Auto Daily Leaderboard udpate Tue Feb 4 12:00:33 PM EST 2025

arena_elo/results/20250203/clean_battle_video_generation.json

@@ -38190,5 +38190,159 @@
     "judge": "arena_user_10.16.39.39",
     "anony": true,
     "tstamp": 1738596567.1919
+  },
+  {
+    "model_a_conv_id": "7f1fe124cbc641eb946c47ad7feaa69f",
+    "model_b_conv_id": "5b3946702e37463785a1a93565f7e5c8",
+    "inputs": {
+      "prompt": "An astronaut is riding a horse in the space in a photorealistic style."
+    },
+    "model_a": "Mochi1",
+    "model_b": "Allegro",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.20.26.107",
+    "anony": true,
+    "tstamp": 1738614372.7043
+  },
+  {
+    "model_a_conv_id": "e10ac80a9c26475b9f455321bad58de3",
+    "model_b_conv_id": "e178fd55aa0d4e48ac49badf32362778",
+    "inputs": {
+      "prompt": "A corgi is playing drum kit."
+    },
+    "model_a": "OpenSora v1.2",
+    "model_b": "CogVideoX-5B",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.28.141",
+    "anony": true,
+    "tstamp": 1738642469.9318
+  },
+  {
+    "model_a_conv_id": "cd2fa919988f43b68bf098ef6694276a",
+    "model_b_conv_id": "1aa894f38cf2475baa7bca15ed50b0a8",
+    "inputs": {
+      "prompt": "skis"
+    },
+    "model_a": "VideoCrafter2",
+    "model_b": "OpenSora v1.2",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738642523.9283
+  },
+  {
+    "model_a_conv_id": "9774e63c5b4242fda9e73d9f0e9e2cf8",
+    "model_b_conv_id": "5c52392468c8431eac6014288f884d0e",
+    "inputs": {
+      "prompt": "industrial area"
+    },
+    "model_a": "CogVideoX-5B",
+    "model_b": "Pyramid Flow",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738642534.4746
+  },
+  {
+    "model_a_conv_id": "69d10955c8c7460e88f4189e6874e71b",
+    "model_b_conv_id": "c3a5ee9c72dc42d391b77b03e744b02c",
+    "inputs": {
+      "prompt": "A person is clay pottery making"
+    },
+    "model_a": "Allegro",
+    "model_b": "VideoCrafter2",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.28.141",
+    "anony": true,
+    "tstamp": 1738655201.1182
+  },
+  {
+    "model_a_conv_id": "d29433f6848547de984f22beaba4a1aa",
+    "model_b_conv_id": "c64542b9546e44c9abc160a396cf13ca",
+    "inputs": {
+      "prompt": "aquarium"
+    },
+    "model_a": "T2V-Turbo",
+    "model_b": "CogVideoX-2B",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.28.141",
+    "anony": true,
+    "tstamp": 1738655210.4853
+  },
+  {
+    "model_a_conv_id": "e07edd3d02974fc6b8f01070bb411dcd",
+    "model_b_conv_id": "ecd9815572084ac8889d5e2b965264bf",
+    "inputs": {
+      "prompt": "Balloon full of water exploding in extreme slow motion."
+    },
+    "model_a": "Allegro",
+    "model_b": "LTXVideo",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738655221.0722
+  },
+  {
+    "model_a_conv_id": "aedcfadceaf0493895be54c6af3431f8",
+    "model_b_conv_id": "97f87ebc7acb45e19082db0385613420",
+    "inputs": {
+      "prompt": "a car turning a corner"
+    },
+    "model_a": "StableVideoDiffusion",
+    "model_b": "CogVideoX-2B",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738655232.9495
+  },
+  {
+    "model_a_conv_id": "664e233461c2414ba6446c36d417d232",
+    "model_b_conv_id": "6b660c8a5d934707949e5a5c11eff3ad",
+    "inputs": {
+      "prompt": "A person is throwing axe"
+    },
+    "model_a": "OpenSora v1.2",
+    "model_b": "T2V-Turbo",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.11.122",
+    "anony": true,
+    "tstamp": 1738655240.7106
+  },
+  {
+    "model_a_conv_id": "3b241ab105b9422bac7a352af20980a7",
+    "model_b_conv_id": "cd1df389a009458db6547b961762e256",
+    "inputs": {
+      "prompt": "marsh"
+    },
+    "model_a": "Allegro",
+    "model_b": "Mochi1",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.11.122",
+    "anony": true,
+    "tstamp": 1738655255.5175
+  },
+  {
+    "model_a_conv_id": "c3f937ad130c4b61abc628c069f56f8b",
+    "model_b_conv_id": "18ac5cd8431d42f39be1c5737a90cb59",
+    "inputs": {
+      "prompt": "a black cat"
+    },
+    "model_a": "OpenSora v1.2",
+    "model_b": "LTXVideo",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738655265.604
   }
 ]

arena_elo/results/20250203/elo_results_video_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138aa413ae0ba8a8397dffc8a6621d219c1575dd52ce435da5ef26e0bc262662
+oid sha256:e44c2ce3391d2cb7050d2dfbdfbd5e61ad73afe9f22af70f5bd601814af17bf6
 size 81355

arena_elo/results/20250203/video_generation_leaderboard.csv

@@ -1,16 +1,16 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-CogVideoX-5B,CogVideoX-5B,1159.0092540900062,1161.5141173137115,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
-StableVideoDiffusion,StableVideoDiffusion,1119.1652382074892,1119.527497594042,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
-Mochi1,Mochi1,1115.980082684981,1116.9082110618078,Apache 2.0,Genmo AI,https://github.com/genmoai/mochi
-Pyramid Flow,Pyramid Flow,1102.364458412885,1105.4662168590303,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
-T2V-Turbo,T2V-Turbo,1058.7072089861442,1059.5148535686037,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
-CogVideoX-2B,CogVideoX-2B,1047.3032613974553,1045.0781276604075,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
-AnimateDiff,AnimateDiff,1039.3611881123752,1039.424966477947,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
-VideoCrafter2,VideoCrafter2,1033.018377281362,1032.492830226435,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
-Allegro,Allegro,991.5783056804162,994.6690648123182,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
-LaVie,LaVie,966.1720991055984,965.7429886883857,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
-LTXVideo,LTXVideo,962.6480235258392,959.4524617654159,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
-OpenSora,OpenSora,882.5438844181672,881.8180482895958,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
-OpenSora v1.2,OpenSora v1.2,853.4604339888641,851.0529393668876,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
-AnimateDiff Turbo,AnimateDiff Turbo,836.2739327164926,834.1335349860783,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
-ModelScope,ModelScope,832.4142513919255,833.2041413293301,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571
+CogVideoX-5B,CogVideoX-5B,1148.2924349094344,1151.3236278632826,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+StableVideoDiffusion,StableVideoDiffusion,1116.9654859853856,1117.3374851265503,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
+Mochi1,Mochi1,1115.339963202651,1116.5692965982148,Apache 2.0,Genmo AI,https://github.com/genmoai/mochi
+Pyramid Flow,Pyramid Flow,1105.2448539154002,1108.3426500242144,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
+T2V-Turbo,T2V-Turbo,1055.1481558969674,1055.7410428844169,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
+CogVideoX-2B,CogVideoX-2B,1051.2453356705832,1049.3244271532658,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+AnimateDiff,AnimateDiff,1038.0230568271697,1038.066664050456,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
+VideoCrafter2,VideoCrafter2,1031.305575335464,1030.9364567062719,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
+Allegro,Allegro,993.8964798932992,997.6337114129967,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
+LTXVideo,LTXVideo,976.1234605002693,970.5638661885408,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
+LaVie,LaVie,964.4024518217399,964.1594080964936,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
+OpenSora,OpenSora,880.8750769535598,880.2789171612135,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+OpenSora v1.2,OpenSora v1.2,857.3897352585354,855.1968063290503,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+AnimateDiff Turbo,AnimateDiff Turbo,834.9025592439705,832.8804580006795,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
+ModelScope,ModelScope,830.8453745855696,831.6451824043493,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571

arena_elo/results/latest/clean_battle_video_generation.json

@@ -38190,5 +38190,159 @@
     "judge": "arena_user_10.16.39.39",
     "anony": true,
     "tstamp": 1738596567.1919
+  },
+  {
+    "model_a_conv_id": "7f1fe124cbc641eb946c47ad7feaa69f",
+    "model_b_conv_id": "5b3946702e37463785a1a93565f7e5c8",
+    "inputs": {
+      "prompt": "An astronaut is riding a horse in the space in a photorealistic style."
+    },
+    "model_a": "Mochi1",
+    "model_b": "Allegro",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.20.26.107",
+    "anony": true,
+    "tstamp": 1738614372.7043
+  },
+  {
+    "model_a_conv_id": "e10ac80a9c26475b9f455321bad58de3",
+    "model_b_conv_id": "e178fd55aa0d4e48ac49badf32362778",
+    "inputs": {
+      "prompt": "A corgi is playing drum kit."
+    },
+    "model_a": "OpenSora v1.2",
+    "model_b": "CogVideoX-5B",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.28.141",
+    "anony": true,
+    "tstamp": 1738642469.9318
+  },
+  {
+    "model_a_conv_id": "cd2fa919988f43b68bf098ef6694276a",
+    "model_b_conv_id": "1aa894f38cf2475baa7bca15ed50b0a8",
+    "inputs": {
+      "prompt": "skis"
+    },
+    "model_a": "VideoCrafter2",
+    "model_b": "OpenSora v1.2",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738642523.9283
+  },
+  {
+    "model_a_conv_id": "9774e63c5b4242fda9e73d9f0e9e2cf8",
+    "model_b_conv_id": "5c52392468c8431eac6014288f884d0e",
+    "inputs": {
+      "prompt": "industrial area"
+    },
+    "model_a": "CogVideoX-5B",
+    "model_b": "Pyramid Flow",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738642534.4746
+  },
+  {
+    "model_a_conv_id": "69d10955c8c7460e88f4189e6874e71b",
+    "model_b_conv_id": "c3a5ee9c72dc42d391b77b03e744b02c",
+    "inputs": {
+      "prompt": "A person is clay pottery making"
+    },
+    "model_a": "Allegro",
+    "model_b": "VideoCrafter2",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.28.141",
+    "anony": true,
+    "tstamp": 1738655201.1182
+  },
+  {
+    "model_a_conv_id": "d29433f6848547de984f22beaba4a1aa",
+    "model_b_conv_id": "c64542b9546e44c9abc160a396cf13ca",
+    "inputs": {
+      "prompt": "aquarium"
+    },
+    "model_a": "T2V-Turbo",
+    "model_b": "CogVideoX-2B",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.28.141",
+    "anony": true,
+    "tstamp": 1738655210.4853
+  },
+  {
+    "model_a_conv_id": "e07edd3d02974fc6b8f01070bb411dcd",
+    "model_b_conv_id": "ecd9815572084ac8889d5e2b965264bf",
+    "inputs": {
+      "prompt": "Balloon full of water exploding in extreme slow motion."
+    },
+    "model_a": "Allegro",
+    "model_b": "LTXVideo",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738655221.0722
+  },
+  {
+    "model_a_conv_id": "aedcfadceaf0493895be54c6af3431f8",
+    "model_b_conv_id": "97f87ebc7acb45e19082db0385613420",
+    "inputs": {
+      "prompt": "a car turning a corner"
+    },
+    "model_a": "StableVideoDiffusion",
+    "model_b": "CogVideoX-2B",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738655232.9495
+  },
+  {
+    "model_a_conv_id": "664e233461c2414ba6446c36d417d232",
+    "model_b_conv_id": "6b660c8a5d934707949e5a5c11eff3ad",
+    "inputs": {
+      "prompt": "A person is throwing axe"
+    },
+    "model_a": "OpenSora v1.2",
+    "model_b": "T2V-Turbo",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.11.122",
+    "anony": true,
+    "tstamp": 1738655240.7106
+  },
+  {
+    "model_a_conv_id": "3b241ab105b9422bac7a352af20980a7",
+    "model_b_conv_id": "cd1df389a009458db6547b961762e256",
+    "inputs": {
+      "prompt": "marsh"
+    },
+    "model_a": "Allegro",
+    "model_b": "Mochi1",
+    "vote_type": "leftvote",
+    "winner": "model_a",
+    "judge": "arena_user_10.16.11.122",
+    "anony": true,
+    "tstamp": 1738655255.5175
+  },
+  {
+    "model_a_conv_id": "c3f937ad130c4b61abc628c069f56f8b",
+    "model_b_conv_id": "18ac5cd8431d42f39be1c5737a90cb59",
+    "inputs": {
+      "prompt": "a black cat"
+    },
+    "model_a": "OpenSora v1.2",
+    "model_b": "LTXVideo",
+    "vote_type": "rightvote",
+    "winner": "model_b",
+    "judge": "arena_user_10.16.39.39",
+    "anony": true,
+    "tstamp": 1738655265.604
   }
 ]

arena_elo/results/latest/elo_results_video_generation.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138aa413ae0ba8a8397dffc8a6621d219c1575dd52ce435da5ef26e0bc262662
+oid sha256:e44c2ce3391d2cb7050d2dfbdfbd5e61ad73afe9f22af70f5bd601814af17bf6
 size 81355

arena_elo/results/latest/video_generation_leaderboard.csv

@@ -1,16 +1,16 @@
 key,Model,Arena Elo rating (anony),Arena Elo rating (full),License,Organization,Link
-CogVideoX-5B,CogVideoX-5B,1159.0092540900062,1161.5141173137115,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
-StableVideoDiffusion,StableVideoDiffusion,1119.1652382074892,1119.527497594042,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
-Mochi1,Mochi1,1115.980082684981,1116.9082110618078,Apache 2.0,Genmo AI,https://github.com/genmoai/mochi
-Pyramid Flow,Pyramid Flow,1102.364458412885,1105.4662168590303,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
-T2V-Turbo,T2V-Turbo,1058.7072089861442,1059.5148535686037,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
-CogVideoX-2B,CogVideoX-2B,1047.3032613974553,1045.0781276604075,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
-AnimateDiff,AnimateDiff,1039.3611881123752,1039.424966477947,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
-VideoCrafter2,VideoCrafter2,1033.018377281362,1032.492830226435,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
-Allegro,Allegro,991.5783056804162,994.6690648123182,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
-LaVie,LaVie,966.1720991055984,965.7429886883857,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
-LTXVideo,LTXVideo,962.6480235258392,959.4524617654159,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
-OpenSora,OpenSora,882.5438844181672,881.8180482895958,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
-OpenSora v1.2,OpenSora v1.2,853.4604339888641,851.0529393668876,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
-AnimateDiff Turbo,AnimateDiff Turbo,836.2739327164926,834.1335349860783,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
-ModelScope,ModelScope,832.4142513919255,833.2041413293301,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571
+CogVideoX-5B,CogVideoX-5B,1148.2924349094344,1151.3236278632826,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+StableVideoDiffusion,StableVideoDiffusion,1116.9654859853856,1117.3374851265503,SVD-nc-community,Stability AI,https://fal.ai/models/fal-ai/fast-svd/text-to-video/api
+Mochi1,Mochi1,1115.339963202651,1116.5692965982148,Apache 2.0,Genmo AI,https://github.com/genmoai/mochi
+Pyramid Flow,Pyramid Flow,1105.2448539154002,1108.3426500242144,MIT LICENSE,Peking University,https://pyramid-flow.github.io/
+T2V-Turbo,T2V-Turbo,1055.1481558969674,1055.7410428844169,cc-by-nc-4.0,"University of California, Santa Barbara",https://github.com/Ji4chenLi/t2v-turbo
+CogVideoX-2B,CogVideoX-2B,1051.2453356705832,1049.3244271532658,CogVideoX LICENSE,THUDM,https://github.com/THUDM/CogVideo
+AnimateDiff,AnimateDiff,1038.0230568271697,1038.066664050456,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v
+VideoCrafter2,VideoCrafter2,1031.305575335464,1030.9364567062719,Apache 2.0,Tencent AI Lab,https://ailab-cvc.github.io/videocrafter2/
+Allegro,Allegro,993.8964798932992,997.6337114129967,Apache 2.0,rhymes-ai,https://github.com/rhymes-ai/Allegro
+LTXVideo,LTXVideo,976.1234605002693,970.5638661885408,Apache 2.0,Lightricks,https://github.com/Lightricks/LTX-Video
+LaVie,LaVie,964.4024518217399,964.1594080964936,Apache 2.0,Shanghai AI Lab,https://github.com/Vchitect/LaVie
+OpenSora,OpenSora,880.8750769535598,880.2789171612135,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+OpenSora v1.2,OpenSora v1.2,857.3897352585354,855.1968063290503,Apache 2.0,HPC-AI Tech,https://github.com/hpcaitech/Open-Sora
+AnimateDiff Turbo,AnimateDiff Turbo,834.9025592439705,832.8804580006795,creativeml-openrail-m,"The Chinese University of Hong Kong, Shanghai AI Lab, Stanford University",https://fal.ai/models/fast-animatediff-t2v-turbo
+ModelScope,ModelScope,830.8453745855696,831.6451824043493,cc-by-nc-4.0,Alibaba Group,https://arxiv.org/abs/2308.06571