{"data":{"slug":"onejune2018-awesome-llm-eval","name":"Awesome-LLM-Eval","tagline":"Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs. 一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.","github_url":"https://github.com/onejune2018/Awesome-LLM-Eval","owner":"onejune2018","repo":"Awesome-LLM-Eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/35061855?v=4","primary_language":null,"stars":648,"forks":78,"topics":["awsome-list","awsome-lists","benchmark","bert","chatglm","chatgpt","dataset","evaluation","gpt3","large-language-model","leaderboard","llama","llm","llm-evaluation","machine-learning","nlp","openai","qwen","rag"],"archived":false,"github_pushed_at":"2025-11-24T01:59:12+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/onejune2018-awesome-llm-eval","markdown_url":"https://www.graphcanon.com/tools/onejune2018-awesome-llm-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/onejune2018-awesome-llm-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=onejune2018-awesome-llm-eval","description":"Awesome-LLM-Eval: a curated list of tools, datasets/benchmark, demos, leaderboard, papers, docs and models, mainly for Evaluation on LLMs.  一个由工具、基准/数据、演示、排行榜和大模型等组成的精选列表，主要面向基础大模型评测，旨在探求生成式AI的技术边界.","homepage_url":"https://arxiv.org/abs/2508.18646","license":"MIT","open_issues":38,"watchers":8,"ai_summary":null,"readme_excerpt":null,"github_created_at":"2023-04-26T10:10:06+00:00","created_at":"2026-07-11T11:59:50.251234+00:00","updated_at":"2026-07-11T11:59:52.575311+00:00","categories":[{"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":"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"}],"tags":[{"slug":"awsome-list","name":"awsome-list"},{"slug":"awsome-lists","name":"awsome-lists"},{"slug":"benchmark","name":"benchmark"},{"slug":"bert","name":"bert"},{"slug":"chatglm","name":"chatglm"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"dataset","name":"dataset"},{"slug":"evaluation","name":"evaluation"}],"trust":{"provenance":{"is_fork":false,"github_id":632878141,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T11:59:50.935Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":null,"days_since_push":229,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:59:51.521Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T11:59:51.252Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T11:59:51.252Z"}}}}