AI/ deepfake · ai · benchmarks · computer-vision

New Benchmark Pits Deepfake Detectors Against Each Other

VendorBench-100 tests 36 deepfake image detectors across three competing paradigms and finds that a high score doesn't always mean a reliable decision.

A new benchmark reveals that the deepfake detection field has a measurement problem, not just a performance problem.

Researchers released VendorBench-100, a cross-paradigm benchmark that runs 36 deepfake image detectors through a single 100-image adversarial corpus. The test covers commercial APIs, zero-shot vision-language models, and open-source detectors — three categories that are widely used but rarely compared head-to-head. Rather than chasing dataset scale, the benchmark focuses on eight families of hard cases: face swaps, text-to-video stills, AI photo edits, avatar compositing, and others. Rankings lean on the Matthews correlation coefficient to handle the corpus's deliberate class imbalance, with ROC-AUC as a secondary measure.

The headline finding isn't the leaderboard. It's the gap between two metrics: models that rank images well by score (ROC-AUC) often fail to make reliable binary calls at a default threshold (MCC). In practice, that means a detector that looks strong on paper may flip the wrong way when deployed without tuning. That distinction matters enormously for any platform using these tools to auto-flag or auto-remove content at scale.

Commercial APIs landed at the top of the median performance table, with vision-language models next and open-source detectors trailing — though individual open-source models closed the gap with the best vision-language models. The benchmark and evaluation code are publicly available, which puts a reproducible baseline in the hands of researchers who have been working without one. Whether vendors take the findings seriously, or quietly move the goalposts, is another question.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →