MethodologyAnnotator qualityUpdatesHugging Face434.9k downloadsSuggest a model or benchmarkRequest a private benchmark
Benchmarks
Dimensions
License
Models
Categories
Number of motions
Motion
Scene
View
Camera Movement v1updated 2026-09-03

World Models: Camera Movement Benchmark

Rapidatabenchmark@rapidata.ai

Abstract

This benchmark ranks world and video generation models on whether they can carry out a camera movement stated in plain terms, without referencing the scene, such as moving forward, tilting down or rolling clockwise, starting from a single still image. We curated 30 camera-movement instructions across 22 spaces and mixed and matched them into 600 prompts, held fixed to ensure reproducibility of the results. The rankings are updated continuously from 513,079 responses across 102,595 pairwise human-preference matches. All data and judgments are public; see the methodology for details on evaluation and scoring.

LeaderboardCompare OutputsMatchupsAnalysisPromptsDetails
#
Model
Organization
Score
95% CI
Interval
Responses
Matches
Win rate
#
Model
Score

Table 1. Overall standings, Camera movement benchmark. Scores from a Bradley–Terry fit rescaled to Elo; intervals are 95% Wald intervals. Click any row to view sample outputs in Figure 1.

Methodology notesCompare Outputs
Figure 1. Sample outputs from Atlas on representative prompts from the fixed set. Outputs shown are those used in matches.
Score vs. cost
50010001500$0.01$0.02$0.05$0.1$0.2cost, USD per video second (log scale)score

Figure 2. Overall Elo against the provider's list price, cost on a log scale. Teal-ringed models are the Pareto frontier, no model is both cheaper and better, joined by a step line, so picking a budget on the x-axis reads off the best model at or under it. Faded models are dominated; whiskers are the score 95% CI. Prices are hand-maintained snapshots of provider list prices; 7 models without a recorded price are not shown. Hover a model for exact numbers.

Evaluation: Models are compared on the same prompts through pairwise human judgements.
Score: Scores show relative performance within this benchmark. A higher score means a model was more likely to be preferred over the other evaluated models.
Uncertainty: The 95% confidence interval shows the uncertainty around each model’s estimated score.
Views: Results can be explored by movement match, and by prompt category.
Coverage: This benchmark includes a fixed prompt set across multiple categories, evaluated on all ranked models.
Data: Available prompts, model outputs, and evaluation results can be downloaded for further analysis.
Version: Results correspond to Camera Movement v1, last updated on 2026-11-19.

We use crowd intelligence to deliver real, diverse human feedback at scale for model evaluation and post-training.

Benchmarks
Text-to-ImageOutput Diversity (Mode Collapse)Multi-Step Image Editing (Identity Drift)Camera MovementRelative Camera MovementPhysicsPhysicsRealismImage-to-3DSVGLLM-to-3DSuggest a model or benchmark
Method
MethodologyData on Hugging Face
Rapidata
rapidata.ai Private benchmarksContactX LinkedIn
Rapidata, benchmark.ai © 2026