69.7%
Accuracy
Run details
- Date
- 2026-06-11
- Test cases
- 564
- Median latency
- 263.43s
- Total cost
- —
- Avg. prompt tokens
- 1,728.9
- Avg. answer tokens
- 1,270.4
- 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 | 76.8% |
| object placements | 71.9% |
| team allocation | 62.0% |
Provenance
- Canonical model
- qwen/qwen3-14b
- Run ID
2026-06-11T14-34-46__openai__qwen3-14b-bf16__musr_de