Social Gym - Bluffing Games: leaderboard

Metric: Bradley-Terry Elo rating (regularized fit on the pooled cross-model pairwise outcomes of four hidden-state bluffing games (Liar's Dice, Skull, Coup, Sheriff of Nottingham), scale 400, anchored at a mean of 1000 over the seven evaluated models; seats and roles balanced over every model combination; relative to this model pool only). Source: arxiv.org. Saturation forecast: Around October 2026. 7 models tracked.

Top models

#ModelScore
1GPT-5 Mini1080
2GPT-4o1025
3GPT-4o Mini996
4Qwen 3 32B982
5Qwen 3 4B976
6Gemma 3 27B973
7Qwen 2.5 3B Instruct964

Interactive version: theaggregate.ai/benchmark?slug=social-gym-bluffing-games · How It Works · Data refreshed daily, snapshot 2026-09-29.