Model · Xiaomi
Xiaomi Mimo Pro v2.5
5 appearances · meta-score 70.4/100 · last seen 2026-07-26 · scored under rubric v15
Pooled composite across 5 primary runs: 62.5 ± 3.5 (95% CI)
- $46.34Total cost
- 506,585,353Tokens
- 83.5%Cache hit
- 7,102Requests
- 4.48%Failure rate
- 1.13Tools/response
- 10,932,453Tokens per $
Agent role scores
| Agent role | Score / 10 |
|---|---|
| Test Agent | 8.18 |
| Sprint-Plan Agent | 8.09 |
| Sprint-Review Agent | 7.70 |
| Scout Agent | 7.52 |
| Build Agent | 7.51 |
| Develop Agent | 7.09 |
| Code-Review Agent | 7.05 |
| Code Agent | 6.93 |
| Pseudocode Agent | 6.92 |
| Orchestrator | 6.16 |
| Architect | 4.24 |
Run history (primary model)
| Run | SoW | Date | Composite |
|---|---|---|---|
| Mimo Pro v2.5 | circles | Jun 2026 | 63.0 |
| Mimo Pro v2.5 | solarSystem | Jun 2026 | 57.6 |
| Mimo Pro v2.5 | circles | Jul 2026 | 64.3 |
| Mimo Pro v2.5 + Mimo | circles | Jul 2026 | 64.3 |
| Mimo Pro v2.5 + Mimo | solarSystem | Jul 2026 | 63.2 |
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.