Prototype · closed beta
unOpen.AI
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Video generation · Lightricks
LTX-2.3 Fast.
LTX-2.3 Fast is a Lightricks video model, released in March 2026. It ranks 32nd of 36 in the Artificial Analysis text to video arena, with an Elo of 845. It ranks 31st of 32 in the Artificial Analysis image to video arena, with an Elo of 822.
- #32 of 36
- Elo 845
Arena ratings
- Creator
- Lightricks
- Category
- Video generation
- Released
- March 2026
- Text to video
- Elo 845 (-18/18) · ranked 32nd of 36 · 3,780 votes
- Image to video
- Elo 822 (-20/20) · ranked 31st of 32 · 3,173 votes
Arena ratings by Artificial Analysis as of 30 October 2026, not figures we measured or the provider published. Rankings move weekly.
Source: the Artificial Analysis arenas, where people choose between two anonymous outputs of the same prompt. Ratings, not specifications: confirm price, licence and limits with Lightricks.
HOW IT COMPARES
Against the leading video models.
Elo rating from blind preference votes · Higher is preferred more often · Linear scale from 0 to 1,300
- HeyGen Video 1
- 1,143
- MiniMax H3 Max
- 1,140
- FLUX 3 Max
- 1,135
- Wan 3.0
- 1,133
- Utopai X
- 1,130
- LTX-2.3 Fast
- 845
Against the leader, HeyGen Video 1, the gap implies voters would choose LTX-2.3 Fast about 15% of the time. A 100-point gap is roughly 64% to 36%; gaps inside the confidence intervals are not meaningful.
Source: Artificial Analysis arenas. Checked 30 October 2026. Measured independently by Artificial Analysis, not by QQuantum.ai or the providers.
TEXT TO VIDEO BY STYLE
Where LTX-2.3 Fast is strongest: text to video.
Elo within each style of prompt · Higher is preferred more often · Linear scale from 0 to 1,000
- Photorealistic (2,289 votes)
- 863
- Flat Design (418 votes)
- 832
- Cartoon and anime (370 votes)
- 800
- 3D Render/CGI (363 votes)
- 766
Each style is rated on its own prompts and votes, so a style with few votes has a wide interval. Use this to shortlist for a brief, then test on your own prompts.
Source: Artificial Analysis arenas. Checked 30 October 2026. Measured independently by Artificial Analysis, not by QQuantum.ai or the providers.
IMAGE TO VIDEO BY STYLE
Where LTX-2.3 Fast is strongest: image to video.
Elo within each style of prompt · Higher is preferred more often · Linear scale from 0 to 1,000
- Photorealistic (2,231 votes)
- 836
- Cartoon and anime (302 votes)
- 790
- Flat Design (259 votes)
- 751
Each style is rated on its own prompts and votes, so a style with few votes has a wide interval. Use this to shortlist for a brief, then test on your own prompts.
Source: Artificial Analysis arenas. Checked 30 October 2026. Measured independently by Artificial Analysis, not by QQuantum.ai or the providers.
THE FULL LEADERBOARD
Every video model, ranked.
Where LTX-2.3 Fast sits among all 37 ranked models. Our Video generation page covers how we evaluate them for real work.
| 1 | HeyGen Video 1 | HeyGen | Oct 2026 | 1143 -16/16 | 1104 -17/17 | 5,570 |
|---|---|---|---|---|---|---|
| 2 | MiniMax H3 Max | Fal | Aug 2026 | 1140 -19/19 | 1125 -19/19 | 2,934 |
| 3 | FLUX 3 Max | Fal | Oct 2026 | 1135 -19/19 | 1058 -19/19 | 2,998 |
| 4 | Wan 3.0 | Alibaba | Aug 2026 | 1133 -17/17 | 1085 -19/19 | 4,515 |
| 5 | Utopai X | Utopai Studios | Sep 2026 | 1130 -18/18 | — | 2,967 |
| 6 | MiniMax H3 (768p) | MiniMax | Jul 2026 | 1120 -17/17 | 1111 -19/19 | 4,411 |
| 7 | Bach 1.0 Pro | Video Rebirth | Sep 2026 | 1109 -18/18 | 1120 -19/19 | 2,993 |
| 8 | P-Video-2-Pro | Pruna AI | Sep 2026 | 1103 -18/18 | 1103 -19/19 | 2,977 |
| 9 | Dreamina Seedance 2.5 | ByteDance Seed | Jul 2026 | 1101 -17/17 | 1129 -19/19 | 4,602 |
| 10 | FLUX 3 | Black Forest Labs | Jul 2026 | 1092 -17/17 | 1041 -19/19 | 3,737 |
| 11 | Dreamina Seedance 2.0 | ByteDance Seed | Mar 2026 | 1085 -17/17 | 1094 -20/20 | 3,720 |
| 12 | Gemini Omni Flash 1.1 | Aug 2026 | 1068 -17/17 | 1024 -19/19 | 4,701 | |
| 13 | Agnes-Video-2.5 | Sapiens AI | Aug 2026 | 1057 -17/17 | 1115 -19/19 | 3,651 |
| 14 | Grok Imagine Video 1.5 | SpaceXAI | May 2026 | 1036 -17/17 | 1054 -19/19 | 3,737 |
| 15 | HappyHorse-1.1 | Alibaba-ATH | Jun 2026 | 1033 -16/16 | 1023 -18/18 | 4,692 |
| 16 | HappyHorse-1.0 | Alibaba-ATH | Apr 2026 | 1032 -17/17 | 1011 -19/19 | 3,637 |
| 17 | Wan2.7-260612 | Alibaba | Jun 2026 | 1022 -16/16 | — | 4,648 |
| 18 | MAGI-2 Preview | Sand.ai | Sep 2026 | 1005 -16/16 | — | 5,958 |
| 19 | Kling 3.0 1080p (Pro) | KlingAI | Mar 2026 | 1000 0/0 | 1000 0/0 | 4,475 |
| 20 | PixVerse V6 | PixVerse | Mar 2026 | 990 -17/17 | 969 -19/19 | 3,677 |
| 32 | LTX-2.3 Fast | Lightricks | Mar 2026 | 845 -18/18 | 822 -20/20 | 3,780 |
Elo from the Artificial Analysis arenas: people choose between two anonymous outputs of the same prompt, and the ratings follow from those votes. The figure after each score is its 95% confidence interval; gaps inside it are not meaningful. Rank and votes are for text to video. Refreshed weekly; not measured by QQuantum.ai. Select a heading to sort.
All 37 video models · Also from Lightricks: LTX-2.5 Fast, LTX-2.5 Pro, LTX-2.3 Pro
Questions
Questions about LTX-2.3 Fast.
When was LTX-2.3 Fast released?
Artificial Analysis records LTX-2.3 Fast as released in March 2026.
How good is LTX-2.3 Fast?
In the Artificial Analysis text to video arena it ranks 32nd of 36, with an Elo of 845 (-18/18 at 95% confidence) from 3,780 votes, checked 30 October 2026. Elo reflects blind human preference, not fitness for your brief.
How does LTX-2.3 Fast compare with the top-ranked model?
The leader, HeyGen Video 1, is rated 1143. On standard Elo arithmetic that gap means voters would prefer LTX-2.3 Fast in about 15% of head-to-head comparisons. Check the confidence intervals: small gaps may not be real.
What does LTX-2.3 Fast cost, and can we use its output commercially?
The arena does not publish prices or licence terms. Check Lightricks's own pricing and terms of use for the access route you plan, including rights in generated output, before production use.
