True Index: Domain Rankings

Private Top-Tier (S & A) standing across 3 core domains
Agentic & Enterprise54.2p
#21
4 Top-Tier private tests
Coding & SWE47.8p
#28
4 Top-Tier private tests
Math & Scientific Reasoning45.0p
#25
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 & Enterprise54.2p (4)72.8p (2)+18.6p
Coding & SWE47.8p (4)50.0p (1)+2.2p
Math & Scientific Reasoning45.0p (3)44.7p (1)-0.3p
Clean Evals Avg (Tiers S & A)
49.6p
13 private, leak-resistant tests
Legacy Benchmarks Avg (Tiers C & D)
55.8p
4 public or aging tests
Matched Public Lift (Boost)
+16.2p
Near zero or negative indicates clean generalization
Machine-Readable Export

Audited Benchmark Performance of Muse Spark 1.3

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.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
Harvey LAB-AA v1.1Private / FreshAgentic & Enterprise#7/2182.6p
AA-Briefcase v1.1Private / FreshAgentic & Enterprise#15/5071.4p
FrontierMathPrivate / FreshMath & Scientific Reasoning#16/2750.4p
FrontierCode-AA 2.0Private / FreshCoding & SWE#29/4639.1p
AutomationBench-AAPrivate / FreshAgentic & Enterprise#33/5034.7p
Code2Video-AAPrivate / FreshCoding & SWE#16/2333.6p
MLCR-AAPrivate / FreshMath & Scientific Reasoning#37/4624.2p
CritPt v2Private / FreshMath & Scientific Reasoning#14/4060.3p
AA-3DPrivate / FreshCoding & SWE#12/2260.1p
CyberBench v1.1Private / FreshCoding & SWE#11/2558.3p
AA-Omniscience v1.1Private / FreshGeneral Knowledge & QA#22/4755.7p
LiveBenchPrivate / FreshGeneral Knowledge & QA#19/2847.5p
AA-AnalystAgentPrivate / FreshAgentic & Enterprise#20/2428.0p

Mid-Tier Evaluations (Tier B) (1)

Partially exposed or transitional evaluations with moderate leakage risk.

BenchmarkBenchmark Integrity StatusDomainRankPercentile
HLE-DiamondSemi-ExposedGeneral Knowledge & QA#19/4962.5p

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

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

BenchmarkBenchmark Integrity StatusDomainRankPercentile
GDP.pdfPublic / AgingAgentic & Enterprise#12/5077.6p
GDPval-AA v2.1Public / AgingAgentic & Enterprise#13/4367.9p
Terminal-Bench 4.0Public / AgingCoding & SWE#25/5050.0p
Terminal-Bench-Science 0.1Public / AgingMath & Scientific Reasoning#25/4144.7p