Memory-World - Active Memory Instruction: leaderboard
Metric: Task Accuracy (%; pass@1, general-purpose models with an explicit memory instruction). Source: arxiv.org. Saturation forecast: Around February 2027. 5 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 59.1 |
| 2 | GPT-5.4 | 52 |
| 3 | Gemini 3.1 Pro (Preview) | 49.6 |
| 4 | Qwen 3 VL 8B (Thinking) | 36.2 |
| 5 | Qwen 3 VL 8B Instruct | 16.5 |
Interactive version: theaggregate.ai/benchmark?slug=memory-world-active-memory-instruction · How It Works · Data refreshed daily, snapshot 2026-09-25.