Auto Daily Leaderboard udpate Tue Dec 17 12:00:27 PM EST 2024

arena_elo/results/20241217/elo_results_image_editing.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e1d6f99332e559b8fe5dd64bacb1608fd1d02a45bdeedc1629bfd586a3b28a9
+size 66025

arena_elo/results/20241217/elo_results_t2i_generation.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d1e9ffa4f8fd5e47dd582a00565679689d8cc4a3924e7f255de60e89d94c8ab
+size 88249

arena_elo/results/20241217/elo_results_video_generation.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc2212d2b435abe89fd71ee2c1d3f9645ec9e975f2b68d609e43aecc2b113b3c
+size 78092

arena_elo/results/20241217/image_editing_leaderboard.csv

@@ -0,0 +1,11 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+MagicBrush,MagicBrush,1096.5501389142828,1100.535668874469,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
+UltraEdit,UltraEdit,1078.207368746881,1078.310780184644,other,Peking University; BIGAI,https://ultra-editing.github.io/
+InfEdit,InfEdit,1062.673020683307,1062.4368154545516,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
+CosXLEdit,CosXLEdit,1057.1819230892963,1058.0740522243516,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
+InstructPix2Pix,InstructPix2Pix,1029.4457607977697,1027.2416877071903,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,991.4504847650438,995.8755710745041,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+Prompt2prompt,Prompt2prompt,982.5942581941629,983.6715745686438,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
+CycleDiffusion,CycleDiffusion,931.9295839148562,925.8794799990146,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
+SDEdit,SDEdit,917.6150732907784,916.0333998933401,MIT License,Stanford University,https://sde-image-editing.github.io
+Pix2PixZero,Pix2PixZero,852.3523876036224,851.940970019291,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/

arena_elo/results/20241217/t2i_generation_leaderboard.csv

@@ -0,0 +1,18 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+FLUX.1-dev,FLUX.1-dev,1120.72681797411,1126.1193230318042,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2.5,PlayGround V2.5,1116.3083326411318,1116.53716746647,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+FLUX.1-schnell,FLUX.1-schnell,1086.9585110392368,1094.1755206329317,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2,PlayGround V2,1073.2481409872314,1072.601807889633,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+Kolors,Kolors,1056.186278310027,1055.2828349010006,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
+StableCascade,StableCascade,1040.9561559499523,1043.675058378235,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
+HunyuanDiT,HunyuanDiT,1024.6241910256629,1018.6693378610773,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
+PixArtAlpha,PixArtAlpha,1020.3775932189805,1012.5349497097153,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+SDXL-Lightning,SDXL-Lightning,1019.9793957395989,1024.0247603469286,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtSigma,PixArtSigma,1018.2074762063806,1018.4478075433599,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
+SD3,SD3,1012.5895583414824,1014.9023319980238,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
+AuraFlow,AuraFlow,995.1836070265956,991.9865669290396,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
+SDXL,SDXL,968.2662569125246,968.9514430147594,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,915.2614647584617,913.5722864921754,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+LCM(v1.5/XL),LCM(v1.5/XL),905.994645416493,900.0497403031939,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
+OpenJourney,OpenJourney,833.5226965856435,828.5931803340982,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,791.608877866481,806.0496115528961,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7

arena_elo/results/20241217/video_generation_leaderboard.csv

@@ -0,0 +1,15 @@
+key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
+CogVideoX-5B,CogVideoX-5B,1154.6629006059775,1149.5622587142664,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+Pyramid Flow,Pyramid Flow,1144.9583803182713,1147.5202832580242,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
+StableVideoDiffusion,StableVideoDiffusion,1129.1433862497965,1131.3989040527151,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
+CogVideoX-2B,CogVideoX-2B,1073.5422607118333,1069.595748763826,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+T2V-Turbo,T2V-Turbo,1063.0471458680881,1062.8220193985985,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
+AnimateDiff,AnimateDiff,1047.8939269524324,1047.8477299178317,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
+VideoCrafter2,VideoCrafter2,1047.8122917029875,1048.2715851977966,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
+Allegro,Allegro,994.0746472106429,999.2774588811247,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
+LaVie,LaVie,975.5067613372935,975.684109319555,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
+LTXVideo,LTXVideo,939.0571715092387,940.3689134989127,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
+OpenSora,OpenSora,891.7792460781329,891.5608241965026,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+OpenSora v1.2,OpenSora v1.2,854.0813701244081,851.8577086699491,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+AnimateDiff Turbo,AnimateDiff Turbo,842.7666328703051,841.2774490400751,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
+ModelScope,ModelScope,841.6738784605934,842.9550070908244,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571

