{"data":{"node":{"slug":"nuprl-multipl-e","name":"MultiPL-E","tagline":"A multi-programming language benchmark for LLMs","github_url":"https://github.com/nuprl/MultiPL-E","owner":"nuprl","repo":"MultiPL-E","owner_avatar_url":"https://avatars.githubusercontent.com/u/4161665?v=4","primary_language":"Python","stars":316,"forks":59,"topics":[],"archived":false,"github_pushed_at":"2026-04-12T16:59:02+00:00","maintenance_label":"Slowing","stars_delta_30d":2,"url":"https://www.graphcanon.com/tools/nuprl-multipl-e","markdown_url":"https://www.graphcanon.com/tools/nuprl-multipl-e.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nuprl-multipl-e","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nuprl-multipl-e"},"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":"ai-benchmark","name":"ai benchmark"},{"slug":"benchmarking","name":"benchmarking"},{"slug":"code-generation","name":"code-generation"},{"slug":"multilingual-benchmark","name":"multilingual benchmark"},{"slug":"neural-code-generation","name":"neural code generation"},{"slug":"program-synthesis","name":"program-synthesis"},{"slug":"python","name":"python"},{"slug":"transformers","name":"transformers"}],"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":"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":14192,"forks":3664,"topics":["evaluation-framework","language-model","transformer"],"archived":false,"github_pushed_at":"2026-09-14T10:51:06+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":"facebookresearch-lingua","name":"lingua","tagline":"Meta Lingua: a lean efficient easy-to-hack codebase to research LLMs","github_url":"https://github.com/facebookresearch/lingua","owner":"facebookresearch","repo":"lingua","owner_avatar_url":"https://avatars.githubusercontent.com/u/16943930?v=4","primary_language":"Python","stars":4764,"forks":270,"topics":[],"archived":false,"github_pushed_at":"2025-07-18T09:36:44+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/facebookresearch-lingua","markdown_url":"https://www.graphcanon.com/tools/facebookresearch-lingua.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/facebookresearch-lingua","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=facebookresearch-lingua","shared_categories":["llm-frameworks"]},{"slug":"eth-sri-lmql","name":"lmql","tagline":"A language for constraint-guided and efficient LLM programming.","github_url":"https://github.com/eth-sri/lmql","owner":"eth-sri","repo":"lmql","owner_avatar_url":"https://avatars.githubusercontent.com/u/5363413?v=4","primary_language":"Python","stars":4203,"forks":221,"topics":["chatgpt","huggingface","language-model","programming-language"],"archived":false,"github_pushed_at":"2025-05-22T07:32:31+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/eth-sri-lmql","markdown_url":"https://www.graphcanon.com/tools/eth-sri-lmql.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/eth-sri-lmql","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=eth-sri-lmql","shared_categories":["llm-frameworks"]},{"slug":"google-big-bench","name":"BIG-bench","tagline":"Collaborative benchmark for language model capabilities","github_url":"https://github.com/google/BIG-bench","owner":"google","repo":"BIG-bench","owner_avatar_url":"https://avatars.githubusercontent.com/u/1342004?v=4","primary_language":"Python","stars":3244,"forks":618,"topics":[],"archived":true,"github_pushed_at":"2024-07-19T11:57:37+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/google-big-bench","markdown_url":"https://www.graphcanon.com/tools/google-big-bench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/google-big-bench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=google-big-bench","shared_categories":["evaluation-observability"]},{"slug":"stanford-crfm-helm","name":"helm","tagline":"Holistic, reproducible and transparent evaluation of foundation models","github_url":"https://github.com/stanford-crfm/helm","owner":"stanford-crfm","repo":"helm","owner_avatar_url":"https://avatars.githubusercontent.com/u/75054807?v=4","primary_language":"Python","stars":2939,"forks":421,"topics":[],"archived":false,"github_pushed_at":"2026-09-01T01:33:19+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/stanford-crfm-helm","markdown_url":"https://www.graphcanon.com/tools/stanford-crfm-helm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/stanford-crfm-helm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=stanford-crfm-helm","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":"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":"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":["evaluation-observability"]},{"slug":"andrewkchan-yalm","name":"yalm","tagline":"LLM inference engine in C++/CUDA without dependency on external libraries except for I/O","github_url":"https://github.com/andrewkchan/yalm","owner":"andrewkchan","repo":"yalm","owner_avatar_url":"https://avatars.githubusercontent.com/u/8591901?v=4","primary_language":"C++","stars":600,"forks":65,"topics":["cpp","cuda","inference-engine","llama","llamacpp","llm","llm-inference","machine-learning","mistral"],"archived":false,"github_pushed_at":"2025-09-13T09:22:40+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/andrewkchan-yalm","markdown_url":"https://www.graphcanon.com/tools/andrewkchan-yalm.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/andrewkchan-yalm","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=andrewkchan-yalm","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":"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"]}]}}