{"data":{"node":{"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":431,"forks":37,"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"},"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":"humaneval","name":"humaneval"},{"slug":"wizardcoder","name":"wizardcoder"}],"edges":[],"neighbours":[{"slug":"openai-evals","name":"evals","tagline":"Framework for evaluating LLMs and LLM systems with an open-source registry of benchmarks.","github_url":"https://github.com/openai/evals","owner":"openai","repo":"evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":19127,"forks":3050,"topics":[],"archived":false,"github_pushed_at":"2026-04-14T15:29:57+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/openai-evals","markdown_url":"https://www.graphcanon.com/tools/openai-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-evals","shared_categories":["evaluation-observability"]},{"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":17226,"forks":1736,"topics":["evaluation-framework","evaluation-metrics","llm-evaluation","llm-evaluation-framework","llm-evaluation-metrics","python"],"archived":false,"github_pushed_at":"2026-07-27T11:33:31+00:00","maintenance_label":"Steady","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":13560,"forks":3467,"topics":["evaluation-framework","language-model","transformer"],"archived":false,"github_pushed_at":"2026-07-13T20:18:15+00:00","maintenance_label":"Steady","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":"openai-simple-evals","name":"simple-evals","tagline":"A lightweight library for evaluating language models.","github_url":"https://github.com/openai/simple-evals","owner":"openai","repo":"simple-evals","owner_avatar_url":"https://avatars.githubusercontent.com/u/14957082?v=4","primary_language":"Python","stars":4595,"forks":501,"topics":[],"archived":false,"github_pushed_at":"2026-04-22T22:16:18+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/openai-simple-evals","markdown_url":"https://www.graphcanon.com/tools/openai-simple-evals.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/openai-simple-evals","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=openai-simple-evals","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":"huggingface-lighteval","name":"lighteval","tagline":"All-in-one toolkit for evaluating LLMs across multiple backends","github_url":"https://github.com/huggingface/lighteval","owner":"huggingface","repo":"lighteval","owner_avatar_url":"https://avatars.githubusercontent.com/u/25720743?v=4","primary_language":"Python","stars":2508,"forks":523,"topics":["evaluation","evaluation-framework","evaluation-metrics","huggingface"],"archived":false,"github_pushed_at":"2026-06-29T13:03:33+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/huggingface-lighteval","markdown_url":"https://www.graphcanon.com/tools/huggingface-lighteval.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/huggingface-lighteval","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=huggingface-lighteval","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":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":"rlancemartin-auto-evaluator","name":"auto-evaluator","tagline":"A lightweight evaluation tool for question-answering using Langchain","github_url":"https://github.com/rlancemartin/auto-evaluator","owner":"rlancemartin","repo":"auto-evaluator","owner_avatar_url":"https://avatars.githubusercontent.com/u/122662504?v=4","primary_language":"Python","stars":1105,"forks":92,"topics":[],"archived":false,"github_pushed_at":"2023-05-10T02:00:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/rlancemartin-auto-evaluator","markdown_url":"https://www.graphcanon.com/tools/rlancemartin-auto-evaluator.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/rlancemartin-auto-evaluator","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=rlancemartin-auto-evaluator","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":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"]},{"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"]},{"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":196,"forks":22,"topics":["evaluation","generative-ai-benchmarking","llm","llm-benchmarking","llm-evaluation"],"archived":false,"github_pushed_at":"2026-07-06T01:17:36+00:00","maintenance_label":"Steady","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"]}]}}