Text to Video Leaderboard (With Audio)Artificial Analysis
Agnes-Video-V2.0, SkyReels V4
Range | Creator | Model | Elo | 95% CI | Samples | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 1-2 |  Alibaba-ATH | HappyHorse-1.0 | 1,213 | -10/10 | 7,612 | Apr 2026 | Coming soon |
| 2 | 1-2 |  ByteDance Seed | Dreamina Seedance 2.0 720p | 1,212 | -9/9 | 8,580 | Mar 2026 | No API available |
| 3 | 3-4 |  Skywork AI | SkyReels V4 | 1,110 | -11/11 | 2,265 | Mar 2026 | $21.00 /min |
| 4 | 3-7 |  KlingAI | Kling 3.0 1080p (Pro) | 1,103 | -9/9 | 6,272 | Feb 2026 | $20.16 /min |
| 5 | 4-9 | KlingAI | Kling 3.0 Omni 1080p (Pro) | 1,097 | -9/9 | 6,013 | Feb 2026 | $16.80 /min |
| 6 | 4-10 | KlingAI | Kling 3.0 Omni 720p (Standard) | 1,095 | -9/9 | 5,973 | Feb 2026 | $13.44 /min |
| 7 | 4-10 |  Google | Veo 3.1 | 1,095 | -9/9 | 6,195 | Jan 2026 | $24.00 /min |
| 8 | 5-11 | KlingAI | Kling 3.0 720p (Standard) | 1,091 | -9/9 | 6,185 | Feb 2026 | $15.12 /min |
| 9 | 5-11 | Google | Veo 3.1 Fast | 1,090 | -9/9 | 5,670 | Jan 2026 | $9.00 /min |
| 10 | 6-12 |  OpenAI | Sora 2 (December) | 1,087 | -9/9 | 4,827 | Dec 2025 | $6.00 /min |
| 11 | 8-13 | Google | Veo 3.1 Lite | 1,082 | -9/9 | 5,310 | Mar 2026 | $4.80 /min |
| 12 | 10-13 |  Vidu | Vidu Q3 Pro | 1,081 | -9/9 | 6,654 | Jan 2026 | $9.60 /min |
| 13 | 11-15 | OpenAI | Sora 2 Pro | 1,076 | -9/9 | 4,858 | Sept 2025 | $30.00 /min |
| 14 | 13-15 |  PixVerse | PixVerse V6 | 1,070 | -9/9 | 7,305 | Mar 2026 | $6.90 /min |
| 15 | 13-15 |  xAI | grok-imagine-video | 1,068 | -9/9 | 6,551 | Jan 2026 | $4.20 /min |
| 16 | 16 | Alibaba | Wan 2.6 | 1,021 | -9/9 | 4,983 | Dec 2025 | $9.00 /min |
| 17 | 17-16 | ByteDance Seed | Seedance 1.5 pro | 1,000 | 0/0 | 4,778 | Dec 2025 | $11.86 /min |
| 18 | 18 | KlingAI | Kling 2.6 Pro (January) | 986 | -9/9 | 6,056 | Jan 2026 | $8.40 /min |
| 19 | 18-19 |  Lightricks | LTX-2.3 Fast  Open Weights | 976 | -10/10 | 5,382 | Mar 2026 | $2.40 /min |
| 20 | 20-21 | Lightricks | LTX-2.3 Pro Open Weights | 953 | -10/10 | 5,563 | Mar 2026 | $3.60 /min |
| 21 | 20-22 | PixVerse | PixVerse V5.6 | 944 | -10/10 | 4,812 | Feb 2026 | Coming soon |
| 22 | 21-22 | Lightricks | LTX-2 Fast Open Weights | 943 | -10/10 | 4,827 | Oct 2025 | $2.40 /min |
| 23 | 23 | Lightricks | LTX-2 Pro Open Weights | 912 | -10/10 | 4,796 | Oct 2025 | $3.60 /min |
| 24 | 23-24 |  Sapiens AI | Agnes-Video-V2.0 | 902 | -12/12 | 2,388 | May 2026 | $0.30 /min |
1 API Pricing reflects the cost to generate 1 minute of 1080p video on the model creator's API at the model's default settings
Frequently Asked Questions
HappyHorse-1.0 currently leads among Text to Video models with audio output in the Artificial Analysis Text to Video Arena with an Elo score of 1213.
The top Text to Video models with audio by Elo rating are: 1. HappyHorse-1.0 (Elo 1213), 2. Dreamina Seedance 2.0 720p (Elo 1212), 3. SkyReels V4 (Elo 1110), 4. Kling 3.0 1080p (Pro) (Elo 1103), 5. Kling 3.0 Omni 1080p (Pro) (Elo 1097). Rankings are based on blind user votes in the Artificial Analysis Video Arena.
LTX-2.3 Fast currently leads among open weights Text to Video models with audio in the Artificial Analysis Text to Video Arena with an Elo score of 976, followed by LTX-2.3 Pro (Elo 953) and LTX-2 Fast (Elo 943).
HappyHorse-1.0 currently leads the Artificial Analysis Text to Video Arena (without audio) with an Elo score of 1359.
The top Text to Video models without audio by Elo rating are: 1. HappyHorse-1.0 (Elo 1359), 2. Dreamina Seedance 2.0 720p (Elo 1274), 3. Kling 3.0 1080p (Pro) (Elo 1250), 4. Kling 3.0 Omni 1080p (Pro) (Elo 1239), 5. grok-imagine-video (Elo 1236). Rankings are based on blind user votes in the Artificial Analysis Video Arena.
LTX-2 Pro currently leads among open weights Text to Video models without audio in the Artificial Analysis Text to Video Arena with an Elo score of 1136, followed by LTX-2.3 Fast (Elo 1133) and LTX-2 Fast (Elo 1130).
Models are ranked using an Elo rating system derived from user votes in blind comparisons in the Artificial Analysis Video Arena. Users compare two videos generated from the same text prompt without knowing which model created each video. Higher Elo scores indicate a model is preferred more often. Vote in the Artificial Analysis Video Arena