{"payload":{"pageCount":1,"repositories":[{"type":"Public","name":"opencompass","owner":"open-compass","isFork":false,"description":"OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.","allTopics":["benchmark","evaluation","openai","llm","chatgpt","large-language-model","llama2","llama3"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":18,"issueCount":101,"starsCount":2891,"forksCount":308,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-06-03T06:52:12.624Z"}},{"type":"Public","name":"ANAH","owner":"open-compass","isFork":false,"description":"[ACL 2024] ANAH: Analytical Annotation of Hallucinations in Large Language Models","allTopics":["acl","gpt","llms","hallucination-detection"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":7,"forksCount":0,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-31T20:08:32.079Z"}},{"type":"Public","name":"VLMEvalKit","owner":"open-compass","isFork":false,"description":"Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 50+ HF models, 20+ benchmarks","allTopics":["computer-vision","evaluation","pytorch","gemini","openai","vqa","vit","gpt","multi-modal","clip","claude","openai-api","gpt4","large-language-models","llm","chatgpt","llava","qwen","gpt-4v"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":3,"issueCount":13,"starsCount":508,"forksCount":59,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-31T08:28:02.003Z"}},{"type":"Public","name":".github","owner":"open-compass","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":1,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-31T02:27:09.928Z"}},{"type":"Public","name":"MathBench","owner":"open-compass","isFork":false,"description":"[ACL 2024 Findings] MathBench: A Comprehensive Multi-Level Difficulty Mathematics Evaluation Dataset","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":2,"starsCount":60,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-30T14:48:12.675Z"}},{"type":"Public","name":"DevBench","owner":"open-compass","isFork":false,"description":"A Comprehensive Benchmark for Software Development.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":73,"forksCount":4,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-30T13:10:52.870Z"}},{"type":"Public","name":"CodeBench","owner":"open-compass","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":0,"starsCount":1,"forksCount":0,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-05-21T11:38:31.710Z"}},{"type":"Public","name":"Ada-LEval","owner":"open-compass","isFork":false,"description":"The official implementation of \"Ada-LEval: Evaluating long-context LLMs with length-adaptable benchmarks\"","allTopics":["gpt4","llm","long-context"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":1,"starsCount":43,"forksCount":2,"license":null,"participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-22T09:36:27.993Z"}},{"type":"Public","name":"T-Eval","owner":"open-compass","isFork":false,"description":"[ACL2024] T-Eval: Evaluating Tool Utilization Capability of Large Language Models Step by Step","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":2,"issueCount":28,"starsCount":168,"forksCount":10,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-04-03T21:05:37.907Z"}},{"type":"Public","name":"human-eval","owner":"open-compass","isFork":true,"description":"Code for the paper \"Evaluating Large Language Models Trained on Code\"","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":2,"forksCount":303,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-14T11:55:53.553Z"}},{"type":"Public","name":"OpenFinData","owner":"open-compass","isFork":false,"description":"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":1,"starsCount":15,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-03-08T06:32:20.542Z"}},{"type":"Public","name":"CriticBench","owner":"open-compass","isFork":false,"description":"A comprehensive benchmark for evaluating critique ability of LLMs","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":21,"forksCount":1,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-02-24T01:31:08.418Z"}},{"type":"Public","name":"code-evaluator","owner":"open-compass","isFork":false,"description":"A multi-language code evaluation tool.","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":1,"issueCount":0,"starsCount":16,"forksCount":6,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-26T04:12:27.117Z"}},{"type":"Public","name":"MMBench","owner":"open-compass","isFork":false,"description":"Official Repo of \"MMBench: Is Your Multi-modal Model an All-around Player?\"","allTopics":[],"primaryLanguage":null,"pullRequestCount":0,"issueCount":8,"starsCount":103,"forksCount":5,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2024-01-08T09:59:44.556Z"}},{"type":"Public","name":"evalplus","owner":"open-compass","isFork":true,"description":"EvalPlus for rigourous evaluation of LLM-synthesized code","allTopics":[],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":83,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-20T08:13:21.996Z"}},{"type":"Public","name":"MixtralKit","owner":"open-compass","isFork":false,"description":"A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI","allTopics":["moe","mistral","llm"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":12,"starsCount":760,"forksCount":81,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-12-15T19:10:55.603Z"}},{"type":"Public","name":"LawBench","owner":"open-compass","isFork":false,"description":"Benchmarking Legal Knowledge of Large Language Models","allTopics":["law","benchmark","llm","chatgpt"],"primaryLanguage":{"name":"Python","color":"#3572A5"},"pullRequestCount":0,"issueCount":4,"starsCount":190,"forksCount":27,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-13T06:42:45.191Z"}},{"type":"Public","name":"BotChat","owner":"open-compass","isFork":false,"description":"Evaluating LLMs' multi-round chatting capability via assessing conversations generated by two LLM instances.","allTopics":[],"primaryLanguage":{"name":"Jupyter Notebook","color":"#DA5B0B"},"pullRequestCount":0,"issueCount":1,"starsCount":104,"forksCount":5,"license":"Apache License 2.0","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-11-02T12:38:19.203Z"}},{"type":"Public","name":"pytorch_sphinx_theme","owner":"open-compass","isFork":true,"description":"Sphinx Theme for OpenCompass - Modified from PyTorch","allTopics":[],"primaryLanguage":{"name":"CSS","color":"#563d7c"},"pullRequestCount":0,"issueCount":0,"starsCount":0,"forksCount":129,"license":"MIT License","participation":null,"lastUpdated":{"hasBeenPushedTo":true,"timestamp":"2023-08-30T04:20:35.062Z"}}],"repositoryCount":19,"userInfo":null,"searchable":true,"definitions":[],"typeFilters":[{"id":"all","text":"All"},{"id":"public","text":"Public"},{"id":"source","text":"Sources"},{"id":"fork","text":"Forks"},{"id":"archived","text":"Archived"},{"id":"template","text":"Templates"}],"compactMode":false},"title":"Repositories"}