True Index: Domain Rankings

Private Top-Tier (S & A) standing across 3 core domains
Agentic & Enterprise79.5p
#9
4 Top-Tier private tests
Coding & SWE64.4p
#16
4 Top-Tier private tests
Math & Scientific Reasoning66.2p
#16
3 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 & Enterprise79.5p (4)86.9p (2)+7.4p
Coding & SWE64.4p (4)71.8p (2)+7.4p
Math & Scientific Reasoning66.2p (3)47.8p (2)-18.4p
Clean Evals Avg (Tiers S & A)
68.1p
12 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
68.9p
6 public or aging tests
Matched Public Lift (Boost)
-7.4p
Near zero or negative indicates clean generalization
Machine-Readable Export

Audited Benchmark Performance of Muse Wonder

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

Top-Tier Validated Tests (Tiers S & A) (12)

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
Harvey LAB-AA v1.1Private / FreshAgentic & Enterprise#4/2193.9p
AA-Briefcase v1.1Private / FreshAgentic & Enterprise#9/5083.7p
MKA (Multimodal Knowledge Agent)Private / FreshAgentic & Enterprise#10/2371.0p
AutomationBench-AAPrivate / FreshAgentic & Enterprise#16/5069.4p
FrontierMathPrivate / FreshMath & Scientific Reasoning#13/2764.6p
MLCR-AAPrivate / FreshMath & Scientific Reasoning#19/4661.9p
FrontierCode-AA 2.0Private / FreshCoding & SWE#19/4661.6p
Code2Video-AAPrivate / FreshCoding & SWE#17/2330.0p
CyberBench v1.1Private / FreshCoding & SWE#1/2589.6p
Code Migration v1.1Private / FreshCoding & SWE#6/2476.4p
CritPt v2Private / FreshMath & Scientific Reasoning#9/4072.2p
AA-Omniscience v1.1Private / FreshGeneral Knowledge & QA#19/4762.3p

Mid-Tier Evaluations (Tier B) (2)

Partially exposed or transitional evaluations with moderate leakage risk.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
HLE-DiamondSemi-ExposedGeneral Knowledge & QA#17/4966.7p
VIALS-AASemi-ExposedMath & Scientific Reasoning#11/2354.5p

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

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
GDP.pdfPublic / AgingAgentic & Enterprise#5/5091.8p
GDPval-AA v2.1Public / AgingAgentic & Enterprise#7/4382.0p
SWE-bench Pro V2Public / AgingCoding & SWE#3/873.3p
Terminal-Bench 4.0Public / AgingCoding & SWE#15/5070.4p
Terminal-Bench-Science 0.1Public / AgingMath & Scientific Reasoning#17/4164.8p
BioMysteryBenchPublic / AgingMath & Scientific Reasoning#19/2330.8p