{"data":{"node":{"slug":"hithink-research-bizfinbench","name":"BizFinBench","tagline":"A Business-Driven Real-World Financial Benchmark for Evaluating LLMs","github_url":"https://github.com/HiThink-Research/BizFinBench","owner":"HiThink-Research","repo":"BizFinBench","owner_avatar_url":"https://avatars.githubusercontent.com/u/186997494?v=4","primary_language":"Python","stars":169,"forks":12,"topics":["benchmark","finance","llm","llm-benchmarking","llm-evaluation"],"archived":false,"github_pushed_at":"2026-05-01T01:36:34+00:00","maintenance_label":"Slowing","stars_delta_30d":1,"url":"https://www.graphcanon.com/tools/hithink-research-bizfinbench","markdown_url":"https://www.graphcanon.com/tools/hithink-research-bizfinbench.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/hithink-research-bizfinbench","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=hithink-research-bizfinbench"},"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":"benchmark","name":"benchmark"},{"slug":"finance","name":"finance"},{"slug":"llm","name":"llm"},{"slug":"llm-benchmarking","name":"llm-benchmarking"},{"slug":"llm-evaluation","name":"llm-evaluation"}],"edges":[],"neighbours":[{"slug":"tauricresearch-tradingagents","name":"TradingAgents","tagline":"Multi-Agents LLM Financial Trading Framework","github_url":"https://github.com/TauricResearch/TradingAgents","owner":"TauricResearch","repo":"TradingAgents","owner_avatar_url":"https://avatars.githubusercontent.com/u/192884433?v=4","primary_language":"Python","stars":107378,"forks":20532,"topics":["agent","finance","llm","multiagent","trading"],"archived":false,"github_pushed_at":"2026-09-18T05:43:45+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/tauricresearch-tradingagents","markdown_url":"https://www.graphcanon.com/tools/tauricresearch-tradingagents.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/tauricresearch-tradingagents","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=tauricresearch-tradingagents","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":"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":"mooler0410-llmspracticalguide","name":"LLMsPracticalGuide","tagline":"Curated list of practical guide resources for LLMs","github_url":"https://github.com/Mooler0410/LLMsPracticalGuide","owner":"Mooler0410","repo":"LLMsPracticalGuide","owner_avatar_url":"https://avatars.githubusercontent.com/u/37475129?v=4","primary_language":null,"stars":10208,"forks":787,"topics":["large-language-models","natural-language-processing","nlp","survey"],"archived":false,"github_pushed_at":"2026-04-08T18:26:44+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/mooler0410-llmspracticalguide","markdown_url":"https://www.graphcanon.com/tools/mooler0410-llmspracticalguide.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mooler0410-llmspracticalguide","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mooler0410-llmspracticalguide","shared_categories":["evaluation-observability"]},{"slug":"wangrongsheng-awesome-llm-resources","name":"awesome-LLM-resources","tagline":"Summary of the world's best LLM resources.","github_url":"https://github.com/WangRongsheng/awesome-LLM-resources","owner":"WangRongsheng","repo":"awesome-LLM-resources","owner_avatar_url":"https://avatars.githubusercontent.com/u/55651568?v=4","primary_language":null,"stars":8968,"forks":993,"topics":["awesome-list","book","course","large-language-models","llama","llm","mistral","openai","qwen","rag","retrieval-augmented-generation","webui"],"archived":false,"github_pushed_at":"2026-09-14T09:00:10+00:00","maintenance_label":"Active","url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources","markdown_url":"https://www.graphcanon.com/tools/wangrongsheng-awesome-llm-resources.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wangrongsheng-awesome-llm-resources","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wangrongsheng-awesome-llm-resources","shared_categories":["evaluation-observability"]},{"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":[]},{"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":"georgian-io-llm-finetuning-toolkit","name":"LLM-Finetuning-Toolkit","tagline":"Toolkit for fine-tuning and testing open-source large language models","github_url":"https://github.com/georgian-io/LLM-Finetuning-Toolkit","owner":"georgian-io","repo":"LLM-Finetuning-Toolkit","owner_avatar_url":"https://avatars.githubusercontent.com/u/10764713?v=4","primary_language":"Python","stars":870,"forks":107,"topics":["ablation-study","classification","falcon","fine-tuning","finetuning","flan-t5","large-language-models","llama2","llm-test","lora","mistral-7b","nlp","nlp-machine-learning","qlora","redpajama","summarization","unit-testing","zephyr"],"archived":false,"github_pushed_at":"2026-05-04T16:33:40+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit","markdown_url":"https://www.graphcanon.com/tools/georgian-io-llm-finetuning-toolkit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/georgian-io-llm-finetuning-toolkit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=georgian-io-llm-finetuning-toolkit","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":46,"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":"curated-awesome-lists-awesome-llms-fine-tuning","name":"awesome-llms-fine-tuning","tagline":"A comprehensive collection of resources for fine-tuning Large Language Models.","github_url":"https://github.com/Curated-Awesome-Lists/awesome-llms-fine-tuning","owner":"Curated-Awesome-Lists","repo":"awesome-llms-fine-tuning","owner_avatar_url":"https://avatars.githubusercontent.com/u/142611331?v=4","primary_language":null,"stars":527,"forks":80,"topics":["ai","awesome-list","deep-learning","fine-tuning","gpt","large-language-models","llms","machine-learning","nlp","transformers"],"archived":false,"github_pushed_at":"2026-09-04T19:22:27+00:00","maintenance_label":"Steady","url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning","markdown_url":"https://www.graphcanon.com/tools/curated-awesome-lists-awesome-llms-fine-tuning.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/curated-awesome-lists-awesome-llms-fine-tuning","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=curated-awesome-lists-awesome-llms-fine-tuning","shared_categories":[]},{"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","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","shared_categories":["evaluation-observability"]}]}}