Individual experiment result
INCLUDE (DE)
Muse Spark Open Meta
Exact match reasoning on / locked provider-internal
86.9%
Exact match
Run details
- Date
- 2026-10-15
- Test cases
- 107
- Median latency
- 5.46s
- Total cost
- $0.27
- Avg. prompt tokens
- 246.9
- Avg. answer tokens
- 137.8
- Avg. reasoning tokens
- 407.6
- 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
- meta/muse-spark-open
- Run ID
2026-10-15T22-21-50__openrouter__meta__muse-spark-open__include_de