WorldReasonBench - Information-Based: leaderboard

WorldReasonBench (2026) tests video generators as future world-state predictors: from an initial frame and an action instruction, the generated video must reach the correct final state through a plausible process. This board is the process-aware reasoning score (0-100), which combines the accuracy of a Qwen3.5-27B judge on structured questions about the video with its temporal and mechanism sub-scores, on the 23 information-based cases; higher is better.

Metric: Process-aware reasoning score (0-100): Acc_QA^0.8 times s_dyn^0.2, where Acc_QA is the binary accuracy of structured questions about the generated video answered by Qwen3.5-27B (extended thinking, 4 fps) and judged against ground truth, and s_dyn the mean of its temporal and mechanism question accuracies, on the 23 Information-Based cases on the 80-case shared evaluation set of WorldReasonBench (image-plus-text to video: from an initial frame and an action instruction, the generator must produce a video reaching the correct future world state; one generated clip per case); higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 11 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Seedance 2.047.6
2Sora237.3
3WorldReasonBench Kling (checkpoint unspecified)35.7
4Wan2.635.5
5Veo 3.1 Fast28.6
6Cosmos-Predict2.524.7
7HunyuanVideo-1.524.2
8LongCat-Video22.8
9LTX2.322.7
10UniVideo17.3
11Wan2.2-14B15

Interactive version: theaggregate.ai/benchmark?slug=worldreasonbench-information-based · How It Works · Data refreshed daily, snapshot 2026-11-21.