NimCritic RoboArena - 7 Policies Recall: leaderboard

NimCritic v1 visual manipulation-progress evaluation, not action execution. LOOM: 300 trajectories, 19,618 calibrated frames, 171 single-task and 129 multi-task; duration-weighted Spearman forward/reverse correlations, signed harmonic PRC-F1 (zero on opposite signs) and terminal completion accuracy with reference progress > 0.99. Native baseline interfaces/output definitions retained. GVL shuffles up to 30 frames, temperature 1; GPT-6 Sol extra reasoning disabled. NimCritic is a separately trained Wan2.2-TI2V-5B-initialized critic with frozen UMT5-XXL,128,000 updates and 20 Euler inference steps; Gemini 3.8 Flash decomposes subtasks. Other checkpoint revisions/efforts unreported; no aliases to untrained backbones. Successful-rollout retrieval,3,872 sessions and 10,750 rollouts. Recall denominator 1,220 human-positive rollouts; hit rate 836 positive sessions overall. This judges existing rollouts, not a robot policy success rate. Metric: Recall (%).

Metric: Recall (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 9 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=nimcritic-roboarena-7-policies-recall · How It Works · Data refreshed daily, snapshot 2026-10-27.