Individual experiment result
MuSR (DE)
MiMo V2.6 Pro Xiaomi
Accuracy reasoning off provider-internal
83.5%
Accuracy
Run details
- Date
- 2026-10-16
- Test cases
- 553
- Median latency
- 26.88s
- Total cost
- —
- Avg. prompt tokens
- 1,743.4
- Avg. answer tokens
- 981.4
- Avg. reasoning tokens
- —
- Quantization
- provider-internal
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 | 83.6% |
| object placements | 73.4% |
| team allocation | 86.2% |
Provenance
- Canonical model
- xiaomi/mimo-v2.6-pro
- Run ID
2026-10-16T17-44-26__openrouter__xiaomi__mimo-v2.6-pro__musr_de