KOpenAudioBench is a Korean spoken question answering benchmark for evaluating speech models. It was constructed by KRAFTON to address the lack of existing Korean benchmarks, building upon the English benchmark OpenAudioBench. The dataset was last updated on June 1, 2026.
Use Cases
- Benchmarking Korean speech model performance based on spoken question answering tasks
- Training speech language models on Korean audio content
- Comparing model capabilities across different languages using a benchmark framework
Strengths
- Addresses a specific gap in Korean speech model evaluation, as noted in the description
- Built upon an established English benchmark (OpenAudioBench), suggesting a structured foundation
Limitations
- Column-level documentation is absent; field semantics must be inferred after download
- Row count is unknown, which may limit suitability assessment
- Freshness should be verified as the last update date is in the future (2026-06-01)
Provenance
- Source
- KRAFTON
- Collection Method
- Constructed by building upon the English benchmark OpenAudioBench.
- Freshness
- Last updated 2026-06-01 05:22:12