Agent Systems Benchmark (ASB)

What is Agent Systems Benchmark (ASB)?

A Linux terminal framework for measuring how AI coding agents scale under concurrent sessions while maintaining task quality, latency, and resource consumption…

Released

2026-09-06

Evaluates

Agents, Language & Knowledge, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://github.com/martin-beck/agent-systems-benchmark

Agent Systems Benchmark (ASB) code

• Code https://github.com/martin-beck/agent-systems-benchmark

Which sources cite Agent Systems Benchmark (ASB)?

• Agent Systems Benchmark (ASB)

Related Agents, Language & Knowledge, Software & AI Compute benchmarks

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