FLUX 3 Max Video Model Ranks Near the Top at Lower Prices
- Source
- x.com
- Date
FLUX 3 Max from @fal, a post-trained version of @bfl_ai's FLUX 3, ranks #2 on AA-Video-I2V v1.1 (statistically tied for #1) and #4 on AA-Video-T2V v2.1, ahead of the base FLUX 3 on both FLUX 3 Max generates 5 to 20 second, 720p videos with native audio from a text prompt or a starting image. fal reports that it generates a 10 second video in under 12 seconds. We benchmarked it at the high reasoning level. FLUX 3 Max ranks #2 on AA-Video-I2V v1.1 and #4 on AA-Video-T2V v2.1, statistically tied with Dreamina Seedance 2.5 and MiniMax H3 (768p) on both, and ahead of its base model FLUX 3. On AA-Video-T2V v2.1, it scores highest of any model in the Physics capability, and in the Marketing & Advertising and Live-Action Film use cases. fal prices FLUX 3 Max at $10.20/min for 720p video, compared to $17.40/min for FLUX 3, and $24.60/min for Dreamina Seedance 2.5 and $5.40/min for MiniMax H3 (768p) on Image to Video. For the first three weeks of launch, fal is offering 75% off, at $2.55/min. Congratulations to @fal on the release! See below for our detailed analysis and comparisons between FLUX 3 Max and other leading models on AA-Video-T2V v2.1 and AA-Video-I2V v1.1 🧵
Context
FLUX 3 Max is not a new model from Black Forest Labs itself. It is a post-trained version of BFL's FLUX 3 built by fal, a company that runs AI models for developers through its API. Post-training means continuing to train a finished base model to improve particular behaviors. On its product page, fal says BFL built the base model while fal did the post-training, optimization and serving. The extra training aimed at visual fidelity, motion coherence, prompt adherence and image-to-video quality. The model makes 5- to 20-second 720p clips with native audio from a text prompt or a starting image.
The ranking needs a careful read. Artificial Analysis puts FLUX 3 Max at #2 on its image-to-video leaderboard and #4 on text-to-video, and says that on both it is statistically tied with Dreamina Seedance 2.5 and MiniMax H3 (768p), as the post puts it. A statistical tie means the score differences fall within the 's margin of uncertainty, so the order among these models is not settled. Two results are clearer. FLUX 3 Max ranks ahead of its base model on both boards, and on text-to-video it scores highest of any model in the Physics capability and in the Marketing & Advertising and Live-Action Film use cases. fal says post-training added 50 points, taking the model from 1,089 to 1,139 Elo on Artificial Analysis's preliminary image-to-video arena. Elo is a rating built up from head-to-head comparisons.
On price, the picture is mixed. Artificial Analysis reports that fal charges $10.20 per minute of 720p video for FLUX 3 Max, against $17.40 for the base FLUX 3 and $24.60 for Seedance 2.5. MiniMax H3 (768p) costs $5.40 on image-to-video, so one of the models it is tied with costs about half as much. For the first three weeks fal is cutting the price by 75%, to $2.55 per minute, and fal's page says that rate ends November 7. fal also reports that a 10-second clip takes about 12 seconds to generate. That speed figure is fal's own and was not part of Artificial Analysis's quality ranking.
Checking sign-in…
Loading comments…







