Individual experiment result
ScaLA (DE)
Gemma 4 26B A4B Google
Matthews correlation coefficient reasoning off provider-internal
66.3%
Matthews correlation coefficient
Run details
- Date
- 2026-06-08
- Test cases
- 2,048
- Median latency
- 0.46s
- Total cost
- $0.28
- Avg. prompt tokens
- 910.7
- Avg. answer tokens
- 2.6
- Avg. reasoning tokens
- —
- 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
- google/gemma-4-26b-a4b-it
- Run ID
2026-06-08T16-45-24__vertex_ai__openai__google__gemma-4-26b-a4b-it-maas__scala_de