Text to Video Leaderboard (With Audio)Artificial Analysis
MAGI-2 Preview (0912), Minimax H3 Max (post-trained by fal), Agnes-Video-2.5, LTX-2.5 Fast, LTX-2.5 Pro
Range | Creator | Model | Elo | 95% CI | Samples | Released | API Pricing 1 | |
|---|---|---|---|---|---|---|---|---|
| 1 | 1-3 |  Google | Gemini Omni Flash | 1233 | -7/7 | 15,172 | May 2026 | $6.00 /min |
| 2 | 1-3 |  Alibaba | Wan 3.0 | 1229 | -9/9 | 6,011 | Aug 2026 | $12.00 /min |
| 3 | 1-4 |  Fal | Minimax H3 Max (post-trained by fal) | 1227 | -9/9 | 5,689 | Aug 2026 | $2.40 /min |
| 4 | 3-4 |  MiniMax | MiniMax H3  Open Weights | 1220 | -8/8 | 8,602 | Jul 2026 | $7.80 /min |
| 5 | 5 |  ByteDance Seed | Dreamina Seedance 2.0 720p | 1210 | -6/6 | 20,345 | Mar 2026 | $9.07 /min |
| 6 | 6-7 |  Sand.ai | MAGI-2 Preview (0912) | 1156 | -9/9 | 5,103 | Sep 2026 | Coming soon |
| 7 | 7-8 | Alibaba | Wan2.7-260612 | 1149 | -6/6 | 16,694 | Jun 2026 | $9.00 /min |
| 8 | 7-8 | Alibaba-ATH | HappyHorse-1.1 | 1147 | -6/6 | 16,670 | Jun 2026 | $9.90 /min |
| 9 | 9 | Alibaba-ATH | HappyHorse-1.0 | 1119 | -7/7 | 7,618 | Apr 2026 | $13.20 /min |
| 10 | 10-12 | Alibaba | Wan 2.7 | 1098 | -7/7 | 4,856 | Apr 2026 | $9.00 /min |
| 11 | 10-14 |  Skywork AI | SkyReels V4 | 1095 | -7/7 | 4,991 | Mar 2026 | $21.00 /min |
| 12 | 10-13 |  KlingAI | Kling 3.0 1080p (Pro) | 1095 | -6/6 | 18,305 | Feb 2026 | $20.16 /min |
| 13 | 11-16 | KlingAI | Kling 3.0 720p (Standard) | 1089 | -6/6 | 17,426 | Feb 2026 | $15.12 /min |
| 14 | 11-18 | Google | Veo 3.1 | 1088 | -7/7 | 7,529 | Jan 2026 | $24.00 /min |
| 15 | 13-18 | Google | Veo 3.1 Fast | 1085 | -6/6 | 16,439 | Jan 2026 | $9.00 /min |
| 16 | 13-19 | Google | Veo 3.1 Lite | 1083 | -7/7 | 5,167 | Mar 2026 | $4.80 /min |
| 17 | 13-22 |  OpenAI | Sora 2 (December) | 1083 | -10/10 | 4,278 | Dec 2025 | $6.00 /min |
| 18 | 14-22 | KlingAI | Kling 3.0 Omni 720p (Standard) | 1082 | -7/7 | 7,265 | Feb 2026 | $13.44 /min |
| 19 | 16-22 |  Vidu | Vidu Q3 Pro | 1078 | -6/6 | 16,534 | Jan 2026 | $9.60 /min |
| 20 | 15-22 |  Sapiens AI | Agnes-Video-2.5 | 1076 | -9/9 | 6,178 | Aug 2026 | $1.50 /min |
| 21 | 17-22 |  PixVerse | PixVerse V6 | 1076 | -7/7 | 7,425 | Mar 2026 | $6.90 /min |
| 22 | 18-22 | KlingAI | Kling 3.0 Omni 1080p (Pro) | 1075 | -7/7 | 7,396 | Feb 2026 | $16.80 /min |
| 23 | 23-24 |  SpaceXAI | grok-imagine-video | 1065 | -6/6 | 15,141 | Jan 2026 | $4.20 /min |
| 24 | 23-26 | OpenAI | Sora 2 Pro | 1059 | -10/10 | 4,350 | Sep 2025 | $30.00 /min |
| 25 | 24-26 |  Lightricks | LTX-2.5 Fast Open Weights | 1055 | -9/9 | 3,079 | Aug 2026 | $7.80 /min |
| 26 | 24-26 | Lightricks | LTX-2.5 Pro Open Weights | 1053 | -9/9 | 3,129 | Aug 2026 | $10.20 /min |
| 27 | 27-28 | Alibaba | Wan 2.6 | 1030 | -7/7 | 5,821 | Dec 2025 | $9.00 /min |
| 28 | 27-28 | Vidu | Vidu Q3 Turbo | 1025 | -9/9 | 3,117 | Feb 2026 | $3.90 /min |
| 29 | 29 | ByteDance Seed | Seedance 1.5 pro | 1000 | 0/0 | 10,205 | Dec 2025 | $11.86 /min |
| 30 | 30-31 | Lightricks | LTX-2.3 Fast Open Weights | 975 | -7/7 | 9,362 | Mar 2026 | $2.40 /min |
| 31 | 30-31 | KlingAI | Kling 2.6 Pro (January) | 974 | -8/8 | 6,284 | Jan 2026 | $8.40 /min |
| 32 | 32-33 | Lightricks | LTX-2.3 Pro Open Weights | 958 | -7/7 | 8,806 | Mar 2026 | $4.80 /min |
| 33 | 32-33 | PixVerse | PixVerse V5.6 | 952 | -8/8 | 4,738 | Feb 2026 | Coming soon |
| 34 | 34 | Lightricks | LTX-2 Fast Open Weights | 924 | -9/9 | 4,535 | Oct 2025 | $2.40 /min |
| 35 | 35-36 | Lightricks | LTX-2 Pro Open Weights | 905 | -9/9 | 4,580 | Oct 2025 | $3.60 /min |
| 36 | 35-36 | Sapiens AI | Agnes-Video-V2.0 | 897 | -9/9 | 3,520 | 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
The top Text to Video models with audio by Elo rating are: 1. Gemini Omni Flash (Elo 1233), 2. Wan 3.0 (Elo 1229), 3. Minimax H3 Max (post-trained by fal) (Elo 1227), 4. MiniMax H3 (Elo 1220), and 5. Dreamina Seedance 2.0 720p (Elo 1210). Rankings are based on blind user votes in the Artificial Analysis Video Arena.
Wan 3.0 currently leads the Artificial Analysis Text to Video Arena (without audio) with an Elo score of 1336.
MiniMax H3 currently leads among open weights Text to Video models without audio in the Artificial Analysis Text to Video Arena with an Elo score of 1302, followed by LTX-2.5 Fast (Elo 1217) and LTX-2.5 Pro (Elo 1209).