FLUX 3 Max by fal ranks #2 on video I2V, tops all models in Physics
ArtificialAnlys · x · 2026-10-20
Artificial Analysis benchmarked FLUX 3 Max, fal's post-trained version of Black Forest Labs' FLUX 3:
- Rankings: #2 on AA-Video-I2V v1.1 (statistically tied for #1) and #4 on AA-Video-T2V v2.1, ahead of base FLUX 3 on both and statistically tied with Dreamina Seedance 2.5 and MiniMax H3 (768p)
- Specs: generates 5–20 second 720p videos with native audio from text or an image; fal reports a 10-second video in under 12 seconds (benchmarked at high reasoning level)
- Strengths: highest Physics score of any model on T2V, near-frontier in Audio Sync and Dialogue & Lip Sync; ranks #1 in the Marketing & Advertising and Live-Action Film use cases, weakest in UI/UX and Knowledge Work. Beats base FLUX 3 on 7 of 10 capabilities, most in Lighting & Materials and Complex Composition
- Pricing: $10.20/min for 720p image-to-video vs $17.40 for FLUX 3, $24.60 for Seedance 2.5 and $5.40 for MiniMax H3; 75% off at $2.55/min for the first three weeks
More from Models
- Together Post-Training launches: turn open models into custom models via SFT or RL — togethercompute · 2026-10-20
- PrismML's Ternary Bonsai 2 squeezes Qwen3.5 VL models to ternary weights, 9B at 2GB — lmoroney · 2026-10-20
- Cline: MiniMax M3.1 Flash matches Opus and GPT on coding at roughly 25x lower cost — MiniMax_AI · 2026-10-20
- Gemini 4 'Argon' spotted in Gemini App and AI Studio, unconfirmed — Efficient-Break-6333 · 2026-10-20
- Anthropic Safeguards blog: Claude self-assessment flags unsafe chats, 78% recall at 1% FPR — javirandor · 2026-10-20
- Unverified: Gemini 4 Argon reportedly catching up with Opus 5.5 — vedantmisra · 2026-10-20