Individual experiment result
INCLUDE (DE)
DeepSeek V4 Pro 0813 DeepSeek
Exact match reasoning off provider-internal
87.9%
Exact match
Run details
- Date
- 2026-08-13
- Test cases
- 107
- Median latency
- 2.24s
- Total cost
- $0.01
- Avg. prompt tokens
- 121.2
- Avg. answer tokens
- 93.8
- 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
- deepseek/deepseek-v4-pro-0813
- Run ID
2026-08-13T13-49-58__openrouter__deepseek__deepseek-v4-pro-0813__include_de