Trendoday

DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images

Can a vision-language model look at a picture of a chain reaction and tell what will happen? Recent multimodal models describe scenes fluently and solve textbook physics problems, which suggests they

  • Upvotes3
–Rank now
#21Peak rank
2Days on list
53Score · 7d
Nov 17, 2026First seen
Rank · 7 days

About this paper

A new benchmark, DominoBench, shows that current vision-language and multimodal models cannot reliably predict physical outcomes from still images unless the critical calculation and necessary quantities are provided.

Can a vision-language model look at a picture of a chain reaction and tell what will happen? Recent multimodal models describe scenes fluently and solve textbook physics problems, which suggests they should also predict how a scene of ramps, ledges, pendulums, seesaws and dominoes plays out once a ball is pushed. We tested this claim on 30 models from 10 families and reached a clear conclusion: unaided, no model predicts the outcome reliably. We built DominoBench, a benchmark of still images of 2D rigid-body scenes whose outcome a physics simulator computes. It holds 854 items in 427 minimal pairs, in which a change of one to three grid steps in one quantity decides whether one person…

vision-language modelsmultimodal modelsDominoBenchfrontier modelsopen-weight models
Upvotes
3
Authors
1
Published
Nov 16, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 8 checks on 2 different days. Its best position was #21 of 30, reached on Nov 17, 23:28 UTC. It dropped off the list after Nov 18, 05:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 15:2818:5822:2801:5805:28 Nov 17, 15:28 UTC · #30Nov 17, 17:28 UTC · #26Nov 17, 19:28 UTC · #28Nov 17, 21:28 UTC · #25Nov 17, 23:28 UTC · #21Nov 18, 01:28 UTC · #21Nov 18, 03:28 UTC · #28Nov 18, 05:28 UTC · #28

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0235 15:2818:5822:2801:5805:28 Nov 17, 15:28 UTC · 3Nov 17, 17:28 UTC · 4Nov 17, 19:28 UTC · 4Nov 17, 21:28 UTC · 4Nov 17, 23:28 UTC · 5Nov 18, 01:28 UTC · 5Nov 18, 03:28 UTC · 5Nov 18, 05:28 UTC · 5

Questions

Is DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 18, 05:28 UTC, after 2 days of trending.

What is the highest rank DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images reached?

#21 on Hugging Face · Daily papers, on Nov 17, 23:28 UTC. Trendoday checks this list every 120 minutes.

How long has DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images been trending?

It was first seen on Nov 17, 2026 and has been on the list on 2 days (8 checks) since.