WorldReasonBench - Human-Centric: 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 9 human-centric 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 9 Human-Centric 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
1Sora244.7
2Seedance 2.035.9
3Veo 3.1 Fast35.1
4Wan2.634.5
5WorldReasonBench Kling (checkpoint unspecified)32.5
6LongCat-Video22.8
7Cosmos-Predict2.522.2
8LTX2.319.3
9UniVideo15.8
10Wan2.2-14B14.5
11HunyuanVideo-1.58.1

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