{"data":{"node":{"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","stars_delta_30d":22,"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"},"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":"code-execution","name":"code-execution"},{"slug":"code-generation","name":"code-generation"},{"slug":"code-repair","name":"code-repair"},{"slug":"gpt-4","name":"gpt-4"},{"slug":"python","name":"python"},{"slug":"test-generation","name":"test-generation"}],"edges":[],"neighbours":[{"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":"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":"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":"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":["evaluation-observability"]},{"slug":"code-yeongyu-lazycodex","name":"lazycodex","tagline":"Agent harness for complex codebases with project memory and execution planning","github_url":"https://github.com/code-yeongyu/lazycodex","owner":"code-yeongyu","repo":"lazycodex","owner_avatar_url":"https://avatars.githubusercontent.com/u/11153873?v=4","primary_language":"TypeScript","stars":3475,"forks":220,"topics":["ai","ai-agents","claude","claude-code","cli","codex","developer-tools","lazy","lazycodex","oh-my-openagent","omo","openai","orchestration","typescript"],"archived":false,"github_pushed_at":"2026-09-19T05:48:44+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/code-yeongyu-lazycodex","markdown_url":"https://www.graphcanon.com/tools/code-yeongyu-lazycodex.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/code-yeongyu-lazycodex","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=code-yeongyu-lazycodex","shared_categories":[]},{"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":3398,"forks":472,"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":"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":["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":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":["evaluation-observability"]},{"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":["evaluation-observability"]},{"slug":"floridsleeves-llmdebugger","name":"LLMDebugger","tagline":"A Large Language Model Debugger verifying runtime execution step by step","github_url":"https://github.com/FloridSleeves/LLMDebugger","owner":"FloridSleeves","repo":"LLMDebugger","owner_avatar_url":"https://avatars.githubusercontent.com/u/23695653?v=4","primary_language":"Python","stars":585,"forks":57,"topics":[],"archived":false,"github_pushed_at":"2024-09-10T23:32:12+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/floridsleeves-llmdebugger","markdown_url":"https://www.graphcanon.com/tools/floridsleeves-llmdebugger.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/floridsleeves-llmdebugger","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=floridsleeves-llmdebugger","shared_categories":["evaluation-observability"]},{"slug":"abacaj-code-eval","name":"code-eval","tagline":"Run evaluation on LLMs using human-eval benchmark.","github_url":"https://github.com/abacaj/code-eval","owner":"abacaj","repo":"code-eval","owner_avatar_url":"https://avatars.githubusercontent.com/u/7272343?v=4","primary_language":"Python","stars":432,"forks":36,"topics":["humaneval","wizardcoder"],"archived":false,"github_pushed_at":"2023-09-12T03:03:56+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/abacaj-code-eval","markdown_url":"https://www.graphcanon.com/tools/abacaj-code-eval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/abacaj-code-eval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=abacaj-code-eval","shared_categories":["evaluation-observability"]},{"slug":"alopatenko-llmevaluation","name":"LLMEvaluation","tagline":"A comprehensive guide to LLM evaluation methods","github_url":"https://github.com/alopatenko/LLMEvaluation","owner":"alopatenko","repo":"LLMEvaluation","owner_avatar_url":"https://avatars.githubusercontent.com/u/7122933?v=4","primary_language":"HTML","stars":201,"forks":24,"topics":["evaluation","generative-ai-benchmarking","llm","llm-benchmarking","llm-evaluation"],"archived":false,"github_pushed_at":"2026-09-15T00:35:53+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/alopatenko-llmevaluation","markdown_url":"https://www.graphcanon.com/tools/alopatenko-llmevaluation.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/alopatenko-llmevaluation","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=alopatenko-llmevaluation","shared_categories":["evaluation-observability"]},{"slug":"amazon-science-cceval","name":"cceval","tagline":"CrossCodeEval Benchmark for Cross-File Code Completion","github_url":"https://github.com/amazon-science/cceval","owner":"amazon-science","repo":"cceval","owner_avatar_url":"https://avatars.githubusercontent.com/u/70298811?v=4","primary_language":"Python","stars":184,"forks":29,"topics":[],"archived":false,"github_pushed_at":"2025-08-15T21:11:15+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/amazon-science-cceval","markdown_url":"https://www.graphcanon.com/tools/amazon-science-cceval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/amazon-science-cceval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=amazon-science-cceval","shared_categories":["evaluation-observability"]}]}}