# MiMo-V2.6-Flash - BenchAudit True Index Profile

**Integrity Profile: Clean Generalization**

> The Verdict: Performs Better on Fresh Private Evals Than Legacy Tests. MiMo-V2.6-Flash (evaluated at default effort) outperforms its legacy benchmark standing (23.5p) when moved to private, leak-resistant evaluations (27.8p), posting a -3.6p Low-Tier Boost across 4 matched domains, particularly in Agentic & Enterprise (-24.8p boost) and Coding & SWE (-13.0p boost)—a strong indicator of genuine generalization.

- **Canonical URL:** https://benchaudit.org/models/mimo-v2-6-flash/
- **True Index Rank:** #37 of 44
- **Creator:** Xiaomi
- **Weights:** Open Weights
- **Clean Evals Avg (Tiers S & A):** 27.8p (10 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 23.5p (6 evals)
- **Low-Tier Boost (Matched Delta):** -3.6p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #24 | 49.0p | 2 |
| Coding & SWE | #31 | 43.6p | 5 |
| Math & Scientific Reasoning | #42 | 13.4p | 2 |

## Head-to-Head: Clean Evals vs. Legacy Benchmarks

| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | 2 (49.0p) | 2 (24.2p) | -24.8p |
| Coding & SWE | 5 (43.6p) | 1 (30.6p) | -13.0p |
| General Knowledge & QA | 1 (5.3p) | 1 (1.0p) | -4.3p |
| Math & Scientific Reasoning | 2 (13.4p) | 2 (38.0p) | +24.6p |

## Audited Benchmark Performance of MiMo-V2.6-Flash

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [CyberBench v1.1](https://benchaudit.org/benchmarks/cyberbench/) | Private / Fresh | Coding & SWE | #6/25 | 74.7p |
| [Code2Video-AA](https://benchaudit.org/benchmarks/code2video-aa/) | Private / Fresh | Coding & SWE | #10/23 | 55.6p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #24/50 | 53.1p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #14/23 | 48.8p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #28/50 | 44.9p |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #23/43 | 44.4p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #30/46 | 36.8p |
| [Vibe Code Bench 1-100 v1.1](https://benchaudit.org/benchmarks/vcb-1-100-v1-1/) | Private / Fresh | Coding & SWE | #9/10 | 31.2p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #35/50 | 30.6p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #31/41 | 27.1p |
| [Code Migration v1.1](https://benchaudit.org/benchmarks/code-migration-v1-1/) | Private / Fresh | Coding & SWE | #20/24 | 19.8p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #33/40 | 15.2p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #43/46 | 11.6p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #45/49 | 8.3p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #45/47 | 5.3p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #48/50 | 4.1p |
| [MMMU-Pro](https://benchaudit.org/benchmarks/mmmu-pro/) | Public / Aging | General Knowledge & QA | #22/22 | 1.0p |
