83.5%
Accuracy
Run details
- Date
- 2026-06-11
- Test cases
- 564
- Median latency
- 23.30s
- Total cost
- $0.23
- Avg. prompt tokens
- 1,477.9
- Avg. answer tokens
- 650.1
- Avg. reasoning tokens
- —
- Quantization
- bf16
About this benchmark
German MuSR v1.1 defect-filtered benchmark: 553 questions (11 truncated team-allocation translations excluded), generate_until cot+; primary metric accuracy.
Subject breakdown
| Subject | Score |
|---|---|
| murder mystery | 86.4% |
| object placements | 76.6% |
| team allocation | 82.4% |
Provenance
- Canonical model
- google/gemma-4-31b-it
- Run ID
2026-06-11T14-02-37__openai__gemma-4-31b-it-bf16__musr_de