Individual experiment result
ScaLA (DE)
Kolibri-1 (FP8) Aleph Alpha
Matthews correlation coefficient reasoning off fp8
59.6%
Matthews correlation coefficient
Run details
- Date
- 2026-10-05
- Test cases
- 2,048
- Median latency
- 0.22s
- Total cost
- —
- Avg. prompt tokens
- 855.9
- Avg. answer tokens
- 2
- Avg. reasoning tokens
- —
- Quantization
- fp8
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
- aleph-alpha/kolibri-1-fp8
- Run ID
2026-10-05T16-52-01__openai__Aleph-Alpha__Kolibri-1__scala_de