Individual experiment result
ScaLA (DE)
Nemotron 3.5 Bolt 74B-A9B (IQ2) NVIDIA
Matthews correlation coefficient reasoning off iq2
58.9%
Matthews correlation coefficient
Run details
- Date
- 2026-10-15
- Test cases
- 2,048
- Median latency
- 5.81s
- Total cost
- —
- Avg. prompt tokens
- 989.9
- Avg. answer tokens
- 2.6
- Avg. reasoning tokens
- —
- Quantization
- iq2
About this benchmark
Native German linguistic acceptability — is the sentence grammatical (ja/nein)? generate_until; primary metric MCC (accuracy recorded as secondary).
Provenance
- Canonical model
- nvidia/nemotron-3.5-bolt-74b-a9b-iq2
- Run ID
2026-10-15T20-41-09__openai__nvidia__NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB__scala_de