True Index: Domain Rankings

Private Top-Tier (S & A) standing across 3 core domains
Agentic & Enterprise41.4p
#33
4 Top-Tier private tests
Coding & SWE59.2p
#20
1 Top-Tier private test
Math & Scientific Reasoning44.1p
#28
2 Top-Tier private tests

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

3 matched domains · positive boost means higher legacy scores
Capability Domain Clean Evals (Tiers S & A) Legacy Benchmarks (Tiers C & D) Public Lift (Boost)
Agentic & Enterprise41.4p (4)27.9p (2)-13.5p
Coding & SWE59.2p (1)40.8p (1)-18.4p
Math & Scientific Reasoning44.1p (2)68.9p (2)+24.8p
Clean Evals Avg (Tiers S & A)
48.3p
7 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
39.0p
6 public or aging tests
Matched Public Lift (Boost)
-6.9p
Near zero or negative indicates clean generalization
Machine-Readable Export

Audited Benchmark Performance of DeepSeek V4.1 Flash

Grouped by benchmark integrity so private capability signal stands apart from aging public tests.

Top-Tier Validated Tests (Tiers S & A) (7)

Private, leak-resistant tests that build real capability signal.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
AutomationBench-AAPrivate / FreshAgentic & Enterprise#14/5073.5p
MLCR-AAPrivate / FreshMath & Scientific Reasoning#17/4667.1p
Code2Video-AAPrivate / FreshCoding & SWE#9/2359.2p
Harvey LAB-AA v1.1Private / FreshAgentic & Enterprise#17/2144.8p
AA-Briefcase v1.1Private / FreshAgentic & Enterprise#37/5026.5p
CritPt v2Private / FreshMath & Scientific Reasoning#30/4021.2p
AA-AnalystAgentPrivate / FreshAgentic & Enterprise#22/2420.9p

Mid-Tier Evaluations (Tier B) (1)

Partially exposed or transitional evaluations with moderate leakage risk.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
HLE-DiamondSemi-ExposedGeneral Knowledge & QA#36/4927.1p

Legacy & Vulnerable Benchmarks (Tiers C & D) (6)

Public or aging benchmarks prone to overfitting and training-data leaks.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
HealthBenchPublic / AgingMath & Scientific Reasoning#2/1698.1p
Terminal-Bench 4.0Public / AgingCoding & SWE#30/5040.8p
Terminal-Bench-Science 0.1Public / AgingMath & Scientific Reasoning#27/4139.7p
GDPval-AA v2.1Public / AgingAgentic & Enterprise#26/4337.4p
GDP.pdfPublic / AgingAgentic & Enterprise#41/5018.4p
MMMU-ProPublic / AgingGeneral Knowledge & QA#18/2218.2p