Individual experiment result
INCLUDE (DE)
Claude Sonnet 5 Anthropic
Exact match reasoning off provider-internal
72.7%
Exact match
Run details
- Date
- 2026-07-21
- Test cases
- 139
- Median latency
- 4.92s
- Total cost
- $0.64
- Avg. prompt tokens
- 229.9
- Avg. answer tokens
- 263.5
- Avg. reasoning tokens
- —
- Quantization
- provider-internal
About this benchmark
INCLUDE-DE v1.2: 107 valid German questions after a blinded semantic audit excluded 32 duplicate, wrong-keyed, non-unique, corrupted, or underspecified source rows consistently; strict final-answer parsing; primary metric exact match.
Provenance
- Canonical model
- anthropic/claude-sonnet-5
- Run ID
2026-07-21T11-51-21__openai__cc__claude-sonnet-5__include_de