MiMo-V2-Flash (Reasoning) — benchmark results
MiMo-V2-Flash evaluated with reasoning enabled. Provider: Xiaomi. Released 2026-01-01. Access: Open.
Unified ELO 1763 ± 34, rank #173 of 1776 rated models, from 60 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA AIME 2025 | 96.33 | Accuracy (%) | 97.8 |
| AA LiveCodeBench | 86.77 | Pass@1 (%) | 97.5 |
| AA TAU-2 Bench | 95.03 | Accuracy (%) | 93.8 |
| AA MMLU-Pro | 84.34 | Accuracy (%) | 89.2 |
| UGI - Natural Intelligence | 43.12 | NatInt Score | 88.3 |
| UGI Leaderboard | 48 | UGI Score | 86.3 |
| UGI - Writing | 44.85 | Writing Score | 85.8 |
| AA Omniscience - Software Engineering (SWE) - Julia | 36 | Accuracy (%) | 84.6 |
| AA CritPt | 4.29 | Accuracy (%) | 84.1 |
| AA GPQA Diamond | 84.65 | Accuracy (%) | 83 |
| AA Humanity's Last Exam | 21.13 | Accuracy (%) | 81.4 |
| AA Global-MMLU-Lite - Korean | 87.58 | Accuracy (%) | 78.3 |
Interactive version: theaggregate.ai/model?slug=mimo-v2-flash-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.