Individual experiment result
ScaLA (DE)
MiMo V2.5 Xiaomi
Matthews correlation coefficient reasoning off fp8
53.4%
Matthews correlation coefficient
Run details
- Date
- 2026-08-11
- Test cases
- 2,048
- Median latency
- 0.74s
- Total cost
- $0.32
- Avg. prompt tokens
- 1,297
- Avg. answer tokens
- 2.7
- 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
- xiaomi/mimo-v2.5
- Run ID
2026-08-11T10-59-13__openrouter__xiaomi__mimo-v2.5__scala_de