Individual experiment result
GermEval NER (DE)
Claude Fable 5 Anthropic
Micro-F1 excluding MISC reasoning on / locked provider-internal
87.7%
Micro-F1 excluding MISC
Run details
- Date
- 2026-07-06
- Test cases
- 1,024
- Median latency
- 5.52s
- Total cost
- $30.07
- Avg. prompt tokens
- 2,083.6
- Avg. answer tokens
- 76.1
- Avg. reasoning tokens
- —
- Quantization
- provider-internal
About this benchmark
Native German named-entity recognition (person/location/org/misc) emitted as JSON; seqeval micro-F1 excluding MISC.
Provenance
- Canonical model
- anthropic/claude-fable-5
- Run ID
2026-07-06T09-11-10__openai__cc__claude-fable-5__germeval_de