BLINDSPOT Benchmark

What is BLINDSPOT?

This entry describes a benchmark for trajectory-level safety calibration of tool-using agents, but the provided abstract and links do not include released task…

Released

2026-09-14

Evaluates

General AI, Safety, Safety & Trustworthiness

Openness

unknown

Importer

Claire Radar

Review status

ai-name-audit-deferred

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.16305

BLINDSPOT paper

• Paper https://arxiv.org/abs/2609.16305

Which sources cite BLINDSPOT?

• BLINDSPOT

Related General AI, Safety, Safety & Trustworthiness benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A3S-Bench
• AARRI-Bench
• ABACUS