arena_elo/results/latest/clean_battle_image_editing.json

@@ -19912,5 +19912,165 @@
     "judge": "arena_user_10.16.30.109",
     "anony": true,
     "tstamp": 1734164709.0709
+  },
+  {
+    "model_a_conv_id": "e8b6eaa5aec546cd81c61cc5f1506744",
+    "model_b_conv_id": "3bac8fe27266456ebe051706fe0609d4",
+    "inputs": {
+      "source_prompt": "A red stop sign sitting on the side of a street.",
+      "target_prompt": "A red stop sign with Chinese writing sitting on the side of a street.",
+      "instruct_prompt": "Let the arabic writing be changed to Chinese."
+    },
+    "model_a": "InfEdit",
+    "model_b": "MagicBrush",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.19.14",
+    "anony": true,
+    "tstamp": 1734377362.9513
+  },
+  {
+    "model_a_conv_id": "1b6d202e5c9846f486f0f2b6ff5f19ca",
+    "model_b_conv_id": "e30bc80bc86b4065bd996c3eab3bee57",
+    "inputs": {
+      "source_prompt": "Man cutting into a pizza with a knife, covered with toppings.",
+      "target_prompt": "Man cutting into a pepperoni pizza with a knife, covered with toppings.",
+      "instruct_prompt": "make it a pepperoni pizza"
+    },
+    "model_a": "CycleDiffusion",
+    "model_b": "Pix2PixZero",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734377375.5701
+  },
+  {
+    "model_a_conv_id": "7b4bbd0eb3364db797422ce449aad3d0",
+    "model_b_conv_id": "62b942178a4049248615348744d2475e",
+    "inputs": {
+      "source_prompt": "A bed sitting in the corner of the room next to a wooden table.",
+      "target_prompt": "A wooden bed sitting in the corner of the room next to a wooden table.",
+      "instruct_prompt": "let the bed be wooden"
+    },
+    "model_a": "InstructPix2Pix",
+    "model_b": "UltraEdit",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.19.14",
+    "anony": true,
+    "tstamp": 1734377382.1764
+  },
+  {
+    "model_a_conv_id": "f15bf7a5e68c4747b00a8d1669c8c0a0",
+    "model_b_conv_id": "2fb82dc4048f4b6899717e5e0408b681",
+    "inputs": {
+      "source_prompt": "Blood oranges cut in half side by side on a cutting board.",
+      "target_prompt": "Apples cut in half side by side on a cutting board.",
+      "instruct_prompt": "Let the blood orange be swapped with an apple."
+    },
+    "model_a": "CycleDiffusion",
+    "model_b": "CosXLEdit",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.30.109",
+    "anony": true,
+    "tstamp": 1734377392.1431
+  },
+  {
+    "model_a_conv_id": "21a676fe36e2457d93e8757c83f40104",
+    "model_b_conv_id": "8e906b34774c4e9aa2bd35ef238d07c1",
+    "inputs": {
+      "source_prompt": "This truck is loaded with two freezers and tied down securely.",
+      "target_prompt": "This truck with open door is loaded with two freezers and tied down securely.",
+      "instruct_prompt": "open the door of the truck"
+    },
+    "model_a": "MagicBrush",
+    "model_b": "UltraEdit",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734377400.1233
+  },
+  {
+    "model_a_conv_id": "a5984a811c924dd3843a29c3dcd48160",
+    "model_b_conv_id": "725932376e944971bd9fc18fde0cf921",
+    "inputs": {
+      "source_prompt": "An empty kitchen filled with dishes and appliances, with a game show on TV.",
+      "target_prompt": "An empty kitchen with granite floors filled with dishes and appliances, with a game show on TV.",
+      "instruct_prompt": "let there be granite floor in the kitchen"
+    },
+    "model_a": "AURORA",
+    "model_b": "InstructPix2Pix",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.9.166",
+    "anony": true,
+    "tstamp": 1734377409.659
+  },
+  {
+    "model_a_conv_id": "3f35a99c009846f083f0ce153bbbd14f",
+    "model_b_conv_id": "fb28b90e96044de1939facf0d55f1eb6",
+    "inputs": {
+      "source_prompt": "a herd of cows stand on some tiled dirt",
+      "target_prompt": "A herd of cows and a dog stand on some tiled dirt.",
+      "instruct_prompt": "Let's add a dog next to the cows."
+    },
+    "model_a": "UltraEdit",
+    "model_b": "Pix2PixZero",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.39.228",
+    "anony": true,
+    "tstamp": 1734444475.8764
+  },
+  {
+    "model_a_conv_id": "aa7bb77379a34dc69091fa7a8193e848",
+    "model_b_conv_id": "aec471bffc42411ba1428e1c384b099c",
+    "inputs": {
+      "source_prompt": "A kitchen with white cabinets and white appliances.",
+      "target_prompt": "Kitchen with white cabinets, white appliances, and a wooden floor.",
+      "instruct_prompt": "Put a wooden floor on the kitchen."
+    },
+    "model_a": "AURORA",
+    "model_b": "Prompt2prompt",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.0.161",
+    "anony": true,
+    "tstamp": 1734444500.5458
+  },
+  {
+    "model_a_conv_id": "2b95806c15d2469aa4d87f287b55be97",
+    "model_b_conv_id": "7bf5a0a11e99410b824e870ae9feab74",
+    "inputs": {
+      "source_prompt": "Outdoor show with black sheep prominent on grass field.",
+      "target_prompt": "Outdoor show with a dog herding black sheep on a grass field.",
+      "instruct_prompt": "A dog should be near the sheep."
+    },
+    "model_a": "Pix2PixZero",
+    "model_b": "InstructPix2Pix",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.39.228",
+    "anony": true,
+    "tstamp": 1734444531.0161
+  },
+  {
+    "model_a_conv_id": "3af371c9f2f9468390e76e8384a1343d",
+    "model_b_conv_id": "4368b19f29df4cf481675e9fb12c5be9",
+    "inputs": {
+      "source_prompt": "a person that has a racket in hand",
+      "target_prompt": "A girl with a baseball bat in hand",
+      "instruct_prompt": "give the girl a baseball bat instead of a racket"
+    },
+    "model_a": "CycleDiffusion",
+    "model_b": "MagicBrush",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.39.228",
+    "anony": true,
+    "tstamp": 1734444563.0927
   }
 ]

