PhyGround - Physical Temporal Validity: leaderboard

PhyGround (2026) asks video generation models to continue a first frame under a prompt that states the expected physical outcome, and has hundreds of screened annotators rate the 2,000 resulting videos from 1 to 5. This board is the mean rating for physical temporal validity, whether motion over time is plausible; higher is better.

Metric: Human rating (1-5) of physical temporal validity (plausible motion over time), human ratings on a 1-5 scale from a quality-controlled pool of 352 annotators (after filtering 459), on 2,000 videos generated from 250 text-plus-first-frame prompts with explicit physical outcomes, each model at its released inference defaults; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 8 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Wan2.2-27B-A14B3.37
2Veo 3.13.29
3OmniWeaving3.17
4Cosmos-Predict2.5-14B2.98
5LTX-2.3-22B2.74
6Wan2.2-TI2V-5B2.68
7LTX-2-19B2.64
8Cosmos-Predict2.5-2B2.56

Interactive version: theaggregate.ai/benchmark?slug=phyground-physical-temporal-validity · How It Works · Data refreshed daily, snapshot 2026-11-21.