Individual experiment result
ScaLA (DE)
Muse Spark Open Meta
Matthews correlation coefficient reasoning on / locked provider-internal
67.8%
Matthews correlation coefficient
Run details
- Date
- 2026-10-16
- Test cases
- 2,048
- Median latency
- 1.76s
- Total cost
- $3.96
- Avg. prompt tokens
- 1,018.2
- Avg. answer tokens
- 8.4
- Avg. reasoning tokens
- 184.5
- Quantization
- provider-internal
About this benchmark
Native German linguistic acceptability — is the sentence grammatical (ja/nein)? generate_until; primary metric MCC (accuracy recorded as secondary).
Provenance
- Canonical model
- meta/muse-spark-open
- Run ID
2026-10-16T11-38-00__openrouter__meta__muse-spark-open__scala_de