arena_elo/results/latest/clean_battle_t2i_generation.json

@@ -112414,5 +112414,215 @@
     "judge": "arena_user_10.20.38.195",
     "anony": true,
     "tstamp": 1734365902.6282
+  },
+  {
+    "model_a_conv_id": "1473c85563b943dcaefb4138c7dd8179",
+    "model_b_conv_id": "4db2010aa7e34e2ea8ca74f433e06afa",
+    "inputs": {
+      "prompt": "A black colored banana."
+    },
+    "model_a": "HunyuanDiT",
+    "model_b": "PlayGround V2.5",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.9.166",
+    "anony": true,
+    "tstamp": 1734383738.5523
+  },
+  {
+    "model_a_conv_id": "c653066ea5b0425eafea28a3b9afdecb",
+    "model_b_conv_id": "1e5dcaea410b492da034aab64dc6ed2d",
+    "inputs": {
+      "prompt": "A vehicle composed of two wheels held in a frame one behind the other, propelled by pedals and steered with handlebars attached to the front wheel."
+    },
+    "model_a": "StableCascade",
+    "model_b": "AuraFlow",
+    "vote_type": "tievote",
+    "winner": "tie",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383765.6899
+  },
+  {
+    "model_a_conv_id": "e3cac69ee6f54a2098f7de9bdca37514",
+    "model_b_conv_id": "4a43c9eacd2842faa3d54eba73a85e17",
+    "inputs": {
+      "prompt": "A giraffe underneath a microwave."
+    },
+    "model_a": "SDXL",
+    "model_b": "StableCascade",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383776.1754
+  },
+  {
+    "model_a_conv_id": "e8254c2978604f95ac505fb21df98802",
+    "model_b_conv_id": "22229cbbe50b47e2a5436a8a80e2064f",
+    "inputs": {
+      "prompt": "Three traffic lights, one green, the other yellow, and one red."
+    },
+    "model_a": "FLUX.1-dev",
+    "model_b": "PixArtAlpha",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383790.2194
+  },
+  {
+    "model_a_conv_id": "8245d0aac4f740b082901c5065d0f176",
+    "model_b_conv_id": "67dc16bfd2e1413ca5e7e39b9dfdab57",
+    "inputs": {
+      "prompt": "One car on the street."
+    },
+    "model_a": "PixArtAlpha",
+    "model_b": "SDXLTurbo",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.19.14",
+    "anony": true,
+    "tstamp": 1734383813.7275
+  },
+  {
+    "model_a_conv_id": "1b13411afaec400697e322b6b4359aa5",
+    "model_b_conv_id": "88a8bf8299eb4094a16aff6cd289896a",
+    "inputs": {
+      "prompt": "A black and white picture of a busy street, only red is in color, a red double decker bus drives down the road."
+    },
+    "model_a": "OpenJourney",
+    "model_b": "StableCascade",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.38.196",
+    "anony": true,
+    "tstamp": 1734383829.8201
+  },
+  {
+    "model_a_conv_id": "00dc9161bfa242d485325b6e765a2a53",
+    "model_b_conv_id": "22db4476409a4ccdbd4a63bbf6165430",
+    "inputs": {
+      "prompt": "Buildings on fire, old film still"
+    },
+    "model_a": "AuraFlow",
+    "model_b": "FLUX.1-dev",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.38.196",
+    "anony": true,
+    "tstamp": 1734402713.6571
+  },
+  {
