MiMo-V2.5-Pro (Reasoning): benchmark results
Provider: Xiaomi. Released 2026-04-23. Access: Open.
Aggregate Rating 1634 ± 23, rank #603 of 2257 rated models, from 55 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 79.86 | Accuracy (%) | 98 |
| AA-Omniscience Hallucination Rate | 24.7 | Hallucination Rate (%) | 96.1 |
| UGI Leaderboard | 53.15 | UGI Score | 94.4 |
| AA TAU-2 Bench | 94.15 | Accuracy (%) | 92 |
| UGI - Writing | 57.42 | Writing Score | 90.5 |
| AA Terminal-Bench Hard | 43.18 | Accuracy (%) | 90.3 |
| UGI - Natural Intelligence | 52.58 | NatInt Score | 89.1 |
| AA Long Context Reasoning | 79.67 | Accuracy (%) | 82.6 |
| AA GPQA Diamond | 86.57 | Accuracy (%) | 81.5 |
| AA Humanity's Last Exam | 35.68 | Accuracy (%) | 80.6 |
| AA Omniscience | 3.25 | Score | 78 |
| AA CritPt | 4 | Accuracy (%) | 66.9 |
Interactive version: theaggregate.ai/model?slug=mimo-v2-5-pro-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-17.