Psi-Bench - Viewpoint Debate Personalization: leaderboard

Metric: Personalized argumentation score (how well arguments are tailored to the hidden client profile), Change My View debates (1-9; DeepSeek-v3.2 judge, which also plays the persona-profiled client; three rounds after the client's opening message, client profile hidden from the model). Source: arxiv.org. Saturation forecast: Around January 2028. 10 models tracked.

Top models

#ModelScore
1DeepSeek V4 Pro5.62
2GPT-5.15.57
3Gemini 3.1 Pro (Preview)5.54
4Grok 4 Fast5.2
5GPT-5 Mini4.91
6DeepSeek V3.24.8
7Gemini 3 Flash4.73
8Qwen 3 32B4.34
9Qwen 3 Next 80B A3B4.1
10Qwen 3 8B3.56

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