+    "model_a_conv_id": "e87222f4fe514b12accaae4f75701562",
+    "model_b_conv_id": "3fce5e80125545ca94f6447ec8f59a63",
+    "inputs": {
+      "prompt": "An elephant under the sea."
+    },
+    "model_a": "AuraFlow",
+    "model_b": "FLUX.1-schnell",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734423306.2512
+  },
+  {
+    "model_a_conv_id": "06f5c391c2fa42999ed323750ff0212b",
+    "model_b_conv_id": "1a514b20028542988cde20236a2b2d43",
+    "inputs": {
+      "prompt": "image of man watching computer screen"
+    },
+    "model_a": "FLUX.1-dev",
+    "model_b": "PixArtSigma",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.9.166",
+    "anony": true,
+    "tstamp": 1734423320.8151
+  },
+  {
+    "model_a_conv_id": "e61ce1b2b7e14aeca23b14253eb41a09",
+    "model_b_conv_id": "d1d3548a08144303b6c5ed4b6e1f5eac",
+    "inputs": {
+      "prompt": "A pink scooter with a black seat next to a blue car."
+    },
+    "model_a": "AuraFlow",
+    "model_b": "SDXL-Lightning",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.0.161",
+    "anony": true,
+    "tstamp": 1734423339.1564
+  },
+  {
+    "model_a_conv_id": "8ba2641367dc423ea74b809f3efa984a",
+    "model_b_conv_id": "3eb509504f734f29a437a0317e867e22",
+    "inputs": {
+      "prompt": "A pizza cooking an oven."
+    },
+    "model_a": "HunyuanDiT",
+    "model_b": "FLUX.1-schnell",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734423354.9366
+  },
+  {
+    "model_a_conv_id": "c07aa52b84c84903865e3508dc95ad29",
+    "model_b_conv_id": "ded5262d36e44852ac6b6824de1969d6",
+    "inputs": {
+      "prompt": "photorealistic, detailed picture of a single flower crown"
+    },
+    "model_a": "HunyuanDiT",
+    "model_b": "SDXL",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.9.166",
+    "anony": true,
+    "tstamp": 1734423377.4903
+  },
+  {
+    "model_a_conv_id": "59499e556ca54afe8f22d72da55984c0",
+    "model_b_conv_id": "ff5b97985cc742e2a8cf78d05de42b8f",
+    "inputs": {
+      "prompt": "A blue bunny in a pink water toilet bowl ."
+    },
+    "model_a": "OpenJourney",
+    "model_b": "PixArtSigma",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.0.161",
+    "anony": true,
+    "tstamp": 1734423386.0567
+  },
+  {
+    "model_a_conv_id": "ca7736066f8747ebb242e4e0267e987f",
+    "model_b_conv_id": "f116363ac433488a988c219916fce529",
+    "inputs": {
+      "prompt": "image of a cat holding up a bird on a wall. 8k, photoreal, sharp details, soft light."
+    },
+    "model_a": "AuraFlow",
+    "model_b": "SDXLTurbo",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.19.14",
+    "anony": true,
+    "tstamp": 1734423395.8237
+  },
+  {
+    "model_a_conv_id": "5ee72c0c2aa84c299737d473e88c841c",
+    "model_b_conv_id": "8275d92f53d349d08f4509b4cafeef03",
+    "inputs": {
+      "prompt": "KFC"
+    },
+    "model_a": "FLUX.1-dev",
+    "model_b": "AuraFlow",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734447254.0219
   }
 ]

