Model · Xiaomi
Xiaomi Mimo v2.5
3 appearances · meta-score 77.4/100 · last seen 2026-07-22 · scored under rubric v15
Pooled composite across 3 primary runs: 74.0 ± 20.7 (95% CI)
- $9.14Total cost
- 423,506,820Tokens
- 90.5%Cache hit
- 6,086Requests
- 0.05%Failure rate
- 1.05Tools/response
- 46,355,655Tokens per $
Agent role scores
| Agent role | Score / 10 |
|---|---|
| Sprint-Review Agent | 9.26 |
| Architect | 8.46 |
| Orchestrator | 8.43 |
| Develop Agent | 8.41 |
| Sprint-Plan Agent | 7.88 |
| Build Agent | 7.81 |
| Test Agent | 7.41 |
| Code-Review Agent | 7.33 |
| Scout Agent | 7.16 |
| Code Agent | 6.76 |
| Pseudocode Agent | 6.71 |
Run history (primary model)
Also in the roster of
Every run on Favur Evals is scored by the same deterministic engine, on the same Statements of Work. The benchmark is self-funded — no vendor sponsorship, credits, or grants.