Visual Reasoning on MathVision
46.34AccuracySupervised ETTC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Supervised ETTCEnsemble Composition=Same Family Models2026.05 | 46.34 | 1.5 | |
| ETTCEnsemble Composition=Same Family Models2026.05 | 44.84 | — | |
| VotingEnsemble Composition=Same Family Models2026.05 | 41.32 | — | |
| Supervised ETTCEnsemble Composition=Similar Size Models2026.05 | 36.62 | 1.05 | |
| ETTCEnsemble Composition=Similar Size Models2026.05 | 35.57 | — | |
| Average (Single-Model)Ensemble Composition=Same Family Models2026.05 | 33.53 | — | |
| VotingEnsemble Composition=Similar Size Models2026.05 | 32.05 | — | |
| Average (Single-Model)Ensemble Composition=Similar Size Models2026.05 | 27.66 | — |