arena_elo/results/latest/clean_battle_video_generation.json

@@ -34732,5 +34732,117 @@
     "judge": "arena_user_10.16.0.161",
     "anony": true,
     "tstamp": 1734257899.1009
+  },
+  {
+    "model_a_conv_id": "6173e486af8c428d9a848b0200cc7988",
+    "model_b_conv_id": "5d42cb7c5e2348c58f5a5b9c7f72bf83",
+    "inputs": {
+      "prompt": "a refrigerator and skis"
+    },
+    "model_a": "AnimateDiff Turbo",
+    "model_b": "StableVideoDiffusion",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383403.2416
+  },
+  {
+    "model_a_conv_id": "fe577415a3534f40ac0656dc89a56495",
+    "model_b_conv_id": "6232e4855afe42609c1c008d8d18a27b",
+    "inputs": {
+      "prompt": "cliff"
+    },
+    "model_a": "StableVideoDiffusion",
+    "model_b": "AnimateDiff Turbo",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383429.3962
+  },
+  {
+    "model_a_conv_id": "4bd8a776d9824b18886e8f6c571bdf4e",
+    "model_b_conv_id": "5f43914fbbac4d2c97a4e823b3c92228",
+    "inputs": {
+      "prompt": "a bottle on the left of a wine glass, front view"
+    },
+    "model_a": "AnimateDiff Turbo",
+    "model_b": "Pyramid Flow",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.38.196",
+    "anony": true,
+    "tstamp": 1734383446.7411
+  },
+  {
+    "model_a_conv_id": "3db167fdf3554290adbba86f121502a9",
+    "model_b_conv_id": "ed7d1fd3800c42a0ac22be7dab20440b",
+    "inputs": {
+      "prompt": "An astronaut is riding a horse in the space in a photorealistic style."
+    },
+    "model_a": "LTXVideo",
+    "model_b": "OpenSora v1.2",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383468.6587
+  },
+  {
+    "model_a_conv_id": "12fc8184fb924afcab619b75dacbebd0",
+    "model_b_conv_id": "5b668299fa4e44f9b2cba803a28c8bde",
+    "inputs": {
+      "prompt": "a horse bending down to drink water from a river"
+    },
+    "model_a": "Allegro",
+    "model_b": "Pyramid Flow",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.19.14",
+    "anony": true,
+    "tstamp": 1734383506.5533
+  },
+  {
+    "model_a_conv_id": "489629ea28084f82bc8a788bbb6a637c",
+    "model_b_conv_id": "115292f59db24996b622f8d997dd40b3",
+    "inputs": {
+      "prompt": "a shark is swimming in the ocean, surrealism style"
+    },
+    "model_a": "VideoCrafter2",
+    "model_b": "LTXVideo",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.36.80",
+    "anony": true,
+    "tstamp": 1734383529.6044
+  },
+  {
+    "model_a_conv_id": "b947a09c283d4e3e8f21e4883e20c2fe",
+    "model_b_conv_id": "966af288672342f285d5058e00a7a4f6",
+    "inputs": {
+      "prompt": "A future where humans have achieved teleportation technology"
+    },
+    "model_a": "Allegro",
+    "model_b": "OpenSora v1.2",
+    "vote_type": "bothbad_vote",
+    "winner": "tie (bothbad)",
+    "judge": "arena_user_10.16.9.166",
+    "anony": true,
+    "tstamp": 1734383559.4769
+  },
+  {
+    "model_a_conv_id": "35db8a04f4d94b7e9d0a5cec8d661162",
+    "model_b_conv_id": "b4eee2ec1f7c4e54aee6cc884a3de290",
+    "inputs": {
+      "prompt": "windmill"
+    },
+    "model_a": "LTXVideo",
+    "model_b": "AnimateDiff",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.19.14",
+    "anony": true,
+    "tstamp": 1734431254.7009
   }
 ]

