True Index: Domain Rankings
Agentic & Enterprise59.0p
#19
3 Top-Tier private testsCoding & SWE61.1p
#18
4 Top-Tier private testsMath & Scientific Reasoning59.1p
#18
3 Top-Tier private testsHead-to-Head: Clean Evals vs. Legacy Benchmarks
| Capability Domain | Clean Evals (Tiers S & A) | Legacy Benchmarks (Tiers C & D) | Public Lift (Boost) |
|---|---|---|---|
| Agentic & Enterprise | 59.0p | 55.6p | -3.5p |
| Coding & SWE | 61.1p | 53.1p | -8.0p |
| General Knowledge & QA | 44.7p | 39.8p | -4.9p |
| Math & Scientific Reasoning | 59.1p | 47.2p | -11.9p |
Clean Evals Avg (Tiers S & A)
56.0p
13 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
48.9p
6 public or aging tests
Matched Public Lift (Boost)
-6.4p
Near zero or negative indicates clean generalization
Machine-Readable Export
Audited Benchmark Performance of DeepSeek V4.1 Flash 1017
Grouped by benchmark integrity so private capability signal stands apart from aging public tests.
Top-Tier Validated Tests (Tiers S & A) (13)
Private, leak-resistant tests that build real capability signal.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| MLCR-AA | Private / Fresh | Math & Scientific Reasoning | #15/46 | 71.4p |
| AA-Briefcase v1.1 | Private / Fresh | Agentic & Enterprise | #18/50 | 65.3p |
| FrontierCode-AA 2.0 | Private / Fresh | Coding & SWE | #18/46 | 63.9p |
| AutomationBench-AA | Private / Fresh | Agentic & Enterprise | #20/50 | 61.2p |
| MKA (Multimodal Knowledge Agent) | Private / Fresh | Agentic & Enterprise | #15/23 | 50.6p |
| FrontierMath | Private / Fresh | Math & Scientific Reasoning | #16/27 | 50.4p |
| Vibe Code Bench 1-100 v1.1 | Private / Fresh | Coding & SWE | #8/10 | 40.4p |
| CyberBench v1.1 | Private / Fresh | Coding & SWE | #7/25 | 71.7p |
| Code Migration v1.1 | Private / Fresh | Coding & SWE | #8/24 | 68.4p |
| LiveBench | Private / Fresh | General Knowledge & QA | #15/28 | 60.9p |
| CritPt v2 | Private / Fresh | Math & Scientific Reasoning | #16/40 | 55.5p |
| ARC-AGI-2 | Private / Fresh | General Knowledge & QA | #15/22 | 43.7p |
| AA-Omniscience v1.1 | Private / Fresh | General Knowledge & QA | #34/47 | 29.5p |
Mid-Tier Evaluations (Tier B) (2)
Partially exposed or transitional evaluations with moderate leakage risk.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| HLE-Diamond | Semi-Exposed | General Knowledge & QA | #26/49 | 47.9p |
| VIALS-AA | Semi-Exposed | Math & Scientific Reasoning | #17/23 | 27.3p |
Legacy & Vulnerable Benchmarks (Tiers C & D) (6)
Public or aging benchmarks prone to overfitting and training-data leaks.
| Benchmark | Benchmark Integrity Status | Domain | Rank | Percentile |
|---|---|---|---|---|
| GDPval-AA v2.1 | Public / Aging | Agentic & Enterprise | #9/43 | 77.4p |
| Terminal-Bench-Science 0.1 | Public / Aging | Math & Scientific Reasoning | #21/41 | 53.6p |
| Terminal-Bench 4.0 | Public / Aging | Coding & SWE | #24/50 | 53.1p |
| BioMysteryBench | Public / Aging | Math & Scientific Reasoning | #17/23 | 40.8p |
| GDP.pdf | Public / Aging | Agentic & Enterprise | #33/50 | 33.7p |
| MMMU-Pro | Public / Aging | General Knowledge & QA | #13/22 | 39.8p |