83.2%
Exact match
Run details
- Date
- 2026-08-30
- Test cases
- 107
- Median latency
- 2.73s
- Total cost
- —
- Avg. prompt tokens
- 147
- Avg. answer tokens
- 150.3
- Avg. reasoning tokens
- —
- 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
- tencent/hy3
- Run ID
2026-08-30T19-46-08__Tencent__tencent__hy3__include_de