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 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
GiantSteps Tempo Ranking
Higher score ranks better on this benchmark.
| 01 | AC | 88.0% | 100.0% | 1 | C |
GiantSteps Tempo Highlights
The leading models and scores on this benchmark.
What is GiantSteps Tempo?
What GiantSteps Tempo measures and how its scores work.
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. This benchmark is not independently verified and has an evidence level of B.
- Family
- GiantSteps Tempo
- Modality
- audio
- Primary category
- audio
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- giantsteps-tempo|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
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 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.