{"data":{"node":{"slug":"gersteinlab-biocoder","name":"BioCoder","tagline":"Benchmark for bioinformatics code generation using LLMs","github_url":"https://github.com/gersteinlab/BioCoder","owner":"gersteinlab","repo":"BioCoder","owner_avatar_url":"https://avatars.githubusercontent.com/u/1662794?v=4","primary_language":"Jupyter Notebook","stars":58,"forks":16,"topics":[],"archived":false,"github_pushed_at":"2025-07-31T09:01:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/gersteinlab-biocoder","markdown_url":"https://www.graphcanon.com/tools/gersteinlab-biocoder.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/gersteinlab-biocoder","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=gersteinlab-biocoder"},"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":"benchmarking","name":"benchmarking"},{"slug":"bioinformatics","name":"bioinformatics"},{"slug":"code-generation","name":"code generation"},{"slug":"evaluation-framework","name":"evaluation-framework"},{"slug":"large-language-models","name":"large language models"}],"edges":[],"neighbours":[{"slug":"zai-org-codegeex","name":"CodeGeeX","tagline":"CodeGeeX is an open multilingual code generation model implemented in Mindspore and available via PyTorch.","github_url":"https://github.com/zai-org/CodeGeeX","owner":"zai-org","repo":"CodeGeeX","owner_avatar_url":"https://avatars.githubusercontent.com/u/223098841?v=4","primary_language":"Python","stars":8809,"forks":688,"topics":["code-generation","pretrained-models","tools"],"archived":false,"github_pushed_at":"2024-08-13T05:59:38+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/zai-org-codegeex","markdown_url":"https://www.graphcanon.com/tools/zai-org-codegeex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/zai-org-codegeex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=zai-org-codegeex","shared_categories":["llm-frameworks"]},{"slug":"bigcode-project-starcoder","name":"starcoder","tagline":"Home of StarCoder: fine-tuning & inference!","github_url":"https://github.com/bigcode-project/starcoder","owner":"bigcode-project","repo":"starcoder","owner_avatar_url":"https://avatars.githubusercontent.com/u/110470554?v=4","primary_language":"Python","stars":7503,"forks":525,"topics":[],"archived":false,"github_pushed_at":"2024-02-27T02:05:57+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/bigcode-project-starcoder","markdown_url":"https://www.graphcanon.com/tools/bigcode-project-starcoder.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/bigcode-project-starcoder","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=bigcode-project-starcoder","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":5576,"forks":930,"topics":["benchmark","language-model","software-engineering"],"archived":false,"github_pushed_at":"2026-07-27T05:34:27+00:00","maintenance_label":"Steady","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":["evaluation-observability"]},{"slug":"openai-human-eval","name":"human-eval","tagline":"Evaluating Large Language Models Trained on Code","github_url":"https://github.com/openai/human-eval","owner":"openai","repo":"human-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":3331,"forks":452,"topics":[],"archived":false,"github_pushed_at":"2025-01-17T18:22:17+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/openai-human-eval","markdown_url":"https://www.graphcanon.com/tools/openai-human-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-human-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-human-eval","shared_categories":["evaluation-observability"]},{"slug":"salesforce-codet5","name":"CodeT5","tagline":"Home of CodeT5: Open Code LLMs for Code Understanding and Generation","github_url":"https://github.com/salesforce/CodeT5","owner":"salesforce","repo":"CodeT5","owner_avatar_url":"https://avatars.githubusercontent.com/u/453694?v=4","primary_language":"Python","stars":3098,"forks":487,"topics":["code-generation","code-intelligence","code-understanding","language-model","large-language-models"],"archived":true,"github_pushed_at":"2026-06-25T16:27:18+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/salesforce-codet5","markdown_url":"https://www.graphcanon.com/tools/salesforce-codet5.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/salesforce-codet5","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=salesforce-codet5","shared_categories":["llm-frameworks"]},{"slug":"microsoft-codebert","name":"CodeBERT","tagline":"CodeBERT series models for code pretraining in Python and programming languages","github_url":"https://github.com/microsoft/CodeBERT","owner":"microsoft","repo":"CodeBERT","owner_avatar_url":"https://avatars.githubusercontent.com/u/6154722?v=4","primary_language":"Python","stars":2787,"forks":497,"topics":[],"archived":false,"github_pushed_at":"2023-07-09T12:26:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/microsoft-codebert","markdown_url":"https://www.graphcanon.com/tools/microsoft-codebert.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/microsoft-codebert","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=microsoft-codebert","shared_categories":[]},{"slug":"opencoder-llm-opencoder-llm","name":"OpenCoder-llm","tagline":"The Open Cookbook for Top-Tier Code Large Language Models","github_url":"https://github.com/OpenCoder-llm/OpenCoder-llm","owner":"OpenCoder-llm","repo":"OpenCoder-llm","owner_avatar_url":"https://avatars.githubusercontent.com/u/186387526?v=4","primary_language":"Python","stars":2103,"forks":125,"topics":[],"archived":false,"github_pushed_at":"2024-12-08T16:46:00+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/opencoder-llm-opencoder-llm","markdown_url":"https://www.graphcanon.com/tools/opencoder-llm-opencoder-llm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/opencoder-llm-opencoder-llm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=opencoder-llm-opencoder-llm","shared_categories":["evaluation-observability","llm-frameworks"]},{"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":2095,"forks":171,"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":["llm-frameworks"]},{"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":1794,"forks":205,"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":"Slowing","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":["evaluation-observability"]},{"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":1291,"forks":74,"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":["evaluation-observability","llm-frameworks"]},{"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":1055,"forks":261,"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":["evaluation-observability"]},{"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":925,"forks":195,"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":["evaluation-observability"]}]}}