arena_elo/results/latest/elo_results_image_editing.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2779d4f77f1acb0bbb07ea90ec1949fc18fd2d425be7d8d5b8b527bd747509
-size 66037
+oid sha256:1e1d6f99332e559b8fe5dd64bacb1608fd1d02a45bdeedc1629bfd586a3b28a9
+size 66025

arena_elo/results/latest/elo_results_t2i_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d685d29506772496dcce7f4f9016da81b7221b971c452d930e07fb78925542
+oid sha256:5d1e9ffa4f8fd5e47dd582a00565679689d8cc4a3924e7f255de60e89d94c8ab
 size 88249

arena_elo/results/latest/elo_results_video_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ba447bb5eb35662cdb14f916bce0f6c464d1ad129456987616a0ad472713b28
-size 78094
+oid sha256:fc2212d2b435abe89fd71ee2c1d3f9645ec9e975f2b68d609e43aecc2b113b3c
+size 78092

arena_elo/results/latest/image_editing_leaderboard.csv

@@ -1,11 +1,11 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-MagicBrush,MagicBrush,1099.0996763755525,1103.1215872001612,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
-InfEdit,InfEdit,1064.6019449726723,1064.3774900407097,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
-UltraEdit,UltraEdit,1060.1503413395278,1060.1905065159747,other,Peking University; BIGAI,https://ultra-editing.github.io/
-CosXLEdit,CosXLEdit,1059.3830956919942,1060.3055997153515,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
-InstructPix2Pix,InstructPix2Pix,1033.0044483215847,1030.7333617117044,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
-PNP,PNP,993.3129456050709,997.7510962932845,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
-Prompt2prompt,Prompt2prompt,984.5326550946988,985.5972292718918,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
-CycleDiffusion,CycleDiffusion,934.4204992615006,928.2622672606797,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
-SDEdit,SDEdit,919.3580391061955,917.7927783091117,MIT License,Stanford University,https://sde-image-editing.github.io
-Pix2PixZero,Pix2PixZero,852.1363542312026,851.8680836811307,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/
+MagicBrush,MagicBrush,1096.5501389142828,1100.535668874469,CC-BY-4.0,"The Ohio State University, University of Waterloo",https://osu-nlp-group.github.io/MagicBrush/
+UltraEdit,UltraEdit,1078.207368746881,1078.310780184644,other,Peking University; BIGAI,https://ultra-editing.github.io/
+InfEdit,InfEdit,1062.673020683307,1062.4368154545516,CC BY-NC-ND 4.0,"University of Michigan, University of California, Berkeley",https://sled-group.github.io/InfEdit/
+CosXLEdit,CosXLEdit,1057.1819230892963,1058.0740522243516,cosxl-nc-community,Stability AI,https://huggingface.co/stabilityai/cosxl
+InstructPix2Pix,InstructPix2Pix,1029.4457607977697,1027.2416877071903,"Copyright 2023 Timothy Brooks, Aleksander Holynski, Alexei A. Efros","University of California, Berkeley",https://www.timothybrooks.com/instruct-pix2pix
+PNP,PNP,991.4504847650438,995.8755710745041,-,Weizmann Institute of Science,https://github.com/MichalGeyer/plug-and-play
+Prompt2prompt,Prompt2prompt,982.5942581941629,983.6715745686438,Apache-2.0,"Google, Tel Aviv University",https://prompt-to-prompt.github.io/
+CycleDiffusion,CycleDiffusion,931.9295839148562,925.8794799990146,X11,Carnegie Mellon University,https://github.com/ChenWu98/cycle-diffusion?tab=readme-ov-file
+SDEdit,SDEdit,917.6150732907784,916.0333998933401,MIT License,Stanford University,https://sde-image-editing.github.io
+Pix2PixZero,Pix2PixZero,852.3523876036224,851.940970019291,MIT License,"Carnegie Mellon University, Adobe Research",https://pix2pixzero.github.io/

arena_elo/results/latest/t2i_generation_leaderboard.csv

@@ -1,18 +1,18 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-FLUX.1-dev,FLUX.1-dev,1119.4993507367947,1125.299955976572,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
-PlayGround V2.5,PlayGround V2.5,1116.1298675197368,1116.345330022557,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
-FLUX.1-schnell,FLUX.1-schnell,1086.1018753336898,1093.492770248625,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
-PlayGround V2,PlayGround V2,1073.4962732593763,1072.8426863653751,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
-Kolors,Kolors,1056.157372170429,1055.2775884874522,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
-StableCascade,StableCascade,1041.3946752377788,1044.0822703692152,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
-HunyuanDiT,HunyuanDiT,1024.3725774826057,1018.3631794518683,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
-PixArtAlpha,PixArtAlpha,1021.0400831062105,1013.1205631316938,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
-SDXL-Lightning,SDXL-Lightning,1019.8109493534727,1023.8815804744781,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
-PixArtSigma,PixArtSigma,1018.4526613676778,1018.68202713549,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
-SD3,SD3,1012.5636684222859,1014.8613506849476,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
-AuraFlow,AuraFlow,995.1375916500524,991.7705839234253,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
-SDXL,SDXL,968.607940081821,969.2635636525999,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
-SDXLTurbo,SDXLTurbo,915.3627794626428,913.6918015316766,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
-LCM(v1.5/XL),LCM(v1.5/XL),906.2347046850977,900.2677722324869,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
-OpenJourney,OpenJourney,833.7354103848717,828.79375484095,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
-LCM,LCM,791.9022197454514,806.3263451345621,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7
+FLUX.1-dev,FLUX.1-dev,1120.72681797411,1126.1193230318042,flux-1-dev-non-commercial-license (other),Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2.5,PlayGround V2.5,1116.3083326411318,1116.53716746647,Playground v2.5 Community License,Playground,https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic
+FLUX.1-schnell,FLUX.1-schnell,1086.9585110392368,1094.1755206329317,Apache-2.0,Black Forest Labs,https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
+PlayGround V2,PlayGround V2,1073.2481409872314,1072.601807889633,Playground v2 Community License,Playground,https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic
+Kolors,Kolors,1056.186278310027,1055.2828349010006,Apache-2.0,Kwai Kolors,https://huggingface.co/Kwai-Kolors/Kolors
+StableCascade,StableCascade,1040.9561559499523,1043.675058378235,stable-cascade-nc-community (other),Stability AI,https://fal.ai/models/stable-cascade/api
+HunyuanDiT,HunyuanDiT,1024.6241910256629,1018.6693378610773,tencent-hunyuan-community,Tencent,https://github.com/Tencent/HunyuanDiT
+PixArtAlpha,PixArtAlpha,1020.3775932189805,1012.5349497097153,openrail++,PixArt-alpha,https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS
+SDXL-Lightning,SDXL-Lightning,1019.9793957395989,1024.0247603469286,openrail++,ByteDance,https://huggingface.co/ByteDance/SDXL-Lightning
+PixArtSigma,PixArtSigma,1018.2074762063806,1018.4478075433599,openrail++,PixArt-alpha,https://github.com/PixArt-alpha/PixArt-sigma
+SD3,SD3,1012.5895583414824,1014.9023319980238,stabilityai-nc-research-community,Stability AI,https://huggingface.co/blog/sd3
+AuraFlow,AuraFlow,995.1836070265956,991.9865669290396,Apache-2.0,Fal.AI,https://huggingface.co/fal/AuraFlow
+SDXL,SDXL,968.2662569125246,968.9514430147594,openrail++,Stability AI,https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0
+SDXLTurbo,SDXLTurbo,915.2614647584617,913.5722864921754,sai-nc-community (other),Stability AI,https://huggingface.co/stabilityai/sdxl-turbo
+LCM(v1.5/XL),LCM(v1.5/XL),905.994645416493,900.0497403031939,openrail++,Latent Consistency,https://fal.ai/models/fast-lcm-diffusion-turbo
+OpenJourney,OpenJourney,833.5226965856435,828.5931803340982,creativeml-openrail-m,PromptHero,https://huggingface.co/prompthero/openjourney
+LCM,LCM,791.608877866481,806.0496115528961,MIT License,Tsinghua University,https://huggingface.co/SimianLuo/LCM_Dreamshaper_v7

arena_elo/results/latest/video_generation_leaderboard.csv

@@ -1,15 +1,15 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-CogVideoX-5B,CogVideoX-5B,1155.1242487301374,1149.940196275879,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
-Pyramid Flow,Pyramid Flow,1146.4159682943312,1148.9251789763025,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
-StableVideoDiffusion,StableVideoDiffusion,1129.7970675880274,1132.0428122987362,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
-CogVideoX-2B,CogVideoX-2B,1074.103501022486,1070.026099029368,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
-T2V-Turbo,T2V-Turbo,1063.4084294886686,1063.1632366108738,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
-AnimateDiff,AnimateDiff,1048.818817477058,1048.6759453056034,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
-VideoCrafter2,VideoCrafter2,1047.6538437813047,1048.0826336644975,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
-Allegro,Allegro,999.6515680922292,1004.9362271276727,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
-LaVie,LaVie,975.7057528572167,975.8225276144419,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
-LTXVideo,LTXVideo,930.4497371812339,932.3534101906998,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
-OpenSora,OpenSora,891.9062117065749,891.6343023538814,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
-OpenSora v1.2,OpenSora v1.2,852.6848699181537,850.3899635877558,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
-AnimateDiff Turbo,AnimateDiff Turbo,842.4410069408768,840.939776792034,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
-ModelScope,ModelScope,841.838976921697,843.0676901722497,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571
+CogVideoX-5B,CogVideoX-5B,1154.6629006059775,1149.5622587142664,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+Pyramid Flow,Pyramid Flow,1144.9583803182713,1147.5202832580242,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
+StableVideoDiffusion,StableVideoDiffusion,1129.1433862497965,1131.3989040527151,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
+CogVideoX-2B,CogVideoX-2B,1073.5422607118333,1069.595748763826,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+T2V-Turbo,T2V-Turbo,1063.0471458680881,1062.8220193985985,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
+AnimateDiff,AnimateDiff,1047.8939269524324,1047.8477299178317,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
+VideoCrafter2,VideoCrafter2,1047.8122917029875,1048.2715851977966,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
+Allegro,Allegro,994.0746472106429,999.2774588811247,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
+LaVie,LaVie,975.5067613372935,975.684109319555,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
+LTXVideo,LTXVideo,939.0571715092387,940.3689134989127,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
+OpenSora,OpenSora,891.7792460781329,891.5608241965026,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+OpenSora v1.2,OpenSora v1.2,854.0813701244081,851.8577086699491,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+AnimateDiff Turbo,AnimateDiff Turbo,842.7666328703051,841.2774490400751,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
+ModelScope,ModelScope,841.6738784605934,842.9550070908244,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571