aiaimodel.cards
← All benchmarks

Elo

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. 1Runway Gen-4.5 · Runway
    1247 Elo

“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

  • Runway Gen-4.5 launch post

    Runway's own claim, quoting the Artificial Analysis Text-to-Video leaderboard as of 30 Nov 2025 (blind pairwise human preference). Later models are not included.

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