SABER Benchmark

What is SABER?

SABER evaluates operational safety of LLM coding agents in stateful project workspaces. Agents perform realistic tasks, and safety is scored from the final…

Released

2026-05-31

Evaluates

Agents, Agents & Tool Use, General AI, Safety

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.01317

SABER paper and code

• Paper https://arxiv.org/abs/2606.01317
• Code https://github.com/sssr-lab/saber

Which sources cite SABER?

• SABER

Related Agents, Agents & Tool Use, General AI, Safety benchmarks

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