ModelCards
← All benchmarks

Multimodal prompting (text + image)

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. 1Pegasus 1.5 · TwelveLabs
    0.4555 score

“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

  • Pegasus 1.5 launch post §6

    TwelveLabs' own comparative evaluation on its internal time-based-metadata set; scores are on a 0–1 scale.

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