SocialReasonBench - Behavior Prediction: leaderboard

Metric: Accuracy (%; the 78 behavior prediction questions of SocialReasonBench; six-option multiple-choice questions on counterfactual narrative gameplay clips of Detroit: Become Human, labels grounded in the game's script, flowchart and recorded branches; zero-shot, temperature 0 or 0.01; Gemini, Qwen3-Omni, MiniCPM-o and ARC-Hunyuan-Video read native video with audio, GPT-4o, Claude 3.5 Sonnet and GLM-4.6V-Flash 32 evenly sampled keyframes without audio). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1GPT-4o (2024-08-06)74.36
2Claude 3.5 Sonnet (20240620)71.79
3Gemini 3 Pro66.67
4Gemini 3 Flash62.82
5Qwen3 Omni 30B A3B Instruct58.97

Interactive version: theaggregate.ai/benchmark?slug=socialreasonbench-behavior-prediction · How It Works · Data refreshed daily, snapshot 2026-09-26.