audio benchmark
GiantSteps Tempo
A dataset for tempo estimation in electronic dance music containing 664 2-minute audio previews from Beatport, annotated from user corrections for evaluating automatic tempo estimation algorithms.
Updated Aug 7, 2026
Published models1
Registry coverage1
MetricScore
EvidenceB
GiantSteps Tempo leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | AC | 88.0% | 100.0% | 1 | C |
GiantSteps Tempo highlights
The top published results on this benchmark's own scale.
What is GiantSteps Tempo?
Definition and scoring fields from the benchmark registry.
A dataset for tempo estimation in electronic dance music containing 664 2-minute audio previews from Beatport, annotated from user corrections for evaluating automatic tempo estimation algorithms.
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- GiantSteps Tempo
- Modality
- audio
- Primary category
- audio
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- giantsteps-tempo|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about GiantSteps Tempo.
Which model scores highest on GiantSteps Tempo?
Qwen2.5-Omni-7B is currently ranked first with 88.0%.
What does GiantSteps Tempo measure?
A dataset for tempo estimation in electronic dance music containing 664 2-minute audio previews from Beatport, annotated from user corrections for evaluating automatic tempo estimation algorithms.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.