Modality Arbitration - MC2 - Conflicting Text Accuracy: leaderboard
Modality Arbitration v1 Table1, Conflicting Text Accuracy. Exact target modality and input condition retained; image/text conflict has two different targets, not pooled. Four exact Instruct VLMs BF16,batch1,seed42,greedy128tokens,nativeRGB processors.
Metric: Score (%). Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | InternVL3-8B | 56.75 | #1695 |
| 2 | Qwen 2.5 VL 7B Instruct | 55.25 | #1842 |
| 3 | Qwen 3 VL 8B Instruct | 42.2 | #982 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=modality-arbitration-mc2-conflicting-text-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-12.