EYT-Bench (PersonaMem-v2) - Anthropomorphic Interaction: leaderboard

Metric: Anthropomorphic interaction (colloquial, emotional, flow, flexibility, rhythm) (0-100): judge rubric of five sub-indicators scored 0, 0.5 or 1 per turn, summed to 0-5, turn weighted with the first two turns at 0.10 each and rescaled to 0-100; multi-turn dialogues of up to 10 turns with a persona-grounded Gemini 3.1 Pro user simulator and a Gemini 3.1 Pro judge (reasoning effort high, temperature 0); PersonaMem-v2 pool (100 dialogues; personas are free-text paragraphs distilled from long real user-assistant interactions). Source: arxiv.org. Saturation forecast: Estimated already saturated. 17 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.693.7
2Claude Opus 4.793.3
3Gemini 3.1 Pro (Preview) (Thinking)92.8
4Seed 2.0 Pro92.7
5DeepSeek V4 Pro91.9
6Qwen 3.5 27B90.5
7Seed 2.0 Lite88.6
8Qwen 3.5 397B A17B88.4
9Qwen 3.5 35B A3B88.2
10DeepSeek V4 Flash84.9
11GPT-5.576.4
12Seed 2.0 Mini62.7

Interactive version: theaggregate.ai/benchmark?slug=eyt-bench-personamem-v2-anthropomorphic-interaction · How It Works · Data refreshed daily, snapshot 2026-09-29.