BASS - Gene Dominance Ranking: leaderboard

Metric: Exact-match accuracy (%) on the 33 gene dominance ranking questions: order four attributes of a song by prominence, credited only for the exact order (multiple-choice, majority vote over four runs); BASS music understanding benchmark, audio language models get a text prompt (one of ten paraphrases) and a full commercial music recording from BASS's songs; raw score before chance normalization; higher is better. Source: arxiv.org. Saturation forecast: Around March 2028. 14 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro21.2#145
2Phi-4 Multimodal Instruct9.12#896
3Voxtral-Small-24B-25079.12#565
4SALMONN-7B0.3#1274

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.

Interactive version: theaggregate.ai/benchmark?slug=bass-gene-dominance-ranking · How It Works · Data refreshed daily, snapshot 2026-10-11.