{"data":{"node":{"slug":"vila-lab-open-llm-leaderboard","name":"Open-LLM-Leaderboard","tagline":"Tracks LLM performance on open-style questions","github_url":"https://github.com/VILA-Lab/Open-LLM-Leaderboard","owner":"VILA-Lab","repo":"Open-LLM-Leaderboard","owner_avatar_url":"https://avatars.githubusercontent.com/u/101944607?v=4","primary_language":"Python","stars":53,"forks":7,"topics":["leaderboard","llm-evaluation","llm-leaderboard","llms","open-ended-evaluation","open-ended-question-marker"],"archived":false,"github_pushed_at":"2024-06-27T11:03:32+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/vila-lab-open-llm-leaderboard","markdown_url":"https://www.graphcanon.com/tools/vila-lab-open-llm-leaderboard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/vila-lab-open-llm-leaderboard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=vila-lab-open-llm-leaderboard"},"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"}],"tags":[{"slug":"leaderboard","name":"leaderboard"},{"slug":"llm-evaluation","name":"llm-evaluation"},{"slug":"model-performance-tracking","name":"model-performance-tracking"},{"slug":"open-style-questions","name":"open-style-questions"}],"edges":[],"neighbours":[{"slug":"confident-ai-deepeval","name":"deepeval","tagline":"LLM Evaluation Framework.","github_url":"https://github.com/confident-ai/deepeval","owner":"confident-ai","repo":"deepeval","owner_avatar_url":"https://avatars.githubusercontent.com/u/130858411?v=4","primary_language":"Python","stars":18342,"forks":1953,"topics":["evaluation-framework","evaluation-metrics","llm-evaluation","llm-evaluation-framework","llm-evaluation-metrics","python"],"archived":false,"github_pushed_at":"2026-09-18T17:06:58+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/confident-ai-deepeval","markdown_url":"https://www.graphcanon.com/tools/confident-ai-deepeval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/confident-ai-deepeval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=confident-ai-deepeval","shared_categories":["evaluation-observability"]},{"slug":"eleutherai-lm-evaluation-harness","name":"lm-evaluation-harness","tagline":"A framework for few-shot evaluation of language models.","github_url":"https://github.com/EleutherAI/lm-evaluation-harness","owner":"EleutherAI","repo":"lm-evaluation-harness","owner_avatar_url":"https://avatars.githubusercontent.com/u/68924597?v=4","primary_language":"Python","stars":13906,"forks":3547,"topics":["evaluation-framework","language-model","transformer"],"archived":false,"github_pushed_at":"2026-09-01T13:51:29+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/eleutherai-lm-evaluation-harness","markdown_url":"https://www.graphcanon.com/tools/eleutherai-lm-evaluation-harness.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eleutherai-lm-evaluation-harness","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eleutherai-lm-evaluation-harness","shared_categories":["evaluation-observability"]},{"slug":"eugeneyan-open-llms","name":"open-llms","tagline":"A list of open LLMs available for commercial use","github_url":"https://github.com/eugeneyan/open-llms","owner":"eugeneyan","repo":"open-llms","owner_avatar_url":"https://avatars.githubusercontent.com/u/6831355?v=4","primary_language":null,"stars":12876,"forks":988,"topics":["commercial","large-language-models","llm","llms"],"archived":false,"github_pushed_at":"2025-02-13T06:37:12+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/eugeneyan-open-llms","markdown_url":"https://www.graphcanon.com/tools/eugeneyan-open-llms.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eugeneyan-open-llms","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eugeneyan-open-llms","shared_categories":[]},{"slug":"rucaibox-llmsurvey","name":"LLMSurvey","tagline":"A collection of papers and resources related to Large Language Models","github_url":"https://github.com/RUCAIBox/LLMSurvey","owner":"RUCAIBox","repo":"LLMSurvey","owner_avatar_url":"https://avatars.githubusercontent.com/u/54706620?v=4","primary_language":"Python","stars":12216,"forks":930,"topics":["chain-of-thought","chatgpt","in-context-learning","instruction-tuning","large-language-models","llm","llms","natural-language-processing","pre-trained-language-models","pre-training","rlhf"],"archived":false,"github_pushed_at":"2025-03-11T09:51:42+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey","markdown_url":"https://www.graphcanon.com/tools/rucaibox-llmsurvey.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rucaibox-llmsurvey","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rucaibox-llmsurvey","shared_categories":[]},{"slug":"wangrongsheng-awesome-llm-resources","name":"awesome-LLM-resources","tagline":"Summary of the world's best LLM resources.","github_url":"https://github.com/WangRongsheng/awesome-LLM-resources","owner":"WangRongsheng","repo":"awesome-LLM-resources","owner_avatar_url":"https://avatars.githubusercontent.com/u/55651568?v=4","primary_language":null,"stars":8968,"forks":993,"topics":["awesome-list","book","course","large-language-models","llama","llm","mistral","openai","qwen","rag","retrieval-augmented-generation","webui"],"archived":false,"github_pushed_at":"2026-09-14T09:00:10+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources","markdown_url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wangrongsheng-awesome-llm-resources","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wangrongsheng-awesome-llm-resources","shared_categories":["evaluation-observability"]},{"slug":"evolvinglmms-lab-lmms-eval","name":"lmms-eval","tagline":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","github_url":"https://github.com/EvolvingLMMs-Lab/lmms-eval","owner":"EvolvingLMMs-Lab","repo":"lmms-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/154951679?v=4","primary_language":"Python","stars":4368,"forks":639,"topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"archived":false,"github_pushed_at":"2026-08-06T02:22:23+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval","markdown_url":"https://www.graphcanon.com/tools/evolvinglmms-lab-lmms-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evolvinglmms-lab-lmms-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evolvinglmms-lab-lmms-eval","shared_categories":["evaluation-observability"]},{"slug":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","shared_categories":[]},{"slug":"declare-lab-instruct-eval","name":"instruct-eval","tagline":"Quantitative evaluation for instruction-tuned language models","github_url":"https://github.com/declare-lab/instruct-eval","owner":"declare-lab","repo":"instruct-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/59164695?v=4","primary_language":"Python","stars":553,"forks":45,"topics":["instruct-tuning","llm"],"archived":false,"github_pushed_at":"2024-03-10T05:00:00+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/declare-lab-instruct-eval","markdown_url":"https://www.graphcanon.com/tools/declare-lab-instruct-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/declare-lab-instruct-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=declare-lab-instruct-eval","shared_categories":["evaluation-observability"]},{"slug":"curated-awesome-lists-awesome-llms-fine-tuning","name":"awesome-llms-fine-tuning","tagline":"A comprehensive collection of resources for fine-tuning Large Language Models.","github_url":"https://github.com/Curated-Awesome-Lists/awesome-llms-fine-tuning","owner":"Curated-Awesome-Lists","repo":"awesome-llms-fine-tuning","owner_avatar_url":"https://avatars.githubusercontent.com/u/142611331?v=4","primary_language":null,"stars":527,"forks":80,"topics":["ai","awesome-list","deep-learning","fine-tuning","gpt","large-language-models","llms","machine-learning","nlp","transformers"],"archived":false,"github_pushed_at":"2026-09-04T19:22:27+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning","markdown_url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/curated-awesome-lists-awesome-llms-fine-tuning","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=curated-awesome-lists-awesome-llms-fine-tuning","shared_categories":[]},{"slug":"glgh-awesome-llm-human-preference-datasets","name":"awesome-llm-human-preference-datasets","tagline":"Curated list of Human Preference Datasets for LLM fine-tuning, RLHF, and eval","github_url":"https://github.com/glgh/awesome-llm-human-preference-datasets","owner":"glgh","repo":"awesome-llm-human-preference-datasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/16108776?v=4","primary_language":null,"stars":391,"forks":19,"topics":["awesome-list","datasets","eval","human-preferences","llm","machine-learning","nlp","rlhf"],"archived":false,"github_pushed_at":"2023-10-04T19:56:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/glgh-awesome-llm-human-preference-datasets","markdown_url":"https://www.graphcanon.com/tools/glgh-awesome-llm-human-preference-datasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/glgh-awesome-llm-human-preference-datasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=glgh-awesome-llm-human-preference-datasets","shared_categories":["evaluation-observability"]},{"slug":"jonathanchaveztamales-llm-leaderboard","name":"llm-leaderboard","tagline":"Comprehensive LLM benchmark scores and provider prices","github_url":"https://github.com/JonathanChavezTamales/llm-leaderboard","owner":"JonathanChavezTamales","repo":"llm-leaderboard","owner_avatar_url":"https://avatars.githubusercontent.com/u/22694942?v=4","primary_language":"JavaScript","stars":356,"forks":40,"topics":["llm","llm-agents","llm-evaluation","llmops","llms-benchmarking"],"archived":false,"github_pushed_at":"2025-10-24T17:47:59+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/jonathanchaveztamales-llm-leaderboard","markdown_url":"https://www.graphcanon.com/tools/jonathanchaveztamales-llm-leaderboard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jonathanchaveztamales-llm-leaderboard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jonathanchaveztamales-llm-leaderboard","shared_categories":["evaluation-observability"]},{"slug":"athina-ai-athina-evals","name":"athina-evals","tagline":"Python SDK for evaluating LLM generated responses","github_url":"https://github.com/athina-ai/athina-evals","owner":"athina-ai","repo":"athina-evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/139258696?v=4","primary_language":"Python","stars":301,"forks":22,"topics":["evaluation","evaluation-framework","evaluation-metrics","llm-eval","llm-evaluation","llm-evaluation-toolkit","llm-ops","llmops"],"archived":false,"github_pushed_at":"2025-06-06T15:54:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/athina-ai-athina-evals","markdown_url":"https://www.graphcanon.com/tools/athina-ai-athina-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/athina-ai-athina-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=athina-ai-athina-evals","shared_categories":["evaluation-observability"]}]}}