# MemBench

MemBench is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates agent memory effectiveness, efficiency, and capacity across factual and reflective memory in participation and observation settings.

## Details

- Address: Online, Global
- Website: [github.com/import-myself/Membench](<https://github.com/import-myself/Membench>)
- Tags: Helpful, Science
- Category: Memory
- Status: Active
- Data licence: MIT
- Data access: open
- Grader: mixed
- Organization: Haoran Tan et al.
- Released: 2024-10
- Paper: [arxiv.org/abs/2506.21605](<https://arxiv.org/abs/2506.21605>)
- Repository: [github.com/import-myself/Membench](<https://github.com/import-myself/Membench>)
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is MemBench?

MemBench is at Online, Global.

### How do I contact MemBench?

To contact MemBench, visit https://github.com/import-myself/Membench.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/membench>)
- [Memory in Online](<https://aibenchmarkindex.com/global/online/category/memory.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.