Individual experiment result
GermEval NER (DE)
GLM-5.1 Z.ai
Micro-F1 excluding MISC reasoning off fp8
52.2%
Micro-F1 excluding MISC
Run details
- Date
- 2026-06-09
- Test cases
- 1,024
- Median latency
- 2.20s
- Total cost
- $1.71
- Avg. prompt tokens
- 1,127.6
- Avg. answer tokens
- 26.5
- Avg. reasoning tokens
- —
- Quantization
- fp8
About this benchmark
Native German named-entity recognition (person/location/org/misc) emitted as JSON; seqeval micro-F1 excluding MISC.
Provenance
- Canonical model
- z-ai/glm-5.1
- Run ID
2026-06-09T15-18-24__openrouter__z-ai__glm-5.1__germeval_de