Individual experiment result
INCLUDE (DE)
MiniMax M2.7 MiniMax
Exact match reasoning on / locked fp8
72.7%
Exact match
Run details
- Date
- Not recorded
- Test cases
- 139
- Median latency
- —
- Total cost
- —
- Avg. prompt tokens
- —
- Avg. answer tokens
- 356.6
- Avg. reasoning tokens
- 816.9
- Quantization
- fp8
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
- minimax/minimax-m2.7
- Run ID
2026-06-08T13-30-45__openrouter__minimax__minimax-m2.7__include_de