Individual experiment result
ScaLA (DE)
DeepSeek V4 Flash 0731 DeepSeek
Matthews correlation coefficient reasoning off fp4
76.1%
Matthews correlation coefficient
Run details
- Date
- 2026-08-11
- Test cases
- 2,048
- Median latency
- 0.76s
- Total cost
- $0.15
- Avg. prompt tokens
- 949.8
- Avg. answer tokens
- 2.5
- Avg. reasoning tokens
- —
- Quantization
- fp4
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-flash-0731
- Run ID
2026-08-11T11-57-58__openrouter__deepseek__deepseek-v4-flash-0731__scala_de