# MiMo-V2-Flash Benchmark Scores & Performance

> MiMo-V2-Flash by Xiaomi scores 41/100 overall, ranking #135 out of 954 AI models.

Canonical page: https://benchlm.ai/models/mimo-v2-flash

Last updated: October 17, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Xiaomi |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | 41/100 |
| Overall Rank | #135 of 954 |

## Family & Coverage

- Family: MiMo-V2-Flash
- Variant: base
- Benchmarks covered: 21 of 639
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [τ²-bench results](/benchmarks/tau2-bench) | 83.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 6.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [GDPval-AA](/benchmarks/gdpvalaa) | 788 | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [SWE-bench Verified](/benchmarks/swe-bench-verified) | 73.4% | [Xiaomi MiMo-V2-Flash](https://github.com/XiaomiMiMo/MiMo-V2-Flash) |
| [LiveCodeBench v6](/benchmarks/livecodebench-v6) | 80.6% | [MiMo-V2-Flash model card](https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash) |
| [SWE Multilingual](/benchmarks/swe-bench-multilingual) | 71.7% | [MiMo-V2-Flash model card](https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash) |
| [AA Coding Index](/benchmarks/aacodingindex) | 49.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [LongBench v2](/benchmarks/longbench-v2) | 60.6% | [MiMo-V2-Flash model card](https://huggingface.co/XiaomiMiMo/MiMo-V2-Flash) |
| [AA-LCR](/benchmarks/lcr) | 36.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [CritPt](/benchmarks/critpt) | 0.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GPQA](/benchmarks/gpqa) | 83.7% | [Reported upstream source](https://mimo.xiaomi.com/blog/mimo-v2-flash) |
| [MMLU-Pro](/benchmarks/mmlu-pro) | 84.9% | [Reported upstream source](https://mimo.xiaomi.com/blog/mimo-v2-flash) |
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 16.1% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [AA-GPQA Diamond](/benchmarks/gpqa-diamond) | 65.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [AA-HLE](/benchmarks/aahle) | 8.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -48.4% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 15.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 76.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |
| [GPQA Diamond (Vals)](/benchmarks/gpqa-diamond) | 59.3% | [Vals AI: GPQA Diamond leaderboard](https://www.vals.ai/models/xiaomi_mimo-v2-flash) |

## Instruction Following Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-IFBench](/benchmarks/ifbench) | 39.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/mimo-v2-flash) |

## Mathematics Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AIME 2025](/benchmarks/aime2025) | 94.1% | [Reported upstream source](https://mimo.xiaomi.com/blog/mimo-v2-flash) |

## Other Xiaomi Models

- [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) - Score: 73.57
- [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) - Score: 64.51
- [MiMo-V2-Pro](/models/mimo-v2-pro) - Score: 52.98
- [MiMo-V2.5-Pro](/models/mimo-v2-5-pro) - Score: 52.97
- [MiMo-V2-Omni](/models/mimo-v2-omni) - Score: 50
- [MiMo-V2.5](/models/mimo-v2-5) - Score: not computed