BehaviorBench - Multi-Round Game Prediction (Distribution): leaderboard
Metric: Given the game rules and the earlier rounds of each subject, predict the next moves, on MobLab economic-game records of human players (dictator, ultimatum, trust, public goods, bomb risk, beauty contest and push/pull games): Wasserstein distance (0-100) between the model-predicted and the observed human choice distributions, with choices normalized to 0-100 and averaged over games; lower is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 6.9 |
| 2 | DeepSeek V3.2 | 10.1 |
| 3 | Claude Sonnet 4.6 | 10.6 |
| 4 | Claude Opus 4.6 | 11.7 |
| 5 | Gemini 3.1 Pro (Preview) | 12.5 |
| 6 | Claude Haiku 4.5 | 12.5 |
| 7 | Qwen 3 4B | 13.1 |
| 8 | GPT-5.4 (High) | 15.2 |
| 9 | Llama 3.3 70B Instruct | 15.3 |
| 10 | GPT-5.4 Mini (High) | 17.6 |
| 11 | Gemini 3.1 Flash Lite (Preview) | 18.6 |
Interactive version: theaggregate.ai/benchmark?slug=behaviorbench-multi-round-game-prediction-distribution · How It Works · Data refreshed daily, snapshot 2026-09-29.