ModelCards
← All benchmarks

vs Runway Gen-4.5

We haven't written a description for this benchmark yet; see the card notes below for how each maker ran it.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1FLUX 3 Video · Black Forest Labs
    77.0%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • FLUX 3 Video Launch post (4 Aug 2026); FLUX 3 post (23 Jul 2026)

    BFL internal human-preference evaluations. The Elo is from the GA launch chart (other models' scores not given in text). Win rates are preliminary early-access results on 10-second 720p text-to-video clips with audio; BFL says they are early and expected to improve.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.