ReaLM - V-Attack: leaderboard

ReaLM (2026) is a red-teaming benchmark for physical-world vision-language models on 832 driving, manipulation, grasping, physics, egocentric, diagnostic and scene cases, attacked black-box toward scenario-specific failure targets. This board is the attack success rate under V-Attack, manipulation of attention value features in a CLIP surrogate ensemble: the percent of attacked cases answered incorrectly; lower is better.

Metric: Attack success rate (%; share of adversarial cases where the model gives an incorrect, task-relevant answer) under V-Attack (attention value-feature manipulation against a CLIP surrogate ensemble, L-inf 16/255) on the 832 ReaLM physical-world cases (driving, manipulation, grasping, physics, egocentric, diagnostics and scene QA; image, question and ground-truth answer), black-box one-shot evaluation at temperature 0, a Qwen3-8B judge extracting the answer; lower is better. Source: arxiv.org. Saturation forecast: Around November 2027. 13 models tracked.

Top models

No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.

Interactive version: theaggregate.ai/benchmark?slug=realm-v-attack · How It Works · Data refreshed daily, snapshot 2026-11-13.