808982778,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:01:07.729Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":608,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":109,"high_count":0,"last_scan_at":"2026-07-11T12:01:15.691Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:01:15.006Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T12:01:15.006Z"}}}}