Benchmark Radar™
Star —

VARM-Bench

Explore score history ↗

VARM-Bench evaluates verifiable structured reasoning in Chinese abusive-speech moderation. It uses field-anchored chain-of-thought rationales with six decision fields, and a deterministic protocol assessing field correctness, alignment, output validity, and record errors.

Released
2026-08-16
Institutions
Nanjing University of Aeronautics and Astronautics · Nanjing University · Huzhou Normal University
Evaluates
General AI, Reasoning, Speech & Audio
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

VARM-Bench paper

No reported scores are on record for this benchmark yet.

Which sources cite VARM-Bench?

Related General AI, Reasoning, Speech & Audio benchmarks