{"id":683,"date":"2023-12-05T23:11:25","date_gmt":"2023-12-05T23:11:25","guid":{"rendered":"https:\/\/aigender.net\/?p=683"},"modified":"2023-12-05T23:11:26","modified_gmt":"2023-12-05T23:11:26","slug":"chatbot-arena-leaderboard","status":"publish","type":"post","link":"https:\/\/aigender.net\/index.php\/2023\/12\/05\/chatbot-arena-leaderboard\/","title":{"rendered":"Chatbot Arena Leaderboard"},"content":{"rendered":"\n<h1 class=\"wp-block-heading\">\ud83c\udfc6 Chatbot Arena Leaderboard<\/h1>\n\n\n\n<p>|&nbsp;<a href=\"https:\/\/lmsys.org\/blog\/2023-05-03-arena\/\" target=\"_blank\" rel=\"noreferrer noopener\">Blog<\/a>&nbsp;|&nbsp;<a href=\"https:\/\/github.com\/lm-sys\/FastChat\" target=\"_blank\" rel=\"noreferrer noopener\">GitHub<\/a>&nbsp;|&nbsp;<a href=\"https:\/\/arxiv.org\/abs\/2306.05685\" target=\"_blank\" rel=\"noreferrer noopener\">Paper<\/a>&nbsp;|&nbsp;<a href=\"https:\/\/github.com\/lm-sys\/FastChat\/blob\/main\/docs\/dataset_release.md\" target=\"_blank\" rel=\"noreferrer noopener\">Dataset<\/a>&nbsp;|&nbsp;<a href=\"https:\/\/twitter.com\/lmsysorg\" target=\"_blank\" rel=\"noreferrer noopener\">Twitter<\/a>&nbsp;|&nbsp;<a href=\"https:\/\/discord.gg\/HSWAKCrnFx\" target=\"_blank\" rel=\"noreferrer noopener\">Discord<\/a>&nbsp;|<\/p>\n\n\n\n<p>This leaderboard is based on the following three benchmarks.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/lmsys.org\/blog\/2023-05-03-arena\/\" target=\"_blank\" rel=\"noreferrer noopener\">Chatbot Arena<\/a>&nbsp;&#8211; a crowdsourced, randomized battle platform. We use 100K+ user votes to compute Elo ratings.<\/li>\n\n\n\n<li><a href=\"https:\/\/arxiv.org\/abs\/2306.05685\" target=\"_blank\" rel=\"noreferrer noopener\">MT-Bench<\/a>&nbsp;&#8211; a set of challenging multi-turn questions. We use GPT-4 to grade the model responses.<\/li>\n\n\n\n<li><a href=\"https:\/\/arxiv.org\/abs\/2009.03300\" target=\"_blank\" rel=\"noreferrer noopener\">MMLU<\/a>&nbsp;(5-shot) &#8211; a test to measure a model\u2019s multitask accuracy on 57 tasks.<\/li>\n<\/ul>\n\n\n\n<p>\ud83d\udcbb Code: The Arena Elo ratings are computed by this&nbsp;<a href=\"https:\/\/colab.research.google.com\/drive\/1RAWb22-PFNI-X1gPVzc927SGUdfr6nsR?usp=sharing\" target=\"_blank\" rel=\"noreferrer noopener\">notebook<\/a>. The MT-bench scores (single-answer grading on a scale of 10) are computed by&nbsp;<a href=\"https:\/\/github.com\/lm-sys\/FastChat\/tree\/main\/fastchat\/llm_judge\" target=\"_blank\" rel=\"noreferrer noopener\">fastchat.llm_judge<\/a>. The MMLU scores are mostly computed by&nbsp;<a href=\"https:\/\/github.com\/declare-lab\/instruct-eval\" target=\"_blank\" rel=\"noreferrer noopener\">InstructEval<\/a>. Higher values are better for all benchmarks. Empty cells mean not available. Last updated: November, 2023.<\/p>\n\n\n\n<figure class=\"wp-block-table\"><table><thead><tr><th>Model<\/th><th>\u2b50 Arena Elo rating<\/th><th>\ud83d\udcc8 MT-bench (score)<\/th><th>MMLU<\/th><th>License<\/th><\/tr><\/thead><tbody><tr><td><a target=\"_blank\" href=\"https:\/\/openai.com\/blog\/new-models-and-developer-products-announced-at-devday\" rel=\"noreferrer noopener\">GPT-4-Turbo<\/a><\/td><td>1210<\/td><td>9.32<\/td><td><\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/openai.com\/research\/gpt-4\" rel=\"noreferrer noopener\">GPT-4<\/a><\/td><td>1159<\/td><td>8.99<\/td><td>86.4<\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/www.anthropic.com\/index\/introducing-claude\" rel=\"noreferrer noopener\">Claude-1<\/a><\/td><td>1146<\/td><td>7.9<\/td><td>77<\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/www.anthropic.com\/index\/claude-2\" rel=\"noreferrer noopener\">Claude-2<\/a><\/td><td>1125<\/td><td>8.06<\/td><td>78.5<\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/www.anthropic.com\/index\/introducing-claude\" rel=\"noreferrer noopener\">Claude-instant-1<\/a><\/td><td>1106<\/td><td>7.85<\/td><td>73.4<\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/openai.com\/blog\/chatgpt\" rel=\"noreferrer noopener\">GPT-3.5-turbo<\/a><\/td><td>1103<\/td><td>7.94<\/td><td>70<\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/WizardLM\/WizardLM-70B-V1.0\" rel=\"noreferrer noopener\">WizardLM-70b-v1.0<\/a><\/td><td>1093<\/td><td>7.71<\/td><td>63.7<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/lmsys\/vicuna-33b-v1.3\" rel=\"noreferrer noopener\">Vicuna-33B<\/a><\/td><td>1090<\/td><td>7.12<\/td><td>59.2<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/openchat\/openchat_3.5\" rel=\"noreferrer noopener\">OpenChat-3.5<\/a><\/td><td>1070<\/td><td>7.81<\/td><td>64.3<\/td><td>Apache-2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/meta-llama\/Llama-2-70b-chat-hf\" rel=\"noreferrer noopener\">Llama-2-70b-chat<\/a><\/td><td>1065<\/td><td>6.86<\/td><td>63<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/WizardLM\/WizardLM-13B-V1.2\" rel=\"noreferrer noopener\">WizardLM-13b-v1.2<\/a><\/td><td>1047<\/td><td>7.2<\/td><td>52.7<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/HuggingFaceH4\/zephyr-7b-beta\" rel=\"noreferrer noopener\">zephyr-7b-beta<\/a><\/td><td>1042<\/td><td>7.34<\/td><td>61.4<\/td><td>MIT<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/mosaicml\/mpt-30b-chat\" rel=\"noreferrer noopener\">MPT-30B-chat<\/a><\/td><td>1031<\/td><td>6.39<\/td><td>50.4<\/td><td>CC-BY-NC-SA-4.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/lmsys\/vicuna-13b-v1.5\" rel=\"noreferrer noopener\">Vicuna-13B<\/a><\/td><td>1031<\/td><td>6.57<\/td><td>55.8<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/Qwen\/Qwen-14B-Chat\" rel=\"noreferrer noopener\">QWen-Chat-14B<\/a><\/td><td>1030<\/td><td>6.96<\/td><td>66.5<\/td><td>Qianwen LICENSE<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/tiiuae\/falcon-180B-chat\" rel=\"noreferrer noopener\">falcon-180b-chat<\/a><\/td><td>1024<\/td><td><\/td><td>68<\/td><td>Falcon-180B TII License<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/HuggingFaceH4\/zephyr-7b-alpha\" rel=\"noreferrer noopener\">zephyr-7b-alpha<\/a><\/td><td>1024<\/td><td>6.88<\/td><td><\/td><td>MIT<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/codellama\/CodeLlama-34b-Instruct-hf\" rel=\"noreferrer noopener\">CodeLlama-34B-instruct<\/a><\/td><td>1022<\/td><td><\/td><td>53.7<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/timdettmers\/guanaco-33b-merged\" rel=\"noreferrer noopener\">Guanaco-33B<\/a><\/td><td>1021<\/td><td>6.53<\/td><td>57.6<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/meta-llama\/Llama-2-13b-chat-hf\" rel=\"noreferrer noopener\">Llama-2-13b-chat<\/a><\/td><td>1021<\/td><td>6.65<\/td><td>53.6<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/mistralai\/Mistral-7B-Instruct-v0.1\" rel=\"noreferrer noopener\">Mistral-7B-Instruct-v0.1<\/a><\/td><td>1008<\/td><td>6.84<\/td><td>55.4<\/td><td>Apache 2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/meta-llama\/Llama-2-7b-chat-hf\" rel=\"noreferrer noopener\">Llama-2-7b-chat<\/a><\/td><td>1001<\/td><td>6.27<\/td><td>45.8<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/lmsys\/vicuna-7b-v1.5\" rel=\"noreferrer noopener\">Vicuna-7B<\/a><\/td><td>994<\/td><td>6.17<\/td><td>49.8<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/cloud.google.com\/vertex-ai\/docs\/generative-ai\/learn\/models#foundation_models\" rel=\"noreferrer noopener\">PaLM-Chat-Bison-001<\/a><\/td><td>991<\/td><td>6.4<\/td><td><\/td><td>Proprietary<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/THUDM\/chatglm3-6b\" rel=\"noreferrer noopener\">ChatGLM3-6B<\/a><\/td><td>970<\/td><td><\/td><td><\/td><td>Apache-2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/bair.berkeley.edu\/blog\/2023\/04\/03\/koala\/\" rel=\"noreferrer noopener\">Koala-13B<\/a><\/td><td>955<\/td><td>5.35<\/td><td>44.7<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/nomic-ai\/gpt4all-13b-snoozy\" rel=\"noreferrer noopener\">GPT4All-13B-Snoozy<\/a><\/td><td>925<\/td><td>5.41<\/td><td>43<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/mosaicml\/mpt-7b-chat\" rel=\"noreferrer noopener\">MPT-7B-Chat<\/a><\/td><td>918<\/td><td>5.42<\/td><td>32<\/td><td>CC-BY-NC-SA-4.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/THUDM\/chatglm2-6b\" rel=\"noreferrer noopener\">ChatGLM2-6B<\/a><\/td><td>918<\/td><td>4.96<\/td><td>45.5<\/td><td>Apache-2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/BlinkDL\/rwkv-4-raven\" rel=\"noreferrer noopener\">RWKV-4-Raven-14B<\/a><\/td><td>915<\/td><td>3.98<\/td><td>25.6<\/td><td>Apache 2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/crfm.stanford.edu\/2023\/03\/13\/alpaca.html\" rel=\"noreferrer noopener\">Alpaca-13B<\/a><\/td><td>893<\/td><td>4.53<\/td><td>48.1<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/OpenAssistant\/oasst-sft-4-pythia-12b-epoch-3.5\" rel=\"noreferrer noopener\">OpenAssistant-Pythia-12B<\/a><\/td><td>884<\/td><td>4.32<\/td><td>27<\/td><td>Apache 2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/THUDM\/chatglm-6b\" rel=\"noreferrer noopener\">ChatGLM-6B<\/a><\/td><td>871<\/td><td>4.5<\/td><td>36.1<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/lmsys\/fastchat-t5-3b-v1.0\" rel=\"noreferrer noopener\">FastChat-T5-3B<\/a><\/td><td>863<\/td><td>3.04<\/td><td>47.7<\/td><td>Apache 2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/stabilityai\/stablelm-tuned-alpha-7b\" rel=\"noreferrer noopener\">StableLM-Tuned-Alpha-7B<\/a><\/td><td>833<\/td><td>2.75<\/td><td>24.4<\/td><td>CC-BY-NC-SA-4.