MiMo-V2-Flash (Reasoning): benchmark results
MiMo-V2-Flash evaluated with reasoning enabled. Provider: Xiaomi. Released 2025-12-16. Access: Open.
Aggregate Rating 1623 ± 17, rank #631 of 2168 rated models, from 121 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 Omniscience - Software Engineering (SWE) - Julia | 36 | Accuracy (%) | 94.5 |
| Tau2-Bench Telecom | 95.03 | Success Rate (%) | 93.9 |
| AA TAU-2 Bench | 95.03 | Accuracy (%) | 93.8 |
| AA MMLU-Pro | 84.34 | Accuracy (%) | 89.1 |
| AA Omniscience - Software Engineering (SWE) - R | 28 | Accuracy (%) | 87.2 |
| UGI - Natural Intelligence | 43.12 | NatInt Score | 86 |
| AA Omniscience - Software Engineering (SWE) - Go | 32 | Accuracy (%) | 85.5 |
| AA Omniscience - Software Engineering (SWE) - Dart | 30 | Accuracy (%) | 85.2 |
| UGI Leaderboard | 48 | UGI Score | 85.1 |
| AA Omniscience - Software Engineering (SWE) - Rust | 62 | Accuracy (%) | 84 |
Interactive version: theaggregate.ai/model?slug=mimo-v2-flash-reasoning · How It Works · Data refreshed daily, snapshot 2026-10-20.