MemSyco-Bench - Contextual Scope Control (Full Dialog): leaderboard

Metric: Generation accuracy (%; correct under the reference answer and task-specific rubric; requests where a remembered preference applies only within its stated scope; the whole preceding multi-turn dialogue is given in context with no memory system). Source: arxiv.org. Saturation forecast: Around December 2026. 5 models tracked.

Top models

#ModelScore
1DeepSeek V4 Flash79
2Qwen 3 8B70
3GPT-4o Mini69.33
4Llama 3.3 70B Instruct66.89
5Llama 3.1 8B Instruct48.33

Interactive version: theaggregate.ai/benchmark?slug=memsyco-bench-contextual-scope-control-full-dialog · How It Works · Data refreshed daily, snapshot 2026-09-29.