WorldReasonBench - World Knowledge: 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 21 world-knowledge 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 21 World Knowledge 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
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Veo 3.1 Fast | 55 | |
| 2 | Seedance 2.0 | 43.2 | |
| 3 | WorldReasonBench Kling (checkpoint unspecified) | 42.2 | |
| 4 | Sora2 | 36.9 | |
| 5 | Wan2.6 | 35.2 | |
| 6 | Wan2.2-14B | 22.9 | |
| 7 | HunyuanVideo-1.5 | 21.6 | |
| 8 | LTX2.3 | 15.6 | |
| 9 | Cosmos-Predict2.5 | 15.2 | |
| 10 | UniVideo | 13.8 | |
| 11 | LongCat-Video | 13.3 |
Interactive version: theaggregate.ai/benchmark?slug=worldreasonbench-world-knowledge · How It Works · Data refreshed daily, snapshot 2026-11-21.