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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Flash | 32.6 |
| 2 | Qwen 3.5 35B A3B | 27.9 |
| 3 | GPT-5 Nano | 27.7 |
Interactive version: theaggregate.ai/benchmark?slug=memtrace · How It Works · Data refreshed daily, snapshot 2026-09-26.