LoSoNA: leaderboard

Metric: Accuracy@3 (%) under the naive (write the next chat message, no instruction to infer norms) prompt condition on 38 curated group-chat scenarios in which other participants demonstrate a hidden local norm and a final elicitor turn forces a revealing reply; three sampled replies per scenario judged for compliance by a fixed Gemini 3.1 Pro Preview judge; accuracy@3 (%) is the share of scenarios where the majority of the three replies comply; higher is better. Source: arxiv.org. Saturation forecast: Around 2031. 8 models tracked.

Top models

#ModelScore
1Claude Fable 547.4
2Gemini 3.1 Pro (Preview)36.8
3Claude Opus 4.836.8
4Mistral Medium 3.136.8
5GPT-5.534.2
6Llama 3.3 70B Instruct28.9
7Qwen 2.5 72B Instruct23.7
8Gemma 3 27B (IT)21.1

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