Individual experiment result
ScaLA (DE)
DeepSeek V4 Pro 0813 DeepSeek
Matthews correlation coefficient reasoning off provider-internal
75.6%
Matthews correlation coefficient
Run details
- Date
- 2026-08-13
- Test cases
- 2,048
- Median latency
- 1.21s
- Total cost
- $0.85
- Avg. prompt tokens
- 949.8
- Avg. answer tokens
- 1.5
- 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
- deepseek/deepseek-v4-pro-0813
- Run ID
2026-08-13T09-11-21__openrouter__deepseek__deepseek-v4-pro-0813__scala_de