LetTokenBurn
Sign in
Auto86%Harbor: pendingMultimodalSafety & Alignment

SEAR

Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language Models

A four-task audio question-answering benchmark evaluating audio language models on deepfake detection using acoustic evidence identification and quantification.

PaperRepoHomepage

How to run

ltb · sear
$ npm i -g lettokenburn-cli
$ ltb bench info sear

External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.

Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs

Scores

11 sourced entries
HarnessSourceConfidenceLink
Claude Opus 593.8N/AIndependentmediumOct 13, 2026arxiv.org
GPT-5.6 Sol89.0N/AIndependentmediumOct 13, 2026arxiv.org
Kimi K376.2N/AIndependentmediumOct 13, 2026arxiv.org
Gemini 3.6 Flash70.5N/AIndependentmediumOct 13, 2026arxiv.org
DeepSeek V4 Flash70.0N/AIndependentmediumOct 13, 2026arxiv.org
Gemini-Flash48.6N/AIndependentmediumSep 30, 2026arxiv.org
Qwen2-Audio39.1N/AIndependentmediumSep 30, 2026arxiv.org
Qwen2.5-Omni25.2N/AIndependentmediumSep 30, 2026arxiv.org
MOSS-Audio23.5N/AIndependentmediumSep 30, 2026arxiv.org
MiniCPM-o13.8N/AIndependentmediumSep 30, 2026arxiv.org
GPT-Audio13.2N/AIndependentmediumSep 30, 2026arxiv.org

Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.

Reproduced by the community

All runs
Loading community runs…

About

Content & Construction: SEAR is a benchmark constructed from ASVspoof datasets, utilizing 35 statistical acoustic features to generate reference evidence. It includes tasks for binary classification (verdict), feature identification/quantification, and open-ended forensic rationale generation.

Scoring & Findings: The benchmark assesses the gap between plausible rationales and verifiable evidence. Key findings show that tool-augmented agents improve detection performance when grounded in reliable acoustic anomalies.