{"data":{"node":{"slug":"xlang-ai-ds-1000","name":"DS-1000","tagline":"Benchmark and code for evaluating large language models on data science tasks","github_url":"https://github.com/xlang-ai/DS-1000","owner":"xlang-ai","repo":"DS-1000","owner_avatar_url":"https://avatars.githubusercontent.com/u/128829376?v=4","primary_language":"Python","stars":278,"forks":31,"topics":["benchmark","code-generation","data-science","large-language-models","semantic-parsing"],"archived":false,"github_pushed_at":"2024-10-30T17:43:46+00:00","maintenance_label":"Dormant","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/xlang-ai-ds-1000","markdown_url":"https://www.graphcanon.com/tools/xlang-ai-ds-1000.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/xlang-ai-ds-1000","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=xlang-ai-ds-1000"},"categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"benchmark","name":"benchmark"},{"slug":"code-generation","name":"code-generation"},{"slug":"data-science","name":"data-science"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"semantic-parsing","name":"semantic-parsing"}],"edges":[],"neighbours":[{"slug":"huggingface-datasets","name":"datasets","tagline":"Largest hub of ready-to-use datasets for AI models","github_url":"https://github.com/huggingface/datasets","owner":"huggingface","repo":"datasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":21999,"forks":3448,"topics":["ai","artificial-intelligence","computer-vision","dataset-hub","datasets","deep-learning","huggingface","llm","machine-learning","natural-language-processing","nlp","numpy","pandas","pytorch","speech","tensorflow"],"archived":false,"github_pushed_at":"2026-09-17T10:04:41+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/huggingface-datasets","markdown_url":"https://www.graphcanon.com/tools/huggingface-datasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-datasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-datasets","shared_categories":["data-retrieval"]},{"slug":"tanweai-pua","name":"pua","tagline":"A skill package for enhancing the functionality of AI agents within development environments","github_url":"https://github.com/tanweai/pua","owner":"tanweai","repo":"pua","owner_avatar_url":"https://avatars.githubusercontent.com/u/256783335?v=4","primary_language":"TypeScript","stars":19454,"forks":1185,"topics":["agency","agent","pip","pua"],"archived":false,"github_pushed_at":"2026-07-16T05:58:58+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/tanweai-pua","markdown_url":"https://www.graphcanon.com/tools/tanweai-pua.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tanweai-pua","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tanweai-pua","shared_categories":[]},{"slug":"swe-bench-swe-bench","name":"SWE-bench","tagline":"Benchmark for assessing language models' capability to resolve real-world Github issues","github_url":"https://github.com/SWE-bench/SWE-bench","owner":"SWE-bench","repo":"SWE-bench","owner_avatar_url":"https://avatars.githubusercontent.com/u/139597579?v=4","primary_language":"Python","stars":5986,"forks":1004,"topics":["benchmark","language-model","software-engineering"],"archived":false,"github_pushed_at":"2026-09-18T05:08:56+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/swe-bench-swe-bench","markdown_url":"https://www.graphcanon.com/tools/swe-bench-swe-bench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/swe-bench-swe-bench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=swe-bench-swe-bench","shared_categories":[]},{"slug":"ise-uiuc-magicoder","name":"magicoder","tagline":"A coding assistant for generating Python code snippets","github_url":"https://github.com/ise-uiuc/magicoder","owner":"ise-uiuc","repo":"magicoder","owner_avatar_url":"https://avatars.githubusercontent.com/u/92598497?v=4","primary_language":"Python","stars":2094,"forks":170,"topics":["ai4code","large-language-models","llm","llm4code"],"archived":false,"github_pushed_at":"2024-11-01T17:28:52+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/ise-uiuc-magicoder","markdown_url":"https://www.graphcanon.com/tools/ise-uiuc-magicoder.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ise-uiuc-magicoder","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ise-uiuc-magicoder","shared_categories":["model-training"]},{"slug":"evalplus-evalplus","name":"evalplus","tagline":"Rigorous evaluation of LLM-synthesized code","github_url":"https://github.com/evalplus/evalplus","owner":"evalplus","repo":"evalplus","owner_avatar_url":"https://avatars.githubusercontent.com/u/132106461?v=4","primary_language":"Python","stars":1825,"forks":209,"topics":["benchmark","chatgpt","efficiency","gpt-4","large-language-models","program-synthesis","testing"],"archived":false,"github_pushed_at":"2025-10-02T22:56:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/evalplus-evalplus","markdown_url":"https://www.graphcanon.com/tools/evalplus-evalplus.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/evalplus-evalplus","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=evalplus-evalplus","shared_categories":[]},{"slug":"huybery-awesome-code-llm","name":"Awesome-Code-LLM","tagline":"👨💻 An awesome and curated list of best code-LLM for research.","github_url":"https://github.com/huybery/Awesome-Code-LLM","owner":"huybery","repo":"Awesome-Code-LLM","owner_avatar_url":"https://avatars.githubusercontent.com/u/13436140?v=4","primary_language":null,"stars":1295,"forks":75,"topics":["awesome","code-generation","large-language-models"],"archived":false,"github_pushed_at":"2024-12-10T08:10:54+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/huybery-awesome-code-llm","markdown_url":"https://www.graphcanon.com/tools/huybery-awesome-code-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huybery-awesome-code-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huybery-awesome-code-llm","shared_categories":[]},{"slug":"bigcode-project-bigcode-evaluation-harness","name":"bigcode-evaluation-harness","tagline":"A framework for evaluating autoregressive code generation language models.","github_url":"https://github.com/bigcode-project/bigcode-evaluation-harness","owner":"bigcode-project","repo":"bigcode-evaluation-harness","owner_avatar_url":"https://avatars.githubusercontent.com/u/110470554?v=4","primary_language":"Python","stars":1062,"forks":262,"topics":[],"archived":false,"github_pushed_at":"2025-07-22T13:18:09+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/bigcode-project-bigcode-evaluation-harness","markdown_url":"https://www.graphcanon.com/tools/bigcode-project-bigcode-evaluation-harness.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bigcode-project-bigcode-evaluation-harness","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bigcode-project-bigcode-evaluation-harness","shared_categories":[]},{"slug":"livecodebench-livecodebench","name":"LiveCodeBench","tagline":"Holistic and contamination-free evaluation of large language models for code","github_url":"https://github.com/LiveCodeBench/LiveCodeBench","owner":"LiveCodeBench","repo":"LiveCodeBench","owner_avatar_url":"https://avatars.githubusercontent.com/u/161278213?v=4","primary_language":"Python","stars":958,"forks":206,"topics":["code-execution","code-generation","code-llms","code-repair","gpt-4","test-generation"],"archived":false,"github_pushed_at":"2025-07-16T00:58:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/livecodebench-livecodebench","markdown_url":"https://www.graphcanon.com/tools/livecodebench-livecodebench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/livecodebench-livecodebench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=livecodebench-livecodebench","shared_categories":[]},{"slug":"salesforce-coderl","name":"CodeRL","tagline":"CodeRL: Combines pretrained models and reinforcement learning for code generation.","github_url":"https://github.com/salesforce/CodeRL","owner":"salesforce","repo":"CodeRL","owner_avatar_url":"https://avatars.githubusercontent.com/u/453694?v=4","primary_language":"Python","stars":576,"forks":69,"topics":["ai","codegeneration","languagemodel","machinelearning","programsynthesis","reinforcementlearning"],"archived":false,"github_pushed_at":"2026-06-02T18:14:33+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/salesforce-coderl","markdown_url":"https://www.graphcanon.com/tools/salesforce-coderl.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/salesforce-coderl","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=salesforce-coderl","shared_categories":["model-training"]},{"slug":"radi-cho-datasetgpt","name":"datasetGPT","tagline":"A command-line tool for generating textual and conversational datasets with LLMs.","github_url":"https://github.com/radi-cho/datasetGPT","owner":"radi-cho","repo":"datasetGPT","owner_avatar_url":"https://avatars.githubusercontent.com/u/12954909?v=4","primary_language":"Python","stars":300,"forks":20,"topics":["cli","dataset-generation","large-language-models","python3"],"archived":false,"github_pushed_at":"2023-08-25T16:39:10+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/radi-cho-datasetgpt","markdown_url":"https://www.graphcanon.com/tools/radi-cho-datasetgpt.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/radi-cho-datasetgpt","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=radi-cho-datasetgpt","shared_categories":["model-training","data-retrieval"]},{"slug":"zhulinsen-fastdatasets","name":"FastDatasets","tagline":"A powerful tool for creating high-quality training datasets for Large Language Models (LLMs)","github_url":"https://github.com/ZhuLinsen/FastDatasets","owner":"ZhuLinsen","repo":"FastDatasets","owner_avatar_url":"https://avatars.githubusercontent.com/u/42829555?v=4","primary_language":"Python","stars":223,"forks":47,"topics":["asyncio","dataset-generation","datasets","llm","python"],"archived":false,"github_pushed_at":"2025-08-31T06:40:43+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/zhulinsen-fastdatasets","markdown_url":"https://www.graphcanon.com/tools/zhulinsen-fastdatasets.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zhulinsen-fastdatasets","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zhulinsen-fastdatasets","shared_categories":["model-training","data-retrieval"]},{"slug":"leolty-repobench","name":"repobench","tagline":"Benchmarking Repository-Level Code Auto-Completion Systems","github_url":"https://github.com/Leolty/repobench","owner":"Leolty","repo":"repobench","owner_avatar_url":"https://avatars.githubusercontent.com/u/58247268?v=4","primary_language":"Python","stars":213,"forks":13,"topics":[],"archived":false,"github_pushed_at":"2024-08-16T07:08:32+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/leolty-repobench","markdown_url":"https://www.graphcanon.com/tools/leolty-repobench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/leolty-repobench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=leolty-repobench","shared_categories":[]}]}}