True Index: Domain Rankings

Private Top-Tier (S & A) standing across 3 core domains
Agentic & Enterprise69.4p
#15
4 Top-Tier private tests
Coding & SWE57.2p
#21
2 Top-Tier private tests
Math & Scientific Reasoning70.2p
#13
3 Top-Tier private tests

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

4 matched domains · positive boost means higher legacy scores
Capability Domain Clean Evals (Tiers S & A) Legacy Benchmarks (Tiers C & D) Public Lift (Boost)
Agentic & Enterprise69.4p (4)95.9p (2)+26.5p
Coding & SWE57.2p (2)100.0p (1)+42.8p
General Knowledge & QA64.2p (2)61.3p (1)-3.0p
Math & Scientific Reasoning70.2p (3)71.2p (2)+1.0p
Clean Evals Avg (Tiers S & A)
65.3p
11 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
82.1p
6 public or aging tests
Matched Public Lift (Boost)
+20.3p
Near zero or negative indicates clean generalization
Machine-Readable Export

Audited Benchmark Performance of Kimi K3.1 Pro

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

Top-Tier Validated Tests (Tiers S & A) (11)

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
MLCR-AAPrivate / FreshMath & Scientific Reasoning#5/4691.3p
AA-Briefcase v1.1Private / FreshAgentic & Enterprise#7/5087.8p
AutomationBench-AAPrivate / FreshAgentic & Enterprise#7/5087.8p
MKA (Multimodal Knowledge Agent)Private / FreshAgentic & Enterprise#11/2366.9p
FrontierMathPrivate / FreshMath & Scientific Reasoning#14/2761.5p
FrontierCode-AA 2.0Private / FreshCoding & SWE#24/4650.4p
AA-Omniscience v1.1Private / FreshGeneral Knowledge & QA#15/4771.0p
AA-3DPrivate / FreshCoding & SWE#11/2264.0p
CritPt v2Private / FreshMath & Scientific Reasoning#15/4057.9p
LiveBenchPrivate / FreshGeneral Knowledge & QA#16/2857.5p
AA-AnalystAgentPrivate / FreshAgentic & Enterprise#18/2435.1p

Mid-Tier Evaluations (Tier B) (2)

Partially exposed or transitional evaluations with moderate leakage risk.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
HLE-DiamondSemi-ExposedGeneral Knowledge & QA#18/4964.6p
VIALS-AASemi-ExposedMath & Scientific Reasoning#13/2345.5p

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

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
Terminal-Bench 4.0Public / AgingCoding & SWE#1/50100.0p
GDP.pdfPublic / AgingAgentic & Enterprise#2/5098.0p
GDPval-AA v2.1Public / AgingAgentic & Enterprise#2/4393.8p
BioMysteryBenchPublic / AgingMath & Scientific Reasoning#9/2372.6p
Terminal-Bench-Science 0.1Public / AgingMath & Scientific Reasoning#15/4169.8p
MMMU-ProPublic / AgingGeneral Knowledge & QA#8/2261.3p