SubtleMemory Benchmark

What is SubtleMemory?

SubtleMemory evaluates fine-grained relational memory discrimination in long-horizon AI agents. It contains 1,522 evaluation instances over 10 long histories…

Released

2026-06-04

Evaluates

General AI, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.05761

SubtleMemory paper and code

• Paper https://arxiv.org/abs/2606.05761
• Code https://github.com/Yummytanmo/SubtleMemory

Which sources cite SubtleMemory?

• SubtleMemory

Related General AI, Language & Knowledge, cs.AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench