Individual experiment result
SB10K (DE)
DeepSeek V4 Pro 0813 DeepSeek
Matthews correlation coefficient reasoning off provider-internal
60.8%
Matthews correlation coefficient
Run details
- Date
- 2026-08-13
- Test cases
- 1,024
- Median latency
- 1.35s
- Total cost
- $0.35
- Avg. prompt tokens
- 778.6
- Avg. answer tokens
- 1.7
- Avg. reasoning tokens
- —
- Quantization
- provider-internal
About this benchmark
Native German Twitter sentiment (positive/neutral/negative), generate_until variant; primary metric MCC.
Provenance
- Canonical model
- deepseek/deepseek-v4-pro-0813
- Run ID
2026-08-13T09-02-33__openrouter__deepseek__deepseek-v4-pro-0813__sb10k_de