Text to Video Leaderboard (With Audio)Artificial Analysis
Wan2.7-260612, Gemini Omni Flash
Range | Creator | Model | Elo | 95% CI | Samples | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 1 |  Google | Gemini Omni Flash | 1,244 | -11/11 | 3,907 | May 2026 | $6.00 /min |
| 2 | 2 |  ByteDance Seed | Dreamina Seedance 2.0 720p | 1,227 | -8/8 | 10,831 | Mar 2026 | $9.07 /min |
| 3 | 3 |  Alibaba | Wan2.7-260612 | 1,164 | -10/10 | 3,938 | Jun 2026 | $9.00 /min |
| 4 | 4 | Alibaba-ATH | HappyHorse-1.1 | 1,149 | -9/9 | 4,412 | Jun 2026 | $9.90 /min |
| 5 | 5 | Alibaba-ATH | HappyHorse-1.0 | 1,128 | -8/8 | 7,193 | Apr 2026 | $13.20 /min |
| 6 | 6-8 |  KlingAI | Kling 3.0 1080p (Pro) | 1,111 | -7/7 | 9,984 | Feb 2026 | $20.16 /min |
| 7 | 6-8 |  Skywork AI | SkyReels V4 | 1,109 | -9/9 | 4,359 | Mar 2026 | $21.00 /min |
| 8 | 6-9 | Alibaba | Wan 2.7 | 1,107 | -9/9 | 3,870 | Apr 2026 | $9.00 /min |
| 9 | 8-12 | KlingAI | Kling 3.0 720p (Standard) | 1,100 | -7/7 | 9,995 | Feb 2026 | $15.12 /min |
| 10 | 9-14 | KlingAI | Kling 3.0 Omni 1080p (Pro) | 1,096 | -8/8 | 7,559 | Feb 2026 | $16.80 /min |
| 11 | 9-14 | Google | Veo 3.1 | 1,095 | -8/8 | 7,736 | Jan 2026 | $24.00 /min |
| 12 | 9-14 | KlingAI | Kling 3.0 Omni 720p (Standard) | 1,093 | -8/8 | 7,454 | Feb 2026 | $13.44 /min |
| 13 | 10-14 | Google | Veo 3.1 Lite | 1,092 | -8/8 | 7,131 | Mar 2026 | $4.80 /min |
| 14 | 10-14 | Google | Veo 3.1 Fast | 1,091 | -7/7 | 9,443 | Jan 2026 | $9.00 /min |
| 15 | 15 |  Vidu | Vidu Q3 Pro | 1,083 | -7/7 | 10,206 | Jan 2026 | $9.60 /min |
| 16 | 16-17 |  PixVerse | PixVerse V6 | 1,073 | -8/8 | 9,172 | Mar 2026 | $6.90 /min |
| 17 | 16-17 |  SpaceXAI | grok-imagine-video | 1,069 | -7/7 | 10,069 | Jan 2026 | $4.20 /min |
| 18 | 18 | Alibaba | Wan 2.6 | 1,028 | -8/8 | 6,456 | Dec 2025 | $9.00 /min |
| 19 | 19 | ByteDance Seed | Seedance 1.5 pro | 1,000 | 0/0 | 7,653 | Dec 2025 | $11.86 /min |
| 20 | 20 | KlingAI | Kling 2.6 Pro (January) | 988 | -8/8 | 7,374 | Jan 2026 | $8.40 /min |
| 21 | 21 |  Lightricks | LTX-2.3 Fast  Open Weights | 975 | -8/8 | 8,353 | Mar 2026 | $2.40 /min |
| 22 | 22 | Lightricks | LTX-2.3 Pro Open Weights | 962 | -8/8 | 8,304 | Mar 2026 | $4.80 /min |
| 23 | 23-24 | Lightricks | LTX-2 Fast Open Weights | 949 | -9/9 | 5,966 | Oct 2025 | $2.40 /min |
| 24 | 23-24 | PixVerse | PixVerse V5.6 | 948 | -9/9 | 6,086 | Feb 2026 | Coming soon |
| 25 | 25 | Lightricks | LTX-2 Pro Open Weights | 923 | -9/9 | 5,961 | Oct 2025 | $3.60 /min |
| 26 | 26 |  Sapiens AI | Agnes-Video-V2.0 | 910 | -10/10 | 4,227 | 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
Gemini Omni Flash currently leads among Text to Video models with audio output in the Artificial Analysis Text to Video Arena with an Elo score of 1244.
The top Text to Video models with audio by Elo rating are: 1. Gemini Omni Flash (Elo 1244), 2. Dreamina Seedance 2.0 720p (Elo 1227), 3. Wan2.7-260612 (Elo 1164), 4. HappyHorse-1.1 (Elo 1149), 5. HappyHorse-1.0 (Elo 1128). 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 975, followed by LTX-2.3 Pro (Elo 962) and LTX-2 Fast (Elo 949).
Gemini Omni Flash currently leads the Artificial Analysis Text to Video Arena (without audio) with an Elo score of 1326.
The top Text to Video models without audio by Elo rating are: 1. Gemini Omni Flash (Elo 1326), 2. HappyHorse-1.0 (Elo 1288), 3. HappyHorse-1.1 (Elo 1273), 4. Dreamina Seedance 2.0 720p (Elo 1272), 5. Wan2.7-260612 (Elo 1244). 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 1129, followed by LTX-2.3 Fast (Elo 1127) and LTX-2 Fast (Elo 1123).
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