True Index: Domain Rankings

Private Top-Tier (S & A) standing across 3 core domains
Agentic & Enterprise39.0p
#34
4 Top-Tier private tests
Coding & SWE49.2p
#27
6 Top-Tier private tests
Math & Scientific Reasoning42.0p
#31
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 & Enterprise39.0p (4)55.5p (2)+16.5p
Coding & SWE49.2p (6)55.1p (1)+5.9p
Math & Scientific Reasoning42.0p (2)33.5p (1)-8.5p
Clean Evals Avg (Tiers S & A)
40.7p
14 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
48.1p
4 public or aging tests
Matched Public Lift (Boost)
+4.7p
Near zero or negative indicates clean generalization
Machine-Readable Export

Audited Benchmark Performance of MiMo-V2.6-Pro

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

Top-Tier Validated Tests (Tiers S & A) (14)

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
Vibe Code Bench 1-100 v1.1Private / FreshCoding & SWE#6/1058.8p
Code2Video-AAPrivate / FreshCoding & SWE#11/2351.9p
AA-Briefcase v1.1Private / FreshAgentic & Enterprise#26/5049.0p
FrontierCode-AA 2.0Private / FreshCoding & SWE#27/4643.5p
MKA (Multimodal Knowledge Agent)Private / FreshAgentic & Enterprise#17/2342.4p
AutomationBench-AAPrivate / FreshAgentic & Enterprise#32/5036.7p
MLCR-AAPrivate / FreshMath & Scientific Reasoning#40/4618.9p
CritPt v2Private / FreshMath & Scientific Reasoning#12/4065.1p
CyberBench v1.1Private / FreshCoding & SWE#9/2564.3p
LiveBenchPrivate / FreshGeneral Knowledge & QA#20/2844.1p
AA-3DPrivate / FreshCoding & SWE#17/2240.8p
Code Migration v1.1Private / FreshCoding & SWE#16/2436.0p
AA-AnalystAgentPrivate / FreshAgentic & Enterprise#20/2428.0p
AA-Omniscience v1.1Private / FreshGeneral Knowledge & QA#38/4720.7p

Mid-Tier Evaluations (Tier B) (2)

Partially exposed or transitional evaluations with moderate leakage risk.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
VIALS-AASemi-ExposedMath & Scientific Reasoning#14/2340.9p
HLE-DiamondSemi-ExposedGeneral Knowledge & QA#43/4911.5p

Legacy & Vulnerable Benchmarks (Tiers C & D) (4)

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
GDPval-AA v2.1Public / AgingAgentic & Enterprise#12/4370.3p
Terminal-Bench 4.0Public / AgingCoding & SWE#23/5055.1p
GDP.pdfPublic / AgingAgentic & Enterprise#30/5040.8p
Terminal-Bench-Science 0.1Public / AgingMath & Scientific Reasoning#29/4133.5p