MemTrace: leaderboard

Metric: Gist accuracy (%; GPT-4o judge; the model answers from the visible multi-session history in its context; saturated history: checkpoints W7-W8, mean of current-state, earlier-state and change-over-time questions). Source: arxiv.org. Saturation forecast: Around 2029. 3 models tracked.

Top models

#ModelScore
1Gemini 3 Flash32.6
2Qwen 3.5 35B A3B27.9
3GPT-5 Nano27.7

Interactive version: theaggregate.ai/benchmark?slug=memtrace · How It Works · Data refreshed daily, snapshot 2026-09-26.