Modality: modality_arm · 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 | claude-vision | anthropic | 0.900 | 0.900 | curated |
| 2 | openai-vision | openai | 0.880 | 0.880 | curated |
| 3 | fal-paddleocr | fal | 0.750 | 0.750 | curated |
No benchmark outputs recorded for this niche yet.