SPY Release Evaluation - MMMU Validation - Self Moderation: leaderboard
SPY Release Evaluation - MMMU Validation - Self Moderation: Native benchmark score. SPY-Bench arXiv 2611.13997v1: personalized visual-privacy compliance, scores 0-100. Native distractor/scenario/conflict and ICS/RtA/AtA/HMS columns remain separate. Full official source model labels bind the evaluated checkpoints. Official repository release links bind four fine-tuned Qwen2-VL-7B-Instruct SFT/DPO/NCA/NCA-P checkpoints; they are distinct released models, not run wrappers around the original model. Self-moderation is an inference configuration of the original. Table 7 first row is an external official result and is not recounted. API effort is unreported. Native source condition: Self Moderation.
Metric: Native benchmark score. Source: arxiv.org. 1 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2 VL 7B Instruct | 50.44 | #2569 |
Interactive version: theaggregate.ai/benchmark?slug=spy-release-evaluation-mmmu-validation-self-moderation · How It Works · Data refreshed daily, snapshot 2026-11-12.