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/databricks\/dolly-v2-12b\" rel=\"noreferrer noopener\">Dolly-V2-12B<\/a><\/td><td>810<\/td><td>3.28<\/td><td>25.7<\/td><td>MIT<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/arxiv.org\/abs\/2302.13971\" rel=\"noreferrer noopener\">LLaMA-13B<\/a><\/td><td>789<\/td><td>2.61<\/td><td>47<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/WizardLM\/WizardLM-30B-V1.0\" rel=\"noreferrer noopener\">WizardLM-30B<\/a><\/td><td><\/td><td>7.01<\/td><td>58.7<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/lmsys\/vicuna-13b-v1.5-16k\" rel=\"noreferrer noopener\">Vicuna-13B-16k<\/a><\/td><td><\/td><td>6.92<\/td><td>54.5<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/WizardLM\/WizardLM-13B-V1.1\" rel=\"noreferrer noopener\">WizardLM-13B-v1.1<\/a><\/td><td><\/td><td>6.76<\/td><td>50<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/allenai\/tulu-30b\" rel=\"noreferrer noopener\">Tulu-30B<\/a><\/td><td><\/td><td>6.43<\/td><td>58.1<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/timdettmers\/guanaco-65b-merged\" rel=\"noreferrer noopener\">Guanaco-65B<\/a><\/td><td><\/td><td>6.41<\/td><td>62.1<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/OpenAssistant\/oasst-sft-6-llama-30b-xor\" rel=\"noreferrer noopener\">OpenAssistant-LLaMA-30B<\/a><\/td><td><\/td><td>6.41<\/td><td>56<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/WizardLM\/WizardLM-13B-V1.0\" rel=\"noreferrer noopener\">WizardLM-13B-v1.0<\/a><\/td><td><\/td><td>6.35<\/td><td>52.3<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/lmsys\/vicuna-7b-v1.5-16k\" rel=\"noreferrer noopener\">Vicuna-7B-16k<\/a><\/td><td><\/td><td>6.22<\/td><td>48.5<\/td><td>Llama 2 Community<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/project-baize\/baize-v2-13b\" rel=\"noreferrer noopener\">Baize-v2-13B<\/a><\/td><td><\/td><td>5.75<\/td><td>48.9<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/Salesforce\/xgen-7b-8k-inst\" rel=\"noreferrer noopener\">XGen-7B-8K-Inst<\/a><\/td><td><\/td><td>5.55<\/td><td>42.1<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/NousResearch\/Nous-Hermes-13b\" rel=\"noreferrer noopener\">Nous-Hermes-13B<\/a><\/td><td><\/td><td>5.51<\/td><td>49.3<\/td><td>Non-commercial<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/mosaicml\/mpt-30b-instruct\" rel=\"noreferrer noopener\">MPT-30B-Instruct<\/a><\/td><td><\/td><td>5.22<\/td><td>47.8<\/td><td>CC-BY-SA 3.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/tiiuae\/falcon-40b-instruct\" rel=\"noreferrer noopener\">Falcon-40B-Instruct<\/a><\/td><td><\/td><td>5.17<\/td><td>54.7<\/td><td>Apache 2.0<\/td><\/tr><tr><td><a target=\"_blank\" href=\"https:\/\/huggingface.co\/h2oai\/h2ogpt-gm-oasst1-en-2048-open-llama-13b\" rel=\"noreferrer noopener\">H2O-Oasst-OpenLLaMA-13B<\/a><\/td><td><\/td><td>4.63<\/td><td>42.8<\/td><td>Apache 2.0<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>New rowNew column<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Visit our&nbsp;<a href=\"https:\/\/huggingface.co\/spaces\/lmsys\/chatbot-arena-leaderboard\" target=\"_blank\" rel=\"noreferrer noopener\">HF space<\/a>&nbsp;for more analysis!<\/h2>\n\n\n\n<p>If you want to see more models, please help us&nbsp;<a href=\"https:\/\/github.com\/lm-sys\/FastChat\/blob\/main\/docs\/arena.md#how-to-add-a-new-model\" target=\"_blank\" rel=\"noreferrer noopener\">add them<\/a>.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Acknowledgment<\/h3>\n\n\n\n<p>We thank&nbsp;<a href=\"https:\/\/www.kaggle.com\/\" target=\"_blank\" rel=\"noreferrer noopener\">Kaggle<\/a>,&nbsp;<a href=\"https:\/\/mbzuai.ac.ae\/\" target=\"_blank\" rel=\"noreferrer noopener\">MBZUAI<\/a>,&nbsp;<a href=\"https:\/\/www.anyscale.com\/\" target=\"_blank\" rel=\"noreferrer noopener\">AnyScale<\/a>, and&nbsp;<a href=\"https:\/\/huggingface.co\/\" target=\"_blank\" rel=\"noreferrer noopener\">HuggingFace<\/a>&nbsp;for their generous&nbsp;<a href=\"https:\/\/lmsys.org\/donations\/\" target=\"_blank\" rel=\"noreferrer noopener\">sponsorship<\/a>.<img decoding=\"async\" src=\"https:\/\/upload.wikimedia.org\/wikipedia\/commons\/thumb\/7\/7c\/Kaggle_logo.png\/400px-Kaggle_logo.png\" alt=\"Image 1\"><img decoding=\"async\" src=\"https:\/\/mma.prnewswire.com\/media\/1227419\/MBZUAI_Logo.jpg?p=facebookg\" alt=\"Image 2\"><img decoding=\"async\" src=\"https:\/\/docs.anyscale.com\/site-assets\/logo.png\" alt=\"Image 3\"><img decoding=\"async\" src=\"https:\/\/huggingface.co\/datasets\/huggingface\/brand-assets\/resolve\/main\/hf-logo-with-title.png\" alt=\"Image 4\"><\/p>\n","protected":false},"excerpt":{"rendered":"<p>\ud83c\udfc6 Chatbot Arena Leaderboard |&nbsp;Blog&nbsp;|&nbsp;GitHub&nbsp;|&nbsp;Paper&nbsp;|&nbsp;Dataset&nbsp;|&nbsp;Twitter&nbsp;|&nbsp;Discord&nbsp;| This leaderboard is based on the following three benchmarks. \ud83d\udcbb Code: The Arena Elo ratings are computed by this&nbsp;notebook. The MT-bench scores (single-answer grading on a scale of 10) are computed by&nbsp;fastchat.llm_judge. The MMLU scores are mostly computed by&nbsp;InstructEval. Higher values are better for all benchmarks. Empty cells mean not [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":684,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_uf_show_specific_survey":0,"_uf_disable_surveys":false,"slim_seo":{"title":"Chatbot Arena Leaderboard - \u041a\u043e\u0440\u0438\u0441\u0442\u0435\u045a\u0435 \u043d\u0430 \u0432\u0435\u0448\u0442\u0430\u0447\u043a\u0430\u0442\u0430 \u0438\u043d\u0442\u0435\u043b\u0438\u0433\u0435\u043d\u0446\u0438\u0458\u0430 (AI) \u0437\u0430 \u0443\u043d\u0430\u043f\u0440\u0435\u0434\u0443\u0432\u0430\u045a\u0435 \u043d\u0430 \u0440\u043e\u0434\u043e\u0432\u0430\u0442\u0430 \u0435\u0434\u043d\u0430\u043a\u0432\u043e\u0441\u0442","description":"\ud83c\udfc6 Chatbot Arena Leaderboard |&nbsp; Blog &nbsp;|&nbsp; GitHub &nbsp;|&nbsp; Paper &nbsp;|&nbsp; Dataset &nbsp;|&nbsp; Twitter &nbsp;|&nbsp; Discord &nbsp;| This"},"footnotes":""},"categories":[1],"tags":[],"class_list":["post-683","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blog"],"_links":{"self":[{"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/posts\/683","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/comments?post=683"}],"version-history":[{"count":1,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/posts\/683\/revisions"}],"predecessor-version":[{"id":685,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/posts\/683\/revisions\/685"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/media\/684"}],"wp:attachment":[{"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/media?parent=683"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/categories?post=683"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aigender.net\/index.php\/wp-json\/wp\/v2\/tags?post=683"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}