Modality: modality_arm, video_generation · full deep dive — every ranked model, test result, and artifact.
Ranked by confidence-adjusted score (single/zero-sample, non-curated scores floored; curated empirical scores trusted as-is).
| # | Model | Provider | Adj. Score | Raw | Evidence |
|---|---|---|---|---|---|
| 1 | fal-ai/recraft-v3 | fal | 0.911 | 0.950 | n=118 |
| 2 | stability/stable-image-sd3-large | stability | 0.150 | 1.000 | provisional (n≤1) |
No benchmark outputs recorded for this niche yet.