BENCHCOMPASS

What is BENCHCOMPASS?

A payment-domain benchmark with 306 items (MCQ, open QA, and attack variants) that tests models' ability to use domain context correctly, distinguish…

Released

2026-09-16

Evaluates

Finance, Language & Knowledge, cs.AI

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.18270

BENCHCOMPASS paper and code

• Paper https://arxiv.org/abs/2609.18270
• Code https://github.com/ant-intl/BenchCompass

Which sources cite BENCHCOMPASS?

• BENCHCOMPASS

Related Finance, Language & Knowledge, cs.AI benchmarks

• 2d-fet-bench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• AARRI-Bench
• ABACUS
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench