M2ABench

What is M2ABench?

A benchmark of 122 real-world AI models in which agents must deploy each model as a ready-to-call API. Standardized test cases check the result, and agents are…

Released

2026-08-02

Evaluates

Agents, Agents & Tool Use, General AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.01189

M2ABench paper and code

• Paper https://arxiv.org/abs/2608.01189
• Code https://github.com/HITDiSC/MADE

Which sources cite M2ABench?

• M2ABench

Related Agents, Agents & Tool Use, General AI benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench
• ActiveVision