MSE-Bench

What is MSE-Bench?

MSE-Bench measures agent performance and execution redundancy across deterministic editing tasks in a controlled simulator.

Released

2026-07-14

Evaluates

General AI, Language & Knowledge, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.13034

MSE-Bench paper and code

• Paper https://arxiv.org/abs/2607.13034
• Code https://github.com/eejyin/Do-AI-Agents-Know-When-a-Task-Is-Simple-Toward-Complexity-Aware-Reasoning-and-Execution

Which sources cite MSE-Bench?

• MSE-Bench

Related General AI, Language & Knowledge, Reasoning benchmarks

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