Individual experiment result
SB10K (DE)
Kolibri-1 (FP8) Aleph Alpha
Matthews correlation coefficient reasoning off fp8
58.4%
Matthews correlation coefficient
Run details
- Date
- 2026-10-05
- Test cases
- 1,024
- Median latency
- 0.23s
- Total cost
- —
- Avg. prompt tokens
- 728.4
- Avg. answer tokens
- 2.4
- Avg. reasoning tokens
- —
- Quantization
- fp8
About this benchmark
Native German Twitter sentiment (positive/neutral/negative), generate_until variant; primary metric MCC.
Provenance
- Canonical model
- aleph-alpha/kolibri-1-fp8
- Run ID
2026-10-05T16-47-29__openai__Aleph-Alpha__Kolibri-1__sb10k_de