# DeepSeek V4.1 Flash 1017 - BenchAudit True Index Profile

**Integrity Profile: Clean Generalization**

> The Verdict: Performs Better on Fresh Private Evals Than Legacy Tests. DeepSeek V4.1 Flash 1017 (evaluated at max effort) outperforms its legacy benchmark standing (48.9p) when moved to private, leak-resistant evaluations (56.0p), posting a -6.4p Low-Tier Boost across 4 matched domains, particularly in Math & Scientific Reasoning (-11.9p boost) and Coding & SWE (-8.0p boost)—a strong indicator of genuine generalization.

- **Canonical URL:** https://benchaudit.org/models/deepseek-v4-1-flash-1017__max/
- **True Index Rank:** #19 of 44
- **Creator:** DeepSeek
- **Weights:** Open Weights
- **Clean Evals Avg (Tiers S & A):** 56.0p (13 evals)
- **Legacy Benchmarks Avg (Tiers C & D):** 48.9p (6 evals)
- **Low-Tier Boost (Matched Delta):** -6.4p
- **Updated:** 2026-11-22

## True Index: Domain Rankings

| Capability Domain | Sub-Rank | Clean Evals (S/A) Avg | Top-Tier Evals |
| --- | ---: | ---: | ---: |
| Agentic & Enterprise | #19 | 59.0p | 3 |
| Coding & SWE | #18 | 61.1p | 4 |
| Math & Scientific Reasoning | #18 | 59.1p | 3 |

## 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 | 3 (59.0p) | 2 (55.6p) | -3.5p |
| Coding & SWE | 4 (61.1p) | 1 (53.1p) | -8.0p |
| General Knowledge & QA | 3 (44.7p) | 1 (39.8p) | -4.9p |
| Math & Scientific Reasoning | 3 (59.1p) | 2 (47.2p) | -11.9p |

## Audited Benchmark Performance of DeepSeek V4.1 Flash 1017

| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
| --- | --- | --- | ---: | ---: |
| [GDPval-AA v2.1](https://benchaudit.org/benchmarks/gdpval-aa-v2-1/) | Public / Aging | Agentic & Enterprise | #9/43 | 77.4p |
| [CyberBench v1.1](https://benchaudit.org/benchmarks/cyberbench/) | Private / Fresh | Coding & SWE | #7/25 | 71.7p |
| [MLCR-AA](https://benchaudit.org/benchmarks/mlcr-aa/) | Private / Fresh | Math & Scientific Reasoning | #15/46 | 71.4p |
| [Code Migration v1.1](https://benchaudit.org/benchmarks/code-migration-v1-1/) | Private / Fresh | Coding & SWE | #8/24 | 68.4p |
| [AA-Briefcase v1.1](https://benchaudit.org/benchmarks/aa-briefcase-v1-1/) | Private / Fresh | Agentic & Enterprise | #18/50 | 65.3p |
| [FrontierCode-AA 2.0](https://benchaudit.org/benchmarks/frontiercode-aa-2-0/) | Private / Fresh | Coding & SWE | #18/46 | 63.9p |
| [AutomationBench-AA](https://benchaudit.org/benchmarks/automationbench-aa/) | Private / Fresh | Agentic & Enterprise | #20/50 | 61.2p |
| [LiveBench](https://benchaudit.org/benchmarks/livebench/) | Private / Fresh | General Knowledge & QA | #15/28 | 60.9p |
| [CritPt v2](https://benchaudit.org/benchmarks/critpt-v2/) | Private / Fresh | Math & Scientific Reasoning | #16/40 | 55.5p |
| [Terminal-Bench-Science 0.1](https://benchaudit.org/benchmarks/terminal-bench-science-0-1/) | Public / Aging | Math & Scientific Reasoning | #21/41 | 53.6p |
| [Terminal-Bench 4.0](https://benchaudit.org/benchmarks/terminal-bench-4-0/) | Public / Aging | Coding & SWE | #24/50 | 53.1p |
| [MKA (Multimodal Knowledge Agent)](https://benchaudit.org/benchmarks/mka/) | Private / Fresh | Agentic & Enterprise | #15/23 | 50.6p |
| [FrontierMath](https://benchaudit.org/benchmarks/frontiermath/) | Private / Fresh | Math & Scientific Reasoning | #16/27 | 50.4p |
| [HLE-Diamond](https://benchaudit.org/benchmarks/hle-diamond/) | Semi-Exposed | General Knowledge & QA | #26/49 | 47.9p |
| [ARC-AGI-2](https://benchaudit.org/benchmarks/arc-agi-2/) | Private / Fresh | General Knowledge & QA | #15/22 | 43.7p |
| [BioMysteryBench](https://benchaudit.org/benchmarks/biomysterybench/) | Public / Aging | Math & Scientific Reasoning | #17/23 | 40.8p |
| [Vibe Code Bench 1-100 v1.1](https://benchaudit.org/benchmarks/vcb-1-100-v1-1/) | Private / Fresh | Coding & SWE | #8/10 | 40.4p |
| [MMMU-Pro](https://benchaudit.org/benchmarks/mmmu-pro/) | Public / Aging | General Knowledge & QA | #13/22 | 39.8p |
| [GDP.pdf](https://benchaudit.org/benchmarks/gdp-pdf/) | Public / Aging | Agentic & Enterprise | #33/50 | 33.7p |
| [AA-Omniscience v1.1](https://benchaudit.org/benchmarks/aa-omniscience-v1-1/) | Private / Fresh | General Knowledge & QA | #34/47 | 29.5p |
| [VIALS-AA](https://benchaudit.org/benchmarks/vials-aa/) | Semi-Exposed | Math & Scientific Reasoning | #17/23 | 27.3p |
