Individual experiment result
SB10K (DE)
Claude Opus 4.8 Anthropic
Matthews correlation coefficient reasoning off provider-internal
64.5%
Matthews correlation coefficient
Run details
- Date
- 2026-06-13
- Test cases
- 1,024
- Median latency
- 1.88s
- Total cost
- $7.16
- Avg. prompt tokens
- 1,372.7
- Avg. answer tokens
- 5
- 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
- anthropic/claude-opus-4.8
- Run ID
2026-06-13T12-15-43__openai__cc__claude-opus-4-8__sb10k_de