Asking an image model to "draw the future" is far harder than asking it to draw well. Given a few observation images and a manual, the model must render each successive world state in order — assembly steps, physical changes, and rule inference all have to be right. This task, multi-step world state prediction, demands tightly entangled understanding and generation, plus the world knowledge to translate human action sequences, physical transformations, and abstract visual reasoning into coherent frames. A study completed during an internship at Meituan proposes the WorldCast benchmark, organizes model capabilities into a four-level hierarchy (L1–L4), and argues that higher-level tasks remain underexplored despite rapid model progress. WorldCast targets exactly that L3–L4 band. [arXiv:2610.20731]

320 Cases, Three Scoring Dimensions

WorldCast contains 320 manually designed cases across eight task categories, requesting 1,352 visual states in total. Categories are not split by "what to draw" but by where the information governing a future process is encoded and what reasoning is needed to turn it into state transitions: physical simulation, adaptive task completion, visual goal realization, in-context procedural learning, and more. One L4 case asks the model to read a furniture assembly manual, plan the order itself, and render every intermediate state while preserving the work surface and component appearance. On the project page's shown result, GPT-Image-2.5 completes the key milestones while Wan 3.0 fails to follow the assembly order.

Scoring uses three complementary dimensions: Task Completion (TC, whether the sequence visibly realizes the task), Causal Plausibility (CP, whether transitions follow physical laws and logical rules), and Visual Consistency (VC, whether identity, count, geometry, and material persist). GPT-5.5 acts as the judge on a 0–3 scale; the final score is a weighted, rescaled combination.

The Leaderboard: A Bigger Cliff Than Expected

Twelve image and video generation systems were evaluated under the same protocol. GPT-Image-2.5 System (paired with GPT-6 Astra) scores 72.8, which the paper describes as early-stage visual state prediction capability on real-world tasks. Nano Banana Pro reaches only 42.8. The best open-source model, SenseNova-U1, scores 20.1 — a gap of more than 3.5x between the top closed system and the best open weights.

The divergence grows with difficulty: GPT-Image-2.5 scores above 60 on all five L4 categories and retains 71.6 on L4, only 2.2 below its L3 score. SenseNova-U1 drops from 24.4 at L3 to 15.0 at L4. The higher the level, the wider the gap. Failure modes are concrete: unintended rotation, wrong reflections, erroneous density, shape drift, and incorrect assembly order.

Three Findings

Strong generators draw on their language backbones. Pairing Nano Banana Pro with GPT-6 Astra as the enhancer raises its overall score from 42.8 to 61.2, yet it still trails the GPT-Image family. Conversely, swapping GPT-Image-2's backbone from GPT-5.5 to GPT-6 yields only marginal gains, with a decline in Physical Simulation. The ceiling of generative capability is welded shut by the planning and reasoning capacity of the language model.

Output format is a hidden variable. Switching GPT-Image-2.5 from interleaved to grid output cuts its overall score by 22.7, with Logic and Rules falling from 74.3 to 23.0. Across four generation steps, weaker models degrade as context accumulates, while GPT-Image-2.5 stays stable.

Agentic harnesses raise the ceiling further. The researchers built two Codex-based harnesses with the same generation budget: an inspect-and-revise loop without coding tools lifts GPT-Image-2.5 from 72.8 to 80.2 and GPT-6-enhanced Nano Banana Pro from 61.2 to 72.5. A coding-first loop that constructs and inspects intermediate visual artifacts before generation pushes the best overall score to 82.4, with the largest gains on Visual Goal Realization, Logic and Rules, and Physical Simulation — code makes intermediate states explicit.

So What

The real signal of this benchmark is not "GPT-Image-2.5 won again," but that the image-generation race is shifting from "drawing it well" to "reasoning it right" — and the latter is the language model's home turf. The open-source side's 20.1 overall and 15.0 at L4 suggest open weights have not truly entered the high-level world-modeling game; catching up may require not a bigger diffusion backbone but better planning and reasoning layers. The dataset is on Hugging Face (wenhaoyan77/WorldCast), and the project page (teal024.github.io/WorldCast) carries the full leaderboard and case gallery.

When "looks good" is saturated, the next dividing line is: does your model know what the